# Robot Skill Hub > Pinned robot code, environment contracts and preparation commands for coding agents. - [Catalog JSON](https://hub.superfastrobotics.com/catalog/v1/index.json): canonical records with bundled recipes - [Official source examples JSON](https://hub.superfastrobotics.com/catalog/v1/references.json): pinned upstream examples; no hub preparation adapter - [Publication manifest](https://hub.superfastrobotics.com/catalog/v1/publication.json): published versions and submission receipts - [Agent quickstart](https://hub.superfastrobotics.com/agent-quickstart.md): find, inspect and prepare commands - [Full documentation](https://hub.superfastrobotics.com/llms-full.txt): quickstart, contracts and every recipe in plain text - [Record schema](https://hub.superfastrobotics.com/schemas/skill.schema.json) - [Compatibility contract](https://hub.superfastrobotics.com/compatibility.md) - [Contribution contract](https://hub.superfastrobotics.com/contributing.md) ## Recipes - [ManiSkill panda LiftPegUpright-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-panda-lift-peg-upright/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-lift-peg-upright/skill.json)) - [ManiSkill panda_wristcam PegInsertionSide-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-panda-peg-insertion-side/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-peg-insertion-side/skill.json)) - [ManiSkill Panda PickCube Python recipe](https://hub.superfastrobotics.com/skills/maniskill-panda-pick-cube/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-pick-cube/skill.json)) - [ManiSkill panda PlaceSphere-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-panda-place-sphere/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-place-sphere/skill.json)) - [ManiSkill panda_wristcam PlugCharger-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-panda-plug-charger/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-plug-charger/skill.json)) - [ManiSkill panda PullCubeTool-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-panda-pull-cube-tool/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-pull-cube-tool/skill.json)) - [ManiSkill panda PullCube-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-panda-pull-cube/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-pull-cube/skill.json)) - [ManiSkill panda PushCube-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-panda-push-cube/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-push-cube/skill.json)) - [ManiSkill Panda StackCube Python recipe](https://hub.superfastrobotics.com/skills/maniskill-panda-stack-cube/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-stack-cube/skill.json)) - [ManiSkill panda StackPyramid-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-panda-stack-pyramid/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-stack-pyramid/skill.json)) - [ManiSkill panda_stick DrawSVG-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-panda-stick-draw-svg/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-stick-draw-svg/skill.json)) - [ManiSkill panda_stick DrawTriangle-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-panda-stick-draw-triangle/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-panda-stick-draw-triangle/skill.json)) - [ManiSkill so100 PickCubeSO100-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-so100-pick-cube/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-so100-pick-cube/skill.json)) - [ManiSkill xarm6_robotiq PickCube-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-xarm6-pick-cube/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-xarm6-pick-cube/skill.json)) - [ManiSkill xarm6_robotiq PlugCharger-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-xarm6-plug-charger/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-xarm6-plug-charger/skill.json)) - [ManiSkill xarm6_robotiq PushCube-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-xarm6-push-cube/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-xarm6-push-cube/skill.json)) - [ManiSkill xarm6_robotiq StackCube-v1 motion planner](https://hub.superfastrobotics.com/skills/maniskill-xarm6-stack-cube/README.md) ([JSON](https://hub.superfastrobotics.com/skills/maniskill-xarm6-stack-cube/skill.json)) ## Official source examples - [MuJoCo minimal interactive simulator](https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/sample/basic.cc): mujoco; Apache-2.0; source reference only - [MuJoCo model format conversion](https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/sample/compile.cc): mujoco; Apache-2.0; source reference only - [MuJoCo MJX tutorial](https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/mjx/tutorial.ipynb): mujoco; Apache-2.0; source reference only - [MuJoCo offscreen trajectory recording](https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/sample/record.cc): mujoco; Apache-2.0; source reference only - [MuJoCo full interactive simulator](https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/simulate/main.cc): mujoco; Apache-2.0; source reference only - [MuJoCo simulation benchmark sample](https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/sample/testspeed.cc): mujoco; Apache-2.0; source reference only - [MuJoCo Python tutorial](https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/python/tutorial.ipynb): mujoco; Apache-2.0; source reference only - [MuJoCo Python interactive viewer](https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/python/mujoco/viewer.py): mujoco; Apache-2.0; source reference only - [PyBullet batch ray casting](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/batchRayCast.py): pybullet; Zlib; source reference only - [PyBullet collision filtering](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/collisionFilter.py): pybullet; Zlib; source reference only - [PyBullet articulated constraints](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/constraint.py): pybullet; Zlib; source reference only - [PyBullet contact friction](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/contactFriction.py): pybullet; Zlib; source reference only - [PyBullet force torque sensing](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/forcetorquesensor.py): pybullet; Zlib; source reference only - [PyBullet simulation quickstart](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/hello_pybullet.py): pybullet; Zlib; source reference only - [PyBullet humanoid knee control](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/humanoid_knee_position_control.py): pybullet; Zlib; source reference only - [PyBullet end-effector orientation IK](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/ik_end_effector_orientation.py): pybullet; Zlib; source reference only - [PyBullet inverse dynamics](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/inverse_dynamics.py): pybullet; Zlib; source reference only - [PyBullet KUKA inverse kinematics](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/inverse_kinematics.py): pybullet; Zlib; source reference only - [PyBullet Jacobian computation](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/jacobian.py): pybullet; Zlib; source reference only - [PyBullet KUKA grasp log playback](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/kuka_grasp_block_playback.py): pybullet; Zlib; source reference only - [PyBullet KUKA and cube interaction](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/kuka_with_cube.py): pybullet; Zlib; source reference only - [PyBullet PD control comparison](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/pdControl.py): pybullet; Zlib; source reference only - [PyBullet depth to point cloud](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/pointCloudFromCameraImage.py): pybullet; Zlib; source reference only - [PyBullet quadruped simulation](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/quadruped.py): pybullet; Zlib; source reference only - [PyBullet racecar control](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/racecar.py): pybullet; Zlib; source reference only - [PyBullet differential racecar](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/racecar_differential.py): pybullet; Zlib; source reference only - [PyBullet interactive robot joint control](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/robotcontrol.py): pybullet; Zlib; source reference only - [PyBullet save and restore state](https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/saveRestoreState.py): pybullet; Zlib; source reference only - [robosuite collect and replay data](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_collect_and_playback_data.py): robosuite; MIT; source reference only - [robosuite composite robot](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_composite_robot.py): robosuite; MIT; source reference only - [robosuite controller demonstration](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_control.py): robosuite; MIT; source reference only - [robosuite device teleoperation](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_device_control.py): robosuite; MIT; source reference only - [robosuite domain randomization](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_domain_randomization.py): robosuite; MIT; source reference only - [robosuite gripper interaction](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_gripper_interaction.py): robosuite; MIT; source reference only - [robosuite gripper selection](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_gripper_selection.py): robosuite; MIT; source reference only - [robosuite Gym wrapper](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_gym_functionality.py): robosuite; MIT; source reference only - [robosuite random action environment](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_random_action.py): robosuite; MIT; source reference only - [robosuite segmentation observations](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_segmentation.py): robosuite; MIT; source reference only - [robosuite sensor corruption](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_sensor_corruption.py): robosuite; MIT; source reference only - [robosuite video recording](https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_video_recording.py): robosuite; MIT; source reference only --- Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` --- # Find and prepare robot manipulation code Find reusable robot code for your current environment, with pinned sources and runnable examples. Install `find-robot-skills` or use its directory in this repository. The folder includes the tool, catalog snapshot, adapter assets and contribution reference; a repository checkout is not required after installation. Browse the public catalog at [hub.superfastrobotics.com](https://hub.superfastrobotics.com/). The examples below start with Panda; search also covers the cataloged Panda Stick, xArm6 Robotiq and SO100 recipes. ```sh python /PATH_TO_SKILL/scripts/rsh.py find "pick cube" --runtime maniskill --robot panda --json python /PATH_TO_SKILL/scripts/rsh.py inspect SKILL_ID --json python /PATH_TO_SKILL/scripts/rsh.py prepare SKILL_ID --project ./experiment --json ``` Use the exact ID returned by `find`. Inspect the controller, state observation inputs, source commit, license, preparation plan, dependencies and evidence before preparing. Missing environment values stay unknown. Explicit incompatible environments produce no compatible candidates. Preparation downloads an exact source archive, verifies its hash, creates an isolated project environment on supported systems, and records a lock. It does not run the simulator. Dependency installation is explicit because package installation can execute code. Follow the tool's returned command arrays; do not replace the project's Python environment or silently update an existing lock. The preparation recipes target Linux x86_64/Python 3.10 and ManiSkill 3.0.0b22 state-based motion planners. Each record specifies its robot, controller and task. On Windows, search and inspect work; download-only preparation can preserve sources for a matching Linux environment. Records retain `not_run` until task execution is demonstrated. Source review, dependency installation, import success and task success are distinct evidence levels. If a useful fix was already needed for the user's work, create a local bundle containing only that fix, exact base/source pins, environment and actual evidence. Public contribution requires both project sharing permission and a limited API token. Follow [contributing](./contributing.md) and the installed skill's reference. No sharing permission means no network submission. Submission never blocks finishing the original user task. --- # Compatibility The catalog wraps official ManiSkill 3.0.0b22 motion planners for Panda variants (`panda`, `panda_wristcam`), Panda Stick (`panda_stick`), xArm6 Robotiq (`xarm6_robotiq`) and SO100. Each recipe pins a full upstream commit and archive SHA-256. Requirements are recorded as complete combinations of task, robot, controller and runtime. The preparation target is Linux x86_64, Python 3.10, `maniskill` 3.0.0b22, simulator state observations and one CPU simulation environment with rendering disabled. Consult each record for its exact robot, controller, package versions and command arguments. A state-based planner uses privileged simulator information; evaluate it separately from an RGB-only controller. Records distinguish source review from runtime results. Task execution has not been demonstrated on this Windows development host; current recipes retain their recorded evidence levels. Source review and structural tests do not establish installation, import, success rate, hardware safety, performance improvement or compatibility with other ManiSkill releases. Video rendering and real hardware control are outside the current preparation scope. Windows/macOS can read the public catalog. The local tool reports unsupported simulator OS rather than treating it as compatible. Unknown requirements remain unknown. Existing research locks remain unchanged until an explicit new preparation is requested. The separate [official source example index](https://hub.superfastrobotics.com/catalog/v1/references.json) covers additional frameworks. Those entries support source browsing only. They are not preparation records, compatibility claims or local execution results; see [source selection notes](sample-sources.md). --- # Minimal public contributions Preserve a useful correction made for the user's task locally first. Do not invent unrelated edits to generate PRs. Public submission is optional; the local patched project remains usable without submission or acceptance. Only the hub's recipe, adapter, dependency metadata, recipe documentation and small reproduction paths declared by that record are accepted. Operational workflows, authentication settings, arbitrary repositories and upstream code are not submission targets. Preserve upstream authorship and license notices. Contributor labels are self-reported. The project must explicitly allow the particular files to be shared publicly. Possessing an API token does not establish sharing permission. The submission payload, resulting branch, PR and contributor evidence can be public immediately. Never include whole projects, conversations, private datasets, keys or logs. The installed skill reference describes `.robot-skill-hub.json` policy, `bundle`, `submit` and `submission-status`. Store `RSH_SUBMISSION_TOKEN` locally, and configure `RSH_API_URL=https://api.superfastrobotics.com`. This limited token authorizes submission and the caller's own status reads; it contains no GitHub permissions. `POST /v1/submissions` requires Bearer authentication and `Idempotency-Key`. Retry the same exact request with the same key after interrupted responses. Reusing a key with another payload is a conflict. Keep the local draft on all failures. A corrected request uses a new key and may declare `supersedes_submission_id` for the caller's prior `needs_changes` request. The Worker records the patch and server receipt, then creates an internal draft PR before returning `submitted`. Structural checks never claim robot execution. GitHub Actions checks run without deployment secrets. A maintainer reviews changes, marks the draft ready when appropriate, and merges manually. Labels `rsh:needs_changes`, `rsh:rejected` and other documented API status labels can guide review; consult the API README for implemented labels. A merged PR remains `merged` until GitHub Pages serves a publication manifest proving the new record version, source pin, file hashes and submission inclusion. Failed publication is reported separately. `published` includes the reusable version and recipe URL. A new project can select that published version explicitly; previous projects are never silently updated. --- # ManiSkill panda LiftPegUpright-v1 motion planner Grasp a peg and lift it upright with the official Panda planner. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/lift_peg_upright.py`, `mani_skill/envs/tasks/tabletop/lift_peg_upright.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "grasping" --runtime maniskill --runtime-version 3.0.0b22 --robot panda --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-lift-peg-upright --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-lift-peg-upright --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.lift_peg_upright:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "LiftPegUpright-v1", "seed": 0, "robot": "panda", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: LiftPegUpright-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill panda LiftPegUpright-v1 motion planner Grasp a peg and lift it upright with the official Panda planner. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.panda.solutions.lift_peg_upright:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/panda/solutions/lift_peg_upright.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-panda-lift-peg-upright` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-panda-lift-peg-upright/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-panda-lift-peg-upright --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-lift-peg-upright --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-lift-peg-upright --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `panda`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. --- # ManiSkill panda_wristcam PegInsertionSide-v1 motion planner Align a peg with a side-facing hole and insert it using Panda WristCam. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda_wristcam | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/peg_insertion_side.py`, `mani_skill/envs/tasks/tabletop/peg_insertion_side.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "peg-in-hole" --runtime maniskill --runtime-version 3.0.0b22 --robot panda_wristcam --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-peg-insertion-side --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-peg-insertion-side --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.peg_insertion_side:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "PegInsertionSide-v1", "seed": 0, "robot": "panda_wristcam", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: PegInsertionSide-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill panda_wristcam PegInsertionSide-v1 motion planner Align a peg with a side-facing hole and insert it using Panda WristCam. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.panda.solutions.peg_insertion_side:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/panda/solutions/peg_insertion_side.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-panda-peg-insertion-side` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-panda-peg-insertion-side/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-panda-peg-insertion-side --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-peg-insertion-side --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-peg-insertion-side --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `panda_wristcam`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. --- # ManiSkill Panda PickCube Python recipe Grasp a cube and move it to a target with the official Panda motion planner. Record version: `contrib-a5dd78ad4e1d4e3d` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | not_run | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **contributor_reported**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/pick_cube.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "grasping" --runtime maniskill --runtime-version 3.0.0b22 --robot panda --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-pick-cube --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-pick-cube --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.pick_cube:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "PickCube-v1", "seed": 0, "robot": "panda", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: PickCube-v1 env info.success is true after upstream solver finishes; adapter exit 0 only when success is true. Timeout: 180 seconds. Stop after one seed; no retries to conceal failures. Use an external 180-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Intake structure checks only. Changed recipe runtime, dependency installation, imports and robot tasks were not run by the hub. Reviewer: Robot Skill Hub API structural intake · 2026-10-17. Commands/checks actually performed: - API schema, exact base/source pin, allowlist and strict unified diff checks Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. ## Recipe notes The hub wrapper in `recipes/maniskill-panda-pick-cube/run.py` imports the original ManiSkill `pick_cube.solve` implementation without copying or modifying it. The original solver reads simulator object poses and uses MPlib motion planning. The initial target is Linux x86_64 and Python 3.10. State observations and an explicit CPU simulation backend and `render_backend="none"` are used. Setting `render_mode=None` alone would leave the upstream GPU rendering backend enabled. No camera observations, video recorder or GUI are requested by the hub wrapper. The upstream demo runner has different rendering defaults; do not substitute its invocation and assume the same hardware requirements. The source archive includes upstream LICENSE and any upstream attribution files; retain them in prepared projects. Follow the original repository's contribution rules for changes to upstream code. The hub API accepts only its own wrapper, dependency metadata and documentation paths. The canonical JSON keeps source inspection and simulator execution evidence in separate fields. Consult those fields for the exact recorded environment. ## Prepare the source from Windows Search and source preparation work on Windows even though the simulator target is Linux. To preserve the pinned source and adapter without attempting an unsupported simulation environment, use the installed skill directory: ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-pick-cube --project ./pick-cube-source --download-only --json ``` The expected result is `needs_configuration` with `reason_code: source_ready_runtime_not_prepared` and `next_command: null`. It verifies the archive SHA-256 and writes a source/recipe lock, but creates no venv, installs no dependencies and runs no robot task. Use a separate matching Linux environment for execution; keep the existing research project's lock. --- # ManiSkill panda PlaceSphere-v1 motion planner Pick up a sphere and place it into a bin with the official Panda planner. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/place_sphere.py`, `mani_skill/envs/tasks/tabletop/place_sphere.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "pick-and-place" --runtime maniskill --runtime-version 3.0.0b22 --robot panda --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-place-sphere --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-place-sphere --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.place_sphere:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "PlaceSphere-v1", "seed": 0, "robot": "panda", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: PlaceSphere-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill panda PlaceSphere-v1 motion planner Pick up a sphere and place it into a bin with the official Panda planner. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.panda.solutions.place_sphere:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/panda/solutions/place_sphere.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-panda-place-sphere` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-panda-place-sphere/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-panda-place-sphere --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-place-sphere --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-place-sphere --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `panda`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. --- # ManiSkill panda_wristcam PlugCharger-v1 motion planner Grasp a charger, align its pins, and plug it into a receptacle. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda_wristcam | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/plug_charger.py`, `mani_skill/envs/tasks/tabletop/plug_charger.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "insertion" --runtime maniskill --runtime-version 3.0.0b22 --robot panda_wristcam --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-plug-charger --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-plug-charger --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.plug_charger:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "PlugCharger-v1", "seed": 0, "robot": "panda_wristcam", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: PlugCharger-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill panda_wristcam PlugCharger-v1 motion planner Grasp a charger, align its pins, and plug it into a receptacle. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.panda.solutions.plug_charger:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/panda/solutions/plug_charger.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-panda-plug-charger` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-panda-plug-charger/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-panda-plug-charger --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-plug-charger --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-plug-charger --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `panda_wristcam`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. --- # ManiSkill panda PullCubeTool-v1 motion planner Use an L-shaped tool to pull a cube toward a goal. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/pull_cube_tool.py`, `mani_skill/envs/tasks/tabletop/pull_cube_tool.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "tool-use" --runtime maniskill --runtime-version 3.0.0b22 --robot panda --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-pull-cube-tool --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-pull-cube-tool --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.pull_cube_tool:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "PullCubeTool-v1", "seed": 0, "robot": "panda", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: PullCubeTool-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill panda PullCubeTool-v1 motion planner Use an L-shaped tool to pull a cube toward a goal. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.panda.solutions.pull_cube_tool:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/panda/solutions/pull_cube_tool.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-panda-pull-cube-tool` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-panda-pull-cube-tool/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-panda-pull-cube-tool --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-pull-cube-tool --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-pull-cube-tool --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `panda`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. --- # ManiSkill panda PullCube-v1 motion planner Pull a cube to its goal with the official Panda motion planner. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/pull_cube.py`, `mani_skill/envs/tasks/tabletop/pull_cube.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "pulling" --runtime maniskill --runtime-version 3.0.0b22 --robot panda --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-pull-cube --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-pull-cube --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.pull_cube:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "PullCube-v1", "seed": 0, "robot": "panda", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: PullCube-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill panda PullCube-v1 motion planner Pull a cube to its goal with the official Panda motion planner. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.panda.solutions.pull_cube:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/panda/solutions/pull_cube.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-panda-pull-cube` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-panda-pull-cube/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-panda-pull-cube --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-pull-cube --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-pull-cube --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `panda`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. --- # ManiSkill panda PushCube-v1 motion planner Push a cube to a goal region with the official Panda motion planner. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/push_cube.py`, `mani_skill/envs/tasks/tabletop/push_cube.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "pushing" --runtime maniskill --runtime-version 3.0.0b22 --robot panda --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-push-cube --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-push-cube --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.push_cube:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "PushCube-v1", "seed": 0, "robot": "panda", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: PushCube-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill panda PushCube-v1 motion planner Push a cube to a goal region with the official Panda motion planner. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.panda.solutions.push_cube:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/panda/solutions/push_cube.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-panda-push-cube` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-panda-push-cube/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-panda-push-cube --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-push-cube --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-push-cube --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `panda`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. --- # ManiSkill Panda StackCube Python recipe Grasp one cube and stack it on another with the official Panda motion planner. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/stack_cube.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "grasping" --runtime maniskill --runtime-version 3.0.0b22 --robot panda --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-stack-cube --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-stack-cube --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.stack_cube:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "StackCube-v1", "seed": 0, "robot": "panda", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: StackCube-v1 env info.success is true after upstream solver finishes; adapter exit 0 only when success is true. Timeout: 180 seconds. Stop after one seed; no retries to conceal failures. Use an external 180-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Source and license verified. Linux execution, dependency installation, imports and task completion have NOT been run by the hub (not_run). Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - git ls-remote https://github.com/haosulab/ManiSkill.git refs/tags/v3.0.0b22 - Download exact commit archive; SHA256 checked - Review pinned setup.py, LICENSE, upstream run.py and task solver Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. ## Recipe notes The hub wrapper in `recipes/maniskill-panda-stack-cube/run.py` imports the original ManiSkill `stack_cube.solve` implementation without copying or modifying it. It combines grasping, lifting and placement using ground-truth simulator state. Use the same exact Linux x86_64 / Python 3.10 / Panda / `pd_joint_pos` target as the PickCube recipe. Sharing the physics engine or robot name with another framework does not make the solver portable. This recipe is not an RGB-only policy and must not be presented as an equivalent visual-policy benchmark. The wrapper sets `render_backend="none"` explicitly, as `render_mode=None` alone does not disable ManiSkill's default GPU rendering backend. No GUI, video or camera output is requested by the wrapper. Graphics examples and other observation modes require their own compatibility checks. Preserve the upstream Apache-2.0 license and original author notices in the downloaded source. The canonical JSON keeps source inspection and simulator execution evidence in separate fields. Consult those fields for the exact recorded environment. --- # ManiSkill panda StackPyramid-v1 motion planner Arrange three cubes into a pyramid using the official Panda planner. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/stack_pyramid.py`, `mani_skill/envs/tasks/tabletop/stack_pyramid.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "stacking" --runtime maniskill --runtime-version 3.0.0b22 --robot panda --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-stack-pyramid --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-stack-pyramid --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.stack_pyramid:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "StackPyramid-v1", "seed": 0, "robot": "panda", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: StackPyramid-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill panda StackPyramid-v1 motion planner Arrange three cubes into a pyramid using the official Panda planner. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.panda.solutions.stack_pyramid:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/panda/solutions/stack_pyramid.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-panda-stack-pyramid` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-panda-stack-pyramid/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-panda-stack-pyramid --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-stack-pyramid --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-stack-pyramid --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `panda`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. --- # ManiSkill panda_stick DrawSVG-v1 motion planner Trace the environment's default SVG outline with the Panda Stick planner. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda_stick | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/draw_svg.py`, `mani_skill/envs/tasks/drawing/draw_svg.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "drawing" --runtime maniskill --runtime-version 3.0.0b22 --robot panda_stick --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-stick-draw-svg --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-stick-draw-svg --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`, `svgpathtools==1.6.1`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.draw_svg:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "DrawSVG-v1", "seed": 0, "robot": "panda_stick", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: DrawSVG-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill panda_stick DrawSVG-v1 motion planner Trace the environment's default SVG outline with the Panda Stick planner. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.panda.solutions.draw_svg:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/panda/solutions/draw_svg.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-panda-stick-draw-svg` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-panda-stick-draw-svg/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-panda-stick-draw-svg --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-stick-draw-svg --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-stick-draw-svg --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `panda_stick`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. --- # ManiSkill panda_stick DrawTriangle-v1 motion planner Trace a triangle with the Panda Stick motion planner. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | panda_stick | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/panda/run.py`, `mani_skill/examples/motionplanning/panda/solutions/draw_triangle.py`, `mani_skill/envs/tasks/drawing/draw_triangle.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "drawing" --runtime maniskill --runtime-version 3.0.0b22 --robot panda_stick --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-panda-stick-draw-triangle --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-panda-stick-draw-triangle --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.panda.solutions.draw_triangle:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "DrawTriangle-v1", "seed": 0, "robot": "panda_stick", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: DrawTriangle-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill panda_stick DrawTriangle-v1 motion planner Trace a triangle with the Panda Stick motion planner. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.panda.solutions.draw_triangle:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/panda/solutions/draw_triangle.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-panda-stick-draw-triangle` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-panda-stick-draw-triangle/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-panda-stick-draw-triangle --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-stick-draw-triangle --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-panda-stick-draw-triangle --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `panda_stick`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. --- # ManiSkill so100 PickCubeSO100-v1 motion planner Pick up a cube and move it to a goal with the official SO100 planner. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | so100 | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/so100/run.py`, `mani_skill/examples/motionplanning/so100/solutions/pick_cube.py`, `mani_skill/envs/tasks/tabletop/pick_cube.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "grasping" --runtime maniskill --runtime-version 3.0.0b22 --robot so100 --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-so100-pick-cube --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-so100-pick-cube --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.so100.solutions.pick_cube:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "PickCubeSO100-v1", "seed": 0, "robot": "so100", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: PickCubeSO100-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill so100 PickCubeSO100-v1 motion planner Pick up a cube and move it to a goal with the official SO100 planner. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.so100.solutions.pick_cube:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/so100/solutions/pick_cube.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-so100-pick-cube` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-so100-pick-cube/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-so100-pick-cube --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-so100-pick-cube --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-so100-pick-cube --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `so100`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. --- # ManiSkill xarm6_robotiq PickCube-v1 motion planner Grasp a cube and move it to a goal with the official xArm6 Robotiq solver. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | xarm6_robotiq | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/xarm6/run.py`, `mani_skill/examples/motionplanning/xarm6/solutions/pick_cube.py`, `mani_skill/envs/tasks/tabletop/pick_cube.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "grasping" --runtime maniskill --runtime-version 3.0.0b22 --robot xarm6_robotiq --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-xarm6-pick-cube --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-xarm6-pick-cube --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.xarm6.solutions.pick_cube:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "PickCube-v1", "seed": 0, "robot": "xarm6_robotiq", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: PickCube-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill xarm6_robotiq PickCube-v1 motion planner Grasp a cube and move it to a goal with the official xArm6 Robotiq solver. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.xarm6.solutions.pick_cube:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/xarm6/solutions/pick_cube.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-xarm6-pick-cube` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-xarm6-pick-cube/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-xarm6-pick-cube --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-xarm6-pick-cube --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-xarm6-pick-cube --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `xarm6_robotiq`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. This robot variant comes from the official xArm6 runner. Some upstream task declarations list Panda/Fetch only and log a warning for xArm6. Sparse rewards avoid Panda-specific dense reward code; confirm the variant in your simulator environment. --- # ManiSkill xarm6_robotiq PlugCharger-v1 motion planner Insert a charger using the official xArm6 Robotiq motion planner. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | xarm6_robotiq | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/xarm6/run.py`, `mani_skill/examples/motionplanning/xarm6/solutions/plug_charger.py`, `mani_skill/envs/tasks/tabletop/plug_charger.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "insertion" --runtime maniskill --runtime-version 3.0.0b22 --robot xarm6_robotiq --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-xarm6-plug-charger --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-xarm6-plug-charger --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.xarm6.solutions.plug_charger:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "PlugCharger-v1", "seed": 0, "robot": "xarm6_robotiq", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: PlugCharger-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill xarm6_robotiq PlugCharger-v1 motion planner Insert a charger using the official xArm6 Robotiq motion planner. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.xarm6.solutions.plug_charger:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/xarm6/solutions/plug_charger.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-xarm6-plug-charger` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-xarm6-plug-charger/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-xarm6-plug-charger --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-xarm6-plug-charger --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-xarm6-plug-charger --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `xarm6_robotiq`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. This robot variant comes from the official xArm6 runner. Some upstream task declarations list Panda/Fetch only and log a warning for xArm6. Sparse rewards avoid Panda-specific dense reward code; confirm the variant in your simulator environment. --- # ManiSkill xarm6_robotiq PushCube-v1 motion planner Push a cube to a goal with the official xArm6 Robotiq solver. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | xarm6_robotiq | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/xarm6/run.py`, `mani_skill/examples/motionplanning/xarm6/solutions/push_cube.py`, `mani_skill/envs/tasks/tabletop/push_cube.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "pushing" --runtime maniskill --runtime-version 3.0.0b22 --robot xarm6_robotiq --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-xarm6-push-cube --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-xarm6-push-cube --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.xarm6.solutions.push_cube:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "PushCube-v1", "seed": 0, "robot": "xarm6_robotiq", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: PushCube-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill xarm6_robotiq PushCube-v1 motion planner Push a cube to a goal with the official xArm6 Robotiq solver. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.xarm6.solutions.push_cube:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/xarm6/solutions/push_cube.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-xarm6-push-cube` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-xarm6-push-cube/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-xarm6-push-cube --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-xarm6-push-cube --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-xarm6-push-cube --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `xarm6_robotiq`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. This robot variant comes from the official xArm6 runner. Some upstream task declarations list Panda/Fetch only and log a warning for xArm6. Sparse rewards avoid Panda-specific dense reward code; confirm the variant in your simulator environment. --- # ManiSkill xarm6_robotiq StackCube-v1 motion planner Stack one cube on another with the official xArm6 Robotiq solver. Record version: `1.0.0` · Hub commit: `01b4b20f7ea55d9e9395915aed4e82c890c4c1c4` ## Exact environment | Runtime | Robot | Controller | Observation | OS | Python | Evidence | | --- | --- | --- | --- | --- | --- | --- | | maniskill 3.0.0b22 | xarm6_robotiq | pd_joint_pos | state | linux x86_64 | >=3.10,<3.11 | source_reviewed | Reads ground-truth object poses, collision geometry and robot state directly from the simulator. Not an RGB-only policy. Compatibility status: **source_reviewed**. An environment match does not establish task completion. Runtime verification: **not_run**. ## Source and license - Repository: https://github.com/haosulab/ManiSkill - Source commit: `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` (v3.0.0b22) - Original authors: ManiSkill contributors - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE) - Source archive SHA256: `d194e39e4f86063f7ea49f25c918ca7474d088ad8d5abdc37573daf4672f86d4` - Upstream files: `mani_skill/examples/motionplanning/xarm6/run.py`, `mani_skill/examples/motionplanning/xarm6/solutions/stack_cube.py`, `mani_skill/envs/tasks/tabletop/stack_cube.py`, `setup.py`, `LICENSE` - Upstream contribution rules: https://github.com/haosulab/ManiSkill/tree/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907 ## Find, inspect, prepare ```sh python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json find "stacking" --runtime maniskill --runtime-version 3.0.0b22 --robot xarm6_robotiq --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json inspect maniskill-xarm6-stack-cube --json python /PATH_TO_SKILL/scripts/rsh.py --catalog https://hub.superfastrobotics.com/catalog/v1/index.json prepare maniskill-xarm6-stack-cube --project ./experiment --plan --json ``` Remove `--plan` to download the checksum-verified pinned source and create an isolated project environment. Preparation returns the remaining configuration. Dependency installation is an explicit `--install-deps` step; it can execute package build hooks. Robot simulation is a separate command returned by prepare, never run by find/inspect. Direct package pins: `torch==2.5.1`, `numpy==1.26.4`, `sapien==3.0.0`, `mplib==0.1.1`, `fast_kinematics==0.2.2`. Direct dependencies pinned; transitive dependencies resolved by pip and captured in the prepared project. No bit-for-bit environment guarantee. Hardware: Linux x86_64 CPU; SAPIEN wheel needs glibc >=2.28. Rendering: disabled explicitly: render_backend=none, render_mode=None, state observations and CPU simulation; graphics paths require separate Vulkan setup. External API keys: none. ## Invocation contract Entrypoint: `mani_skill.examples.motionplanning.xarm6.solutions.stack_cube:solve`. ```json { "argv": [ "{python}", "{recipe_dir}/run.py", "--seed", "0" ], "inputs": { "task": "StackCube-v1", "seed": 0, "robot": "xarm6_robotiq", "controller": "pd_joint_pos", "obs_mode": "state", "sim_backend": "cpu", "render_backend": "none", "reward_mode": "sparse" }, "outputs": { "format": "last stdout line JSON", "fields": [ "status", "success", "elapsed_steps", "task", "seed", "runtime", "robot", "controller", "observation", "sim_backend", "render_backend" ], "error_fields": [ "status", "reason_code", "error_type", "message" ] } } ``` Success: StackCube-v1 env info.success is true after the upstream solver finishes; exit 0 requires success. Timeout: 300 seconds. Stop after one seed; no automatic retries. Use an external 300-second process timeout. Failures: Dependency installation unavailable or incompatible; Required Linux mplib wheels unavailable on host OS; Motion planning reports failure or env info.success is false; Runtime exception or asset download failure. ## Actual evidence Inspected the pinned solver signature, task registration, source license and wrapper contract. No simulator invocation evidence is attached. Reviewer: Robot Skill Hub source review · 2026-10-17. Commands/checks actually performed: - python tools/import_official_samples.py --archive .local/upstream/maniskill-33967b9.tar.gz --check - python -m unittest discover -s tests/python -p test_bulk_catalog.py Submitted evidence and hub verification remain separate. A schema check, PR creation or merge does not establish task success or publication. ## Reusable fixes Only actual reusable fixes. Public submission permission and a scoped pilot token are separate requirements. Submission opens a public internal draft PR; it is not publication. # ManiSkill xarm6_robotiq StackCube-v1 motion planner Stack one cube on another with the official xArm6 Robotiq solver. ## Source - Repository: https://github.com/haosulab/ManiSkill - Release: v3.0.0b22; commit `33967b9e3ead1f841eec57cc9f31d0d8b8cf0907` - Solver: [mani_skill.examples.motionplanning.xarm6.solutions.stack_cube:solve](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/mani_skill/examples/motionplanning/xarm6/solutions/stack_cube.py) - License: [Apache-2.0](https://github.com/haosulab/ManiSkill/blob/33967b9e3ead1f841eec57cc9f31d0d8b8cf0907/LICENSE); robot/mesh assets retain upstream notices. - Recipe ID: `maniskill-xarm6-stack-cube` - Canonical JSON: https://hub.superfastrobotics.com/skills/maniskill-xarm6-stack-cube/skill.json ## Agent preparation ```sh python skills/find-robot-skills/scripts/rsh.py inspect maniskill-xarm6-stack-cube --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-xarm6-stack-cube --project ./experiment --plan --json python skills/find-robot-skills/scripts/rsh.py prepare maniskill-xarm6-stack-cube --project ./experiment --download-only --json ``` Run preparation on Linux x86_64 with Python 3.10 for the simulator environment. Add `--install-deps` explicitly to install dependencies. The returned task command is a separate execution step. Input is one seed (`--seed 0` by default); output is a final JSON line with task status and success. Use a 300-second process timeout. ## Environment contract `maniskill==3.0.0b22`, robot `xarm6_robotiq`, `pd_joint_pos`, `state` observations, `cpu` simulation, `render_backend=none`, no video/display, sparse rewards. The planner reads privileged simulator poses and collision geometry. It is a simulation example, not a perception policy or a physical robot controller. The source archive and direct dependency versions are pinned. Transitive Python dependencies resolve during installation and are captured by the project lock. The exact source and wrapper contracts were inspected; runtime status is recorded in the JSON evidence fields. A nonzero exit and JSON error preserve failures. This robot variant comes from the official xArm6 runner. Some upstream task declarations list Panda/Fetch only and log a warning for xArm6. Sparse rewards avoid Panda-specific dense reward code; confirm the variant in your simulator environment. --- # Official source examples These records are discovery references with no hub preparation adapter. Follow upstream setup and invocation instructions. ```json { "schema_version": "1", "checked_at": "2026-10-17", "description": "Pinned official examples for source discovery. These entries are separate from Hub preparation recipes.", "selection": "Official examples from widely followed simulator repositories. GitHub stars are a dated repository interest proxy, not a ranking of actual usage.", "records": [ { "id": "mujoco-basic", "name": "MuJoCo minimal interactive simulator", "summary": "Build the official minimal C++ simulator with GLFW camera interaction.", "framework": "mujoco", "kind": "official_example", "capabilities": [ "simulation", "cpp", "viewer" ], "source": { "repository": "https://github.com/google-deepmind/mujoco", "commit": "f1d45bd5422c74beddfb0d1deb590a02583d21de", "tag": "3.3.7", "path": "sample/basic.cc", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/sample/basic.cc", "sha256": "ca585c99ca6eede2b2d15fb28b6d63b7c822d4a5e8ea7e031865682a700abddc", "bytes": 5646 }, "license": { "spdx": "Apache-2.0", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://mujoco.readthedocs.io/en/3.3.7/programming/samples.html" }, "requirements": { "python": "Python examples follow upstream package constraints; native samples use C++", "packages": [ "mujoco==3.3.7 (Python)", "MuJoCo 3.3.7 and CMake toolchain (native samples)" ], "display": "Upstream example controls rendering; inspect source before use. GUI, device, model or dataset setup may be required.", "source_imports": [ "GLFW/glfw3.h", "cstdio", "cstdlib", "cstring", "mujoco/mujoco.h" ] }, "invocation": { "entrypoint": "C++ main: sample/basic.cc (build with upstream CMake)", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 15726, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "mujoco-compile", "name": "MuJoCo model format conversion", "summary": "Convert MJCF, URDF, and binary model formats with the official compiler sample.", "framework": "mujoco", "kind": "official_example", "capabilities": [ "model-conversion", "mjcf", "urdf" ], "source": { "repository": "https://github.com/google-deepmind/mujoco", "commit": "f1d45bd5422c74beddfb0d1deb590a02583d21de", "tag": "3.3.7", "path": "sample/compile.cc", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/sample/compile.cc", "sha256": "61b4e5d60decb2667ba3e0394503e3188bb7dccb59dec836021272cf5ef08d28", "bytes": 4305 }, "license": { "spdx": "Apache-2.0", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://mujoco.readthedocs.io/en/3.3.7/programming/samples.html" }, "requirements": { "python": "Python examples follow upstream package constraints; native samples use C++", "packages": [ "mujoco==3.3.7 (Python)", "MuJoCo 3.3.7 and CMake toolchain (native samples)" ], "display": "Upstream example controls rendering; inspect source before use. GUI, device, model or dataset setup may be required.", "source_imports": [ "cctype", "chrono", "cstddef", "cstdio", "cstdlib", "cstring", "iostream", "mujoco/mujoco.h" ] }, "invocation": { "entrypoint": "C++ main: sample/compile.cc (build with upstream CMake)", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 15726, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "mujoco-mjx-tutorial", "name": "MuJoCo MJX tutorial", "summary": "Use the official notebook to explore JAX-based accelerated MuJoCo simulation.", "framework": "mujoco", "kind": "official_example", "capabilities": [ "jax", "accelerated-simulation", "reinforcement-learning" ], "source": { "repository": "https://github.com/google-deepmind/mujoco", "commit": "f1d45bd5422c74beddfb0d1deb590a02583d21de", "tag": "3.3.7", "path": "mjx/tutorial.ipynb", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/mjx/tutorial.ipynb", "sha256": "9f9512ce0651b90443528553c617852a81ba0886d1267f1a0635bb4c73a68432", "bytes": 59067 }, "license": { "spdx": "Apache-2.0", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://mujoco.readthedocs.io/en/3.3.7/programming/samples.html" }, "requirements": { "python": "Python examples follow upstream package constraints; native samples use C++", "packages": [ "mujoco-mjx (follow pinned tutorial install cells)", "jax and accelerator-compatible jaxlib", "notebook dependencies listed in source_imports" ], "display": "The upstream notebook requires a GPU-accelerated Colab runtime and JAX/MJX setup. Inspect notebook install cells before running.", "source_imports": [ "IPython.display", "brax", "brax.base", "brax.envs.base", "brax.io", "brax.mjx.base", "brax.training.agents.ppo", "datetime", "distutils.util", "etils", "flax", "flax.training", "functools", "google.colab", "itertools", "jax", "matplotlib", "matplotlib.pyplot", "mediapy", "ml_collections", "mujoco", "numpy", "orbax", "os", "subprocess", "time", "typing" ] }, "invocation": { "entrypoint": "Notebook: mjx/tutorial.ipynb", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 15726, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "mujoco-record", "name": "MuJoCo offscreen trajectory recording", "summary": "Render passive model dynamics offscreen and write raw frame data.", "framework": "mujoco", "kind": "official_example", "capabilities": [ "offscreen-rendering", "video", "simulation" ], "source": { "repository": "https://github.com/google-deepmind/mujoco", "commit": "f1d45bd5422c74beddfb0d1deb590a02583d21de", "tag": "3.3.7", "path": "sample/record.cc", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/sample/record.cc", "sha256": "6c751d365ebf823970ababffaef1e38e59fb82ee00ab6351fa5057f6460fd967", "bytes": 8653 }, "license": { "spdx": "Apache-2.0", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://mujoco.readthedocs.io/en/3.3.7/programming/samples.html" }, "requirements": { "python": "Python examples follow upstream package constraints; native samples use C++", "packages": [ "mujoco==3.3.7 (Python)", "MuJoCo 3.3.7 and CMake toolchain (native samples)" ], "display": "Upstream example controls rendering; inspect source before use. GUI, device, model or dataset setup may be required.", "source_imports": [ "array_safety.h", "cstdio", "cstdlib", "cstring", "mujoco/mujoco.h" ] }, "invocation": { "entrypoint": "C++ main: sample/record.cc (build with upstream CMake)", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 15726, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "mujoco-simulate", "name": "MuJoCo full interactive simulator", "summary": "Build and run the official simulator with model inspection, profiling, and sensor plots.", "framework": "mujoco", "kind": "official_example", "capabilities": [ "simulation", "viewer", "profiling" ], "source": { "repository": "https://github.com/google-deepmind/mujoco", "commit": "f1d45bd5422c74beddfb0d1deb590a02583d21de", "tag": "3.3.7", "path": "simulate/main.cc", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/simulate/main.cc", "sha256": "7659d8b4b8f298c141ce92ffc867a3e48f0b65a45f5a995fb0e0840c9d3d13bb", "bytes": 16024 }, "license": { "spdx": "Apache-2.0", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://mujoco.readthedocs.io/en/3.3.7/programming/samples.html" }, "requirements": { "python": "Python examples follow upstream package constraints; native samples use C++", "packages": [ "mujoco==3.3.7 (Python)", "MuJoCo 3.3.7 and CMake toolchain (native samples)" ], "display": "Upstream example controls rendering; inspect source before use. GUI, device, model or dataset setup may be required.", "source_imports": [ "array_safety.h", "cerrno", "chrono", "cstdint", "cstdio", "cstdlib", "cstring", "glfw_adapter.h", "iostream", "memory", "mujoco/experimental/usd/usd.h", "mujoco/mujoco.h", "mutex", "new", "simulate.h", "string", "thread" ] }, "invocation": { "entrypoint": "C++ main: simulate/main.cc (build with upstream CMake)", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 15726, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "mujoco-testspeed", "name": "MuJoCo simulation benchmark sample", "summary": "Time model rollouts and inspect contact, constraint, and CPU statistics.", "framework": "mujoco", "kind": "official_example", "capabilities": [ "benchmark", "simulation", "rollout" ], "source": { "repository": "https://github.com/google-deepmind/mujoco", "commit": "f1d45bd5422c74beddfb0d1deb590a02583d21de", "tag": "3.3.7", "path": "sample/testspeed.cc", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/sample/testspeed.cc", "sha256": "47402cbcc448e93e3b218e74084ad0c91a90a19780e4eaa113b634fc44bdf8b1", "bytes": 11521 }, "license": { "spdx": "Apache-2.0", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://mujoco.readthedocs.io/en/3.3.7/programming/samples.html" }, "requirements": { "python": "Python examples follow upstream package constraints; native samples use C++", "packages": [ "mujoco==3.3.7 (Python)", "MuJoCo 3.3.7 and CMake toolchain (native samples)" ], "display": "Upstream example controls rendering; inspect source before use. GUI, device, model or dataset setup may be required.", "source_imports": [ "chrono", "cstdio", "cstdlib", "cstring", "mujoco/mujoco.h", "ratio", "string", "thread", "vector" ] }, "invocation": { "entrypoint": "C++ main: sample/testspeed.cc (build with upstream CMake)", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 15726, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "mujoco-tutorial", "name": "MuJoCo Python tutorial", "summary": "Work through official model loading, simulation, rendering, and control examples.", "framework": "mujoco", "kind": "official_example", "capabilities": [ "simulation", "python", "control", "quickstart" ], "source": { "repository": "https://github.com/google-deepmind/mujoco", "commit": "f1d45bd5422c74beddfb0d1deb590a02583d21de", "tag": "3.3.7", "path": "python/tutorial.ipynb", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/python/tutorial.ipynb", "sha256": "eb5b33305e9317c194b4adf529d1d71e81d0b251325a779f9b5112d25587743e", "bytes": 75215 }, "license": { "spdx": "Apache-2.0", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://mujoco.readthedocs.io/en/3.3.7/programming/samples.html" }, "requirements": { "python": "Python examples follow upstream package constraints; native samples use C++", "packages": [ "mujoco==3.3.7 (Python)", "MuJoCo 3.3.7 and CMake toolchain (native samples)" ], "display": "Upstream example controls rendering; inspect source before use. GUI, device, model or dataset setup may be required.", "source_imports": [ "IPython.display", "distutils.util", "google.colab", "itertools", "matplotlib.pyplot", "mediapy", "mujoco", "numpy", "os", "subprocess", "time" ] }, "invocation": { "entrypoint": "Notebook: python/tutorial.ipynb", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 15726, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "mujoco-viewer", "name": "MuJoCo Python interactive viewer", "summary": "Launch the official Python viewer and inspect its passive and managed simulation interfaces.", "framework": "mujoco", "kind": "official_example", "capabilities": [ "viewer", "simulation", "python" ], "source": { "repository": "https://github.com/google-deepmind/mujoco", "commit": "f1d45bd5422c74beddfb0d1deb590a02583d21de", "tag": "3.3.7", "path": "python/mujoco/viewer.py", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/python/mujoco/viewer.py", "sha256": "8954ad166e1865c9844ae6566ebde5aab91376ba514b9406b9f9f7e8f7e4afd8", "bytes": 18520 }, "license": { "spdx": "Apache-2.0", "url": "https://github.com/google-deepmind/mujoco/blob/f1d45bd5422c74beddfb0d1deb590a02583d21de/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://mujoco.readthedocs.io/en/3.3.7/programming/samples.html" }, "requirements": { "python": "Python examples follow upstream package constraints; native samples use C++", "packages": [ "mujoco==3.3.7 (Python)", "MuJoCo 3.3.7 and CMake toolchain (native samples)" ], "display": "Upstream example controls rendering; inspect source before use. GUI, device, model or dataset setup may be required.", "source_imports": [ "abc", "absl", "atexit", "contextlib", "glfw", "math", "mujoco", "numpy", "os", "queue", "sys", "threading", "time", "typing", "weakref" ] }, "invocation": { "entrypoint": "python -m mujoco.viewer --mjcf=/path/to/model.xml", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 15726, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-batchraycast", "name": "PyBullet batch ray casting", "summary": "Cast batches of rays around a simulated scene and visualize intersections.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "ray-casting", "sensing", "collision" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/batchRayCast.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/batchRayCast.py", "sha256": "d5331351922f6679d724a6c618827c60d127ae7dad14d239cf6064892cfc262e", "bytes": 1672 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "math", "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/batchRayCast.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-collisionfilter", "name": "PyBullet collision filtering", "summary": "Configure collision groups and masks between simulated bodies.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "collision", "filtering" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/collisionFilter.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/collisionFilter.py", "sha256": "7b7f881a26b5180db0526502ca5342ca04b9c36267b8f641c0b0396005d79ed9", "bytes": 630 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/collisionFilter.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-constraint", "name": "PyBullet articulated constraints", "summary": "Create and change constraints between robot links and other bodies.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "constraints", "articulation" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/constraint.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/constraint.py", "sha256": "d7ca6ba3ef98bffc6247f7a6b29eea38204a8a15d5698e38c430888d689ba0a3", "bytes": 687 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "math", "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/constraint.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-contactfriction", "name": "PyBullet contact friction", "summary": "Inspect contact behavior under different friction settings.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "contact", "friction", "physics" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/contactFriction.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/contactFriction.py", "sha256": "46e104d83310a2fb72847ac05d60c905094292ac83f8bfd16d8189cad921ba59", "bytes": 1172 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "pybullet", "pybullet_data" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/contactFriction.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-forcetorquesensor", "name": "PyBullet force torque sensing", "summary": "Enable joint force torque sensing and inspect the sensor readings.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "force-torque", "sensing" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/forcetorquesensor.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/forcetorquesensor.py", "sha256": "6b3dc989cf80fdd5388dc2db1caa46e6e74b8d73ed3cd32b5b778a88c2378f33", "bytes": 794 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "pybullet", "pybullet_data" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/forcetorquesensor.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-hello-pybullet", "name": "PyBullet simulation quickstart", "summary": "Load a plane and R2D2 model, step simulation, and inspect the base pose.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "simulation", "urdf", "quickstart" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/hello_pybullet.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/hello_pybullet.py", "sha256": "7cac3a5bc3cffa06c4ad0172a954c3bae0202b0a3acea349e304ca73b080765d", "bytes": 646 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/hello_pybullet.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-humanoid-knee-position-control", "name": "PyBullet humanoid knee control", "summary": "Explore position control on the knees of a simulated humanoid.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "humanoid", "position-control", "motor-control" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/humanoid_knee_position_control.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/humanoid_knee_position_control.py", "sha256": "ce03f4cfc807ed2ad237397df3552e24a80ec9c6b66f2b018fec896d8aaadcd2", "bytes": 1596 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/humanoid_knee_position_control.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-ik-end-effector-orientation", "name": "PyBullet end-effector orientation IK", "summary": "Control KUKA end-effector position and orientation toward a fixed pose.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "inverse-kinematics", "orientation", "kuka" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/ik_end_effector_orientation.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/ik_end_effector_orientation.py", "sha256": "875fe8ec522764166a29655044c98a8fd3f3410d36442efe52a737b378cde080", "bytes": 1453 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "datetime", "math", "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/ik_end_effector_orientation.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-inverse-dynamics", "name": "PyBullet inverse dynamics", "summary": "Compute inverse dynamics and use torque control in a simulated articulated model.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "inverse-dynamics", "torque-control" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/inverse_dynamics.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/inverse_dynamics.py", "sha256": "279dc137017b83f4cfde56df2907076e88182278daab7293c32b5f07425973d0", "bytes": 5133 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "math", "matplotlib.pyplot", "pybullet", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/inverse_dynamics.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-inverse-kinematics", "name": "PyBullet KUKA inverse kinematics", "summary": "Move a KUKA end effector along target positions using inverse kinematics and joint motors.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "inverse-kinematics", "kuka", "arm-control" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/inverse_kinematics.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/inverse_kinematics.py", "sha256": "b74720fe9223a95b0cadfbc3e3fbc83b7eadbfba518d6e36e3fb27828188a8ed", "bytes": 4504 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "datetime", "math", "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/inverse_kinematics.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-jacobian", "name": "PyBullet Jacobian computation", "summary": "Compute a robot Jacobian and compare Cartesian velocity calculations.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "jacobian", "kinematics" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/jacobian.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/jacobian.py", "sha256": "2b6430a1063ad0ff0717296e29067da594afaeb5ccdaa790f27b001de07a88a0", "bytes": 3805 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "pybullet", "pybullet_data" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/jacobian.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-kuka-grasp-block-playback", "name": "PyBullet KUKA grasp log playback", "summary": "Replay a recorded KUKA grasp trajectory from the upstream state log.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "grasping", "trajectory-playback", "kuka" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/kuka_grasp_block_playback.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/kuka_grasp_block_playback.py", "sha256": "4b8ada60d08b4a3a735fbcc7588323c6acb5b581286d7676f5c68cb7c148a554", "bytes": 2019 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "pybullet", "pybullet_data", "struct" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/kuka_grasp_block_playback.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-kuka-with-cube", "name": "PyBullet KUKA and cube interaction", "summary": "Run a KUKA arm along an IK trajectory in a cube scene and record state/contact logs.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "kuka", "manipulation", "joint-control" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/kuka_with_cube.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/kuka_with_cube.py", "sha256": "96814d2cabec8d0d410ff61e5ef68283b202156b90d70d06cca125614daa84e7", "bytes": 4115 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "datetime", "math", "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/kuka_with_cube.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-pdcontrol", "name": "PyBullet PD control comparison", "summary": "Compare proportional-derivative controllers on an articulated robot.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "pd-control", "joint-control" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/pdControl.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/pdControl.py", "sha256": "1506818d6b5c47ed3eb55dee4531694e2a72612646223caf2d3c7a3c378607da", "bytes": 6426 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "pdControllerExplicit", "pdControllerStable", "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/pdControl.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-pointcloudfromcameraimage", "name": "PyBullet depth to point cloud", "summary": "Convert rendered camera depth samples into a world-space point cloud.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "point-cloud", "camera", "depth" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/pointCloudFromCameraImage.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/pointCloudFromCameraImage.py", "sha256": "6391077f0e1e8290a9f231efa68b84c0831561b3333feab9ddd09d1f87391d16", "bytes": 5639 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "math", "numpy", "pybullet", "pybullet_data" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/pointCloudFromCameraImage.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-quadruped", "name": "PyBullet quadruped simulation", "summary": "Load and control a quadruped model using the upstream interactive example.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "quadruped", "joint-control" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/quadruped.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/quadruped.py", "sha256": "1efbeaf03bdd5d2511f545829620491c419eb73984bbc7d4ef067061c496bc53", "bytes": 20411 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "math", "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/quadruped.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-racecar", "name": "PyBullet racecar control", "summary": "Drive the simulated racecar using upstream motor and steering controls.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "mobile-robot", "steering", "vehicle-control" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/racecar.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/racecar.py", "sha256": "5dc233309afa9086f343c1a91ec909ce62d4af46ba937ce6a790cae08c797e8d", "bytes": 1893 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "inspect", "os", "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/racecar.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-racecar-differential", "name": "PyBullet differential racecar", "summary": "Control a racecar model with differential drivetrain constraints.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "mobile-robot", "differential-drive", "constraints" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/racecar_differential.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/racecar_differential.py", "sha256": "a0790d6d0b8ce3797abd8b8964042050ed4897bcf931cd26d22419ad4839f8e5", "bytes": 4711 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "pybullet", "pybullet_data", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/racecar_differential.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-robotcontrol", "name": "PyBullet interactive robot joint control", "summary": "Inspect a robot's joints and drive them with GUI control parameters.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "joint-control", "robot-model" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/robotcontrol.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/robotcontrol.py", "sha256": "f0112cb3d835e5b110bb17df69b7b912d0a76d5bdb7d42f252faf2a979914186", "bytes": 780 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "pybullet", "pybullet_data" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/robotcontrol.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "pybullet-saverestorestate", "name": "PyBullet save and restore state", "summary": "Save and restore simulation states for repeatable experiments.", "framework": "pybullet", "kind": "official_example", "capabilities": [ "state", "replay", "simulation" ], "source": { "repository": "https://github.com/bulletphysics/bullet3", "commit": "2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5", "tag": "3.25", "path": "examples/pybullet/examples/saveRestoreState.py", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/examples/pybullet/examples/saveRestoreState.py", "sha256": "9eb0c993428d2589486ed0ee1c2d5af21dd9ec15ca8cf3a26e261382fafde7c6", "bytes": 3323 }, "license": { "spdx": "Zlib", "url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/LICENSE.txt", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/bulletphysics/bullet3/blob/2c204c49e56ed15ec5fcfa71d199ab6d6570b3f5/README.md" }, "requirements": { "python": "upstream-defined", "packages": [ "pybullet (build matching the pinned upstream source)" ], "display": "Most examples connect to a PyBullet GUI or shared-memory server. Upstream pybullet_data models and adjacent helper files may be required.", "source_imports": [ "difflib", "math", "pybullet", "pybullet_data", "sys", "time" ] }, "invocation": { "entrypoint": "python examples/pybullet/examples/saveRestoreState.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 14800, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-collect-and-playback-data", "name": "robosuite collect and replay data", "summary": "Collect state and action data, then replay it in the upstream demonstration workflow.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "demonstrations", "data-collection", "trajectory-playback" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_collect_and_playback_data.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_collect_and_playback_data.py", "sha256": "6661bb80943eab70af753bab1bda2ace2be57679a21b2f4d26c1700e5fc9fe82", "bytes": 4003 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "argparse", "glob", "numpy", "os", "robosuite", "robosuite.wrappers", "time" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_collect_and_playback_data.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-composite-robot", "name": "robosuite composite robot", "summary": "Instantiate a composed robot and exercise its action space in a manipulation task.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "robot-composition", "controllers" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_composite_robot.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_composite_robot.py", "sha256": "15b959be2ceb693ad69b3076c3ccfd59981423b62f86ed45f770035b87296ac5", "bytes": 2497 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "argparse", "numpy", "robosuite", "robosuite.controllers", "robosuite.robots", "robosuite.utils.robot_composition_utils", "time", "typing" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_composite_robot.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-control", "name": "robosuite controller demonstration", "summary": "Compare controller behavior with prescribed action sequences.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "controllers", "manipulation" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_control.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_control.py", "sha256": "c09ee40659987d0c0d7cefa8e291bb0f921a676187884aa63a8950849dd6e822", "bytes": 8672 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "robosuite", "robosuite.controllers.composite.composite_controller_factory", "robosuite.utils.input_utils", "time", "typing" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_control.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-device-control", "name": "robosuite device teleoperation", "summary": "Teleoperate a simulated robot with an upstream supported input device.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "teleoperation", "device-control" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_device_control.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_device_control.py", "sha256": "9085aa5dcc0119a13b8b1f4c49632a14201519d669cdeed3231656519b68e4cc", "bytes": 10844 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "argparse", "copy", "numpy", "robosuite", "robosuite.controllers.composite.composite_controller", "robosuite.devices", "robosuite.devices.mjgui", "robosuite.wrappers", "time" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_device_control.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-domain-randomization", "name": "robosuite domain randomization", "summary": "Apply upstream domain randomization to visual and physical environment properties.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "domain-randomization", "simulation" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_domain_randomization.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_domain_randomization.py", "sha256": "adb60909d959f5f2dff10bd4f078348118f5816bc326ab325442d7cce784f821", "bytes": 2573 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "mujoco", "robosuite.macros", "robosuite.utils.input_utils", "robosuite.wrappers" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_domain_randomization.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-gripper-interaction", "name": "robosuite gripper interaction", "summary": "Run an upstream gripper interaction test scene.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "gripper", "contact" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_gripper_interaction.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_gripper_interaction.py", "sha256": "5c8005d1c24d1c09219147c95da4af9d3c15163eb21c80af65f0365ca54b909e", "bytes": 5007 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "robosuite.models", "robosuite.models.arenas.table_arena", "robosuite.models.grippers", "robosuite.models.objects", "robosuite.utils", "robosuite.utils.binding_utils", "robosuite.utils.mjcf_utils", "xml.etree.ElementTree" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_gripper_interaction.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-gripper-selection", "name": "robosuite gripper selection", "summary": "Select robot and gripper models and simulate an upstream manipulation environment.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "gripper", "robot-model", "manipulation" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_gripper_selection.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_gripper_selection.py", "sha256": "acb722b947a495256304e683de2cca8dbb56bf27a377a8b216fd99080a1edd34", "bytes": 1663 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "numpy", "robosuite", "time" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_gripper_selection.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-gym-functionality", "name": "robosuite Gym wrapper", "summary": "Use the upstream GymWrapper interface around a manipulation environment.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "gym", "environment", "reinforcement-learning" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_gym_functionality.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_gym_functionality.py", "sha256": "150c7e7217be2ec220430a5b091da37ed4f2280e2fc8611e37a44b7287e15bcf", "bytes": 2168 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "robosuite", "robosuite.wrappers" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_gym_functionality.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-random-action", "name": "robosuite random action environment", "summary": "Create an upstream robot manipulation environment and step random actions.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "environment", "manipulation", "quickstart" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_random_action.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_random_action.py", "sha256": "1b9e5a0407b26410d907e7d52a52c60e429e1f289b0d334c262c64bd14cec8f8", "bytes": 2284 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "robosuite.utils.input_utils", "time" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_random_action.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-segmentation", "name": "robosuite segmentation observations", "summary": "Render and inspect instance, class, or element segmentation observations.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "segmentation", "camera", "perception" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_segmentation.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_segmentation.py", "sha256": "f0985b450ded3b90d5a6343e5d3311adf4d952e36776fb6fb91be42b443e0a40", "bytes": 3616 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "PIL", "argparse", "colorsys", "imageio", "json", "matplotlib.cm", "numpy", "random", "robosuite" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_segmentation.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-sensor-corruption", "name": "robosuite sensor corruption", "summary": "Add upstream sensor noise, delay, and corruption to observations.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "sensing", "domain-randomization", "robustness" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_sensor_corruption.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_sensor_corruption.py", "sha256": "9f6828fd293279fc86e61898867fca4823fc42192ac2670009dbd3d36a141f0e", "bytes": 10298 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "argparse", "copy", "cv2", "numpy", "robosuite", "robosuite.controllers.composite.composite_controller", "robosuite.devices", "robosuite.utils.observables", "robosuite.wrappers", "sys" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_sensor_corruption.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } }, { "id": "robosuite-demo-video-recording", "name": "robosuite video recording", "summary": "Record a manipulation environment's camera frames to video.", "framework": "robosuite", "kind": "official_example", "capabilities": [ "video", "camera", "simulation" ], "source": { "repository": "https://github.com/ARISE-Initiative/robosuite", "commit": "a071383d53568ab798eb315c0e95357911be922d", "tag": "v1.5.1", "path": "robosuite/demos/demo_video_recording.py", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/robosuite/demos/demo_video_recording.py", "sha256": "f430c3f2d925cf47302ca23611f34e612060259fe40f0fcfb63c535843220765", "bytes": 2176 }, "license": { "spdx": "MIT", "url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/LICENSE", "scope": "Example source code. Robot models, textures, logs, and third-party assets retain their own upstream licenses." }, "access": { "mode": "source_reference", "hub_prepare": false, "instructions": "Open the pinned source and follow upstream setup and invocation. This entry has no Hub runtime adapter.", "setup_url": "https://github.com/ARISE-Initiative/robosuite/blob/a071383d53568ab798eb315c0e95357911be922d/README.md" }, "requirements": { "python": "upstream-defined; setup.py declares >=3, dependencies impose additional constraints", "packages": [ "robosuite==1.5.1" ], "display": "OpenGL/MuJoCo rendering and upstream robot assets are required; teleoperation demos also need an input device.", "source_imports": [ "argparse", "imageio", "numpy", "robosuite", "robosuite.macros" ] }, "invocation": { "entrypoint": "python robosuite/demos/demo_video_recording.py", "notes": "Inspect source arguments and local paths first. Run from the pinned upstream checkout as documented; examples may open a window, run continuously, or expect existing data. No success-rate or task-completion guarantee is attached." }, "popularity": { "metric": "github_stars", "repository_stars": 2666, "checked_at": "2026-10-17", "meaning": "Repository interest proxy, not example usage or install count." }, "evidence": { "level": "source_reviewed", "runtime_verification": "not_run", "checked_at": "2026-10-17", "inspection": "Fetched the exact source file, parsed Python/imports or located its native main/notebook cells, and inspected the repository license." } } ] } ```