Robot Skill Hub by Superfast Robotics

Shadow DexEE distal-finger curl control

Control six named distal finger joints through the original MuJoCo PID plugin; no object-grasp or hardware claim.

mujoco-shadow-dexee-finger-control | Record version: 1.0.0

Record JSON | Markdown recipe | Complete search index

Fetch and prepare

curl -fsSL https://hub.superfastrobotics.com/skills/mujoco-shadow-dexee-finger-control/skill.json
curl -fsSL https://hub.superfastrobotics.com/skills/mujoco-shadow-dexee-finger-control/README.md
python /PATH_TO_SKILL/scripts/rsh.py inspect mujoco-shadow-dexee-finger-control --json
python /PATH_TO_SKILL/scripts/rsh.py prepare mujoco-shadow-dexee-finger-control --project ./experiment --expected-source-commit 62ab00f2bc44f6f20c1c9b7a13f3fb1dd41a4e35 --expected-record-version 1.0.0 --plan --json

Inspect the requirements, then remove --plan to prepare a project. Preparation verifies the archive SHA256 and preserves exact source pins. --install-deps explicitly installs dependencies. Run the returned simulation command separately.

Environment

Runtime
mujoco 3.3.7
Robot
shadow_dexee
Controller
native_plugin_pid
Observation
joint_state
OS / architecture
linux / x86_64
Python
>=3.10,<3.11

Compatibility status: hub_verified

Privileged simulator state and declared goals; no perception or real sensor validation.

Requirements

Headless. EGL libraries are required for MuJoCo imports; PushT uses SDL dummy video. No interactive display.

Packages: mujoco==3.3.7, numpy==1.26.4

Direct runtime versions are pinned and measured. The receipt retains the complete environment freeze; prepare records the installed environment. System drivers are separate host requirements.

External API keys: none.

Invocation

Executable interface

{
  "version": "1",
  "kind": "controller",
  "abstraction_level": 1,
  "execution_domain": "simulation",
  "language": "python",
  "input_transport": "json_file_or_inline",
  "output_transport": "json_stdout",
  "output_selector": "outputs",
  "conventions": {
    "linear_unit": "m",
    "angular_unit": "rad",
    "time_unit": "s",
    "coordinate_frame": "right_handed_world_xyz; +z_up",
    "joint_order": "F0/J2,F0/J3,F1/J2,F1/J3,F2/J2,F2/J3",
    "quaternion_order": "not_used"
  },
  "input_schema": {
    "type": "object",
    "required": [
      "seed",
      "joint_offset_rad"
    ],
    "properties": {
      "seed": {
        "type": "integer",
        "minimum": 0,
        "maximum": 10000
      },
      "joint_offset_rad": {
        "type": "number",
        "minimum": -0.15,
        "maximum": 0.15,
        "x-unit": "rad"
      }
    },
    "additionalProperties": false
  },
  "output_schema": {
    "type": "object",
    "required": [
      "joint_positions_rad",
      "target_joint_positions_rad",
      "max_error_rad",
      "movement_rad"
    ],
    "properties": {
      "joint_positions_rad": {
        "type": "array",
        "minItems": 6,
        "maxItems": 6,
        "items": {
          "type": "number",
          "minimum": -20,
          "maximum": 20
        },
        "x-unit": "rad",
        "x-frame": "named_model_joint_coordinates",
        "x-order": [
          "F0/J2",
          "F0/J3",
          "F1/J2",
          "F1/J3",
          "F2/J2",
          "F2/J3"
        ]
      },
      "target_joint_positions_rad": {
        "type": "array",
        "minItems": 6,
        "maxItems": 6,
        "items": {
          "type": "number",
          "minimum": -20,
          "maximum": 20
        },
        "x-unit": "rad",
        "x-frame": "named_model_joint_coordinates",
        "x-order": [
          "F0/J2",
          "F0/J3",
          "F1/J2",
          "F1/J3",
          "F2/J2",
          "F2/J3"
        ]
      },
      "max_error_rad": {
        "type": "number",
        "minimum": 0,
        "maximum": 50,
        "x-unit": "rad"
      },
      "movement_rad": {
        "type": "number",
        "minimum": 0,
        "maximum": 50,
        "x-unit": "rad"
      }
    },
    "additionalProperties": false
  },
  "preconditions": [
    "Use the exact recorded source, Linux Python 3.10 environment and pinned direct packages.",
    "No physical robot, network actuation or external robot credentials."
  ],
  "postconditions": [
    "All reported checks must be true and all output numbers finite.",
    "Success covers the declared goal and frozen cases, not arbitrary tasks or physical hardware."
  ],
  "failure_codes": [
    "invalid_input_or_environment",
    "execution_failed",
    "task_failed"
  ],
  "composition": {
    "depends_on": [],
    "automatic_frame_conversion": false,
    "automatic_hardware_execution": false
  },
  "origin_reference_ids": [
    "mujoco-menagerie-artifact-shadow-dexee-scene-xml"
  ],
  "origin_relationship": "prepared_from_the_same_pinned_model; inspect the declared controller and goal; no physical compatibility is inferred"
}

Entrypoint: python run.py

{
  "argv": [
    "{python}",
    "{recipe_dir}/run.py",
    "--source-dir",
    "{source_dir}",
    "--example"
  ],
  "inputs": {
    "seed": 0,
    "joint_offset_rad": 0.08
  },
  "outputs": {
    "format": "single JSON object",
    "payload_selector": "outputs",
    "schema": {
      "type": "object",
      "required": [
        "joint_positions_rad",
        "target_joint_positions_rad",
        "max_error_rad",
        "movement_rad"
      ],
      "properties": {
        "joint_positions_rad": {
          "type": "array",
          "minItems": 6,
          "maxItems": 6,
          "items": {
            "type": "number",
            "minimum": -20,
            "maximum": 20
          },
          "x-unit": "rad",
          "x-frame": "named_model_joint_coordinates",
          "x-order": [
            "F0/J2",
            "F0/J3",
            "F1/J2",
            "F1/J3",
            "F2/J2",
            "F2/J3"
          ]
        },
        "target_joint_positions_rad": {
          "type": "array",
          "minItems": 6,
          "maxItems": 6,
          "items": {
            "type": "number",
            "minimum": -20,
            "maximum": 20
          },
          "x-unit": "rad",
          "x-frame": "named_model_joint_coordinates",
          "x-order": [
            "F0/J2",
            "F0/J3",
            "F1/J2",
            "F1/J3",
            "F2/J2",
            "F2/J3"
          ]
        },
        "max_error_rad": {
          "type": "number",
          "minimum": 0,
          "maximum": 50,
          "x-unit": "rad"
        },
        "movement_rad": {
          "type": "number",
          "minimum": 0,
          "maximum": 50,
          "x-unit": "rad"
        }
      },
      "additionalProperties": false
    }
  }
}

Success: All declared goal and finite-state checks pass; exit 0 with task_complete. Control the six J2/J3 distal finger joints through the original PID plugin. Other hand joints retain their native reset controls. This is finger curl, not all-joint hand posture or object grasping.

Timeout: 180 seconds. Terminate the adapter at the recorded timeout. No physical hardware is opened.

Failure modes

Source and license

Repository
https://github.com/google-deepmind/mujoco_menagerie
Authors
MuJoCo Menagerie contributors and the pinned model licensors
Commit
62ab00f2bc44f6f20c1c9b7a13f3fb1dd41a4e35
Archive SHA256
6866543ef9f07fd24f3fa4d134c06b30f5276f48daf412022b6edbaf6b2f0152
License
Apache-2.0
Hub commit
ce1d44c01f1a9f707f055da0888068fe32390e62

Evidence

Runtime: task_complete / task_complete

All 3 frozen cases completed against this exact adapter and source.

Reviewer: Hub finite-case Lambda execution harness | 2026-10-20

Submitter reports and hub verification remain separate. Source review does not establish task success.