Robotics

Control mobile robots (quadruped, bipedal, wheeled, aerial) via IM platforms. Supports Unitree robots and Insight9 AI stereo camera.

Security Scan

The skill's code and runtime instructions largely match its stated purpose (IM-driven robot control), but the package is mostly stubbed/mocked, has minor inconsistencies, and should be reviewed before connecting to real hardware or providing credentials.

Purpose & Capability

The name/description (IM-driven control for Unitree robots and Insight9 camera) aligns with the included code: robot adapters for Unitree models, IM adapters for the listed platforms, and a sensor adapter for Insight9. The code implements command parsing, movement, SLAM stubs and a factory registry for supported robots. Many features are placeholders or labeled 'coming soon', which fits the project being a work-in-progress.

Instruction Scope

SKILL.md usage examples and instructions stay within robot-control bounds and don't request unrelated system data or secrets. However there are small inconsistencies: the README/SKILL example imports 'unitree_robot_skill' while the pyproject package name is 'openclaw-robotics' and the repository top-level exports differ — this may cause confusion or runtime import errors. Runtime instructions do not instruct reading system files or environment variables.

Install Mechanism

No install spec is provided in the registry metadata (instruction-only), which minimizes installer risk. The repository does include Python source files and a pyproject.toml (depends on numpy) — but no automated install script or external downloads. This is lower-risk, though the registry metadata and README recommend installing from a GitHub repo; the skill package source is listed as 'unknown' in the provided registry data, so confirm upstream source before installing.

Credentials

The skill declares no required environment variables or primary credentials. IM adapters accept configuration fields (e.g., app_secret, access_token) in a config dict but do not read env vars by themselves. This is proportionate to the stated purpose. Note: if you later provide IM credentials (WeCom/Feishu/WhatsApp tokens) via the adapter config, those are appropriate for IM integration but should be supplied securely and only after verifying the code and origin.

Persistence & Privilege

The skill does not request permanent/always-on inclusion (always:false). It does not modify other skills or system-wide settings in the provided code. Adapters are instantiated per initialization and no background services are installed by the skill itself.

Assessment

What to consider before installing or using this skill: - Source provenance: the registry metadata lists no authoritative source here — verify the repository and author (LooperRobotics) on GitHub or another trusted host before installing or giving it network/credentials access. - Incomplete / stubbed behavior: many adapters and SLAM/navigation modules are stubs or placeholders (they set connected=True and return canned data). Treat this as development code. Expect runtime errors or missing functionality (e.g., some typing/import issues) if you try to use it as-is. - Credentials: the IM adapters accept secrets in their config (app_secret, access_token, corp_secret, etc.). Those are reasonable for an IM-integrated robot controller, but the skill currently does not declare or manage them — only pass them via config. Only provide credentials after inspecting the code and confirming network endpoints. - Hardware safety: before connecting this code to real robots, perform thorough review and testing in simulation or with the robot powered off/blocked. Mistakes in motion control or parsing can cause dangerous movement. Implement hardware-level safety interlocks. - Runtime bugs: there are small inconsistencies (example import name vs package, missing typing imports in some functions) which may cause runtime exceptions. Run tests in a safe environment and review error handling. - Recommended actions: verify the upstream repository/commit, run the test suite locally, review any code that would send network requests (the adapters are currently stubs), and only provide credentials/config through secure means if you trust the source. If you need autonomous operation, add careful authorization and safety checks before enabling control of physical robots.

Unitree Robot Controller Skill

Control various mobile robots through instant messaging platforms.

Supported Robots

Code	Model	Type
unitree_go1	Unitree GO1	Quadruped
unitree_go2	Unitree GO2	Quadruped
unitree_g1	Unitree G1	Bipedal/Humanoid
unitree_h1	Unitree H1	Bipedal/Humanoid

Coming Soon

Code	Type
wheeled_*	Wheeled robots
drone_*	Aerial robots
surface_*	Surface vehicles

Supported Sensors

Code	Sensor
insight9	Looper Robotics AI Stereo Camera (RGB-D)

Navigation

• TinyNav integration for path planning and obstacle avoidance (coming soon)

Usage

from unitree_robot_skill import initialize, execute

initialize(robot="unitree_go2", im="wecom")
execute("forward 1m")
execute("turn left 45")