Multi Robot Skill

多机器人协同控制 Skill。让 AI Agent 具备感知反馈、动态适配、并行调度多种机器人的能力。支持机械臂、四足机器人等任意 HTTP API 机器人。

This skill appears to do what it says, but review and follow these precautions before installing: - Review and trust robot endpoints you register. The skill will issue HTTP requests to any endpoint you register, which can access your internal network (SSRF-like risk). Only register devices you control or trust. - Inspect skill.py and the adapter implementations included in the bundle (adapters/ and core/) before running, especially if you plan to auto-generate adapters at runtime. - Install dependencies (requests) in an isolated environment (virtualenv) since there is no automatic install routine provided. - If you expect to operate in a sensitive network, run the agent in a network-restricted environment or audit outbound traffic; the skill has full ability to contact the URLs you supply. - If the agent will be given API docs to parse and asked to generate executable adapter code, ensure generated code is reviewed before being loaded/executed. If you want me to, I can: (1) scan the remaining omitted files (skill.py, README, docs) for any hidden network endpoints or secrets; (2) list exact functions in skill.py that register adapters and perform network calls; or (3) produce a short checklist to safely test the skill in an isolated lab environment.

Type: OpenClaw Skill Name: multi-robot-skill Version: 2.0.0 The Multi-Robot Coordination Skill is a well-structured framework designed to allow AI agents to orchestrate tasks across multiple robots (e.g., mechanical arms and quadrupeds) using HTTP APIs. It includes a robust task planner with dependency resolution, a multi-threaded coordinator, and a state manager. The instructions in SKILL.md and OPENCLAW_INTEGRATION.md guide the AI agent to dynamically generate Python adapters for new hardware based on user-provided API documentation, which is a legitimate feature of the OpenClaw ecosystem. No evidence of data exfiltration, malicious execution, or unauthorized persistence was found across the code (skill.py, core/coordinator.py) or the extensive documentation.