Principles Agent

基于第一性原理思维的迭代式 Agent，拆解复杂目标为原子任务，自动验证调试并依赖感知执行保证最终交付质量。

This skill appears coherent and consistent with its description: it orchestrates decomposition and delegates LLM calls to the host. Before installing, note: (1) run it inside OpenClaw or provide a proper llm_call function — the CLI will raise if llm_call isn't injected; (2) the code contains some minor implementation issues (some methods build prompts then parse the prompt as if it were an LLM response), which are likely bugs rather than malicious behavior; (3) the skill writes a report only when you pass --output (so be cautious about the output path you provide). If you plan to run this in production, review the code for robustness around JSON extraction and error handling and test it in a sandboxed OpenClaw session first.

Type: OpenClaw Skill Name: principles-agent Version: 0.2.0 The principles-agent skill is a legitimate implementation of a task-decomposition framework based on first-principles thinking. The code (orchestrator.py, executor.py, etc.) focuses entirely on logic flow, iterative refinement, and topological sorting of tasks, relying on the host environment to provide LLM access. It adheres to its stated permission boundaries, containing no network requests, environment variable access, or unauthorized file system operations. The internal prompts used for the AI agent are strictly aligned with the framework's purpose and do not contain malicious instructions or injection attempts.