Openclaw Cc Rules

提供基于顶级 AI 编程工具的结构化工作流规范，涵盖计划、任务追踪、只读探索、Git 操作安全及多文件变更策略。

This skill is internally consistent: it is a ruleset that tells the agent to read repo files and run read-only git commands before making changes. Things to consider before installing: 1) SKILL.md will cause the agent to automatically examine code whenever it senses a coding scenario—if you prefer manual control, change the trigger or keep it user-invocable only. 2) The README suggests cloning from a third‑party GitHub repo (owner 'badxtdss'); do not git-clone or run code from unknown repositories without review. 3) Because the skill uses exec/read operations, verify the agent environment (git availability, workspace permissions) and review the SKILL.md/README locally to ensure the activation rules and allowed commands match your security policy. If you want higher assurance, request the author/source or inspect a local copy before enabling automatic activation.

Type: OpenClaw Skill Name: openclaw-cc-rules Version: 1.0.0 The 'openclaw-cc-rules' skill bundle provides a structured and defensive programming workflow for AI agents, emphasizing a 'Plan-before-Action' methodology. The instructions in SKILL.md include safety protocols that explicitly forbid destructive Git commands (e.g., git push --force) and mandate the exclusion of sensitive files like .env or credentials.json from commits. While the README.md contains informal language regarding the origin of the rules ('leaked CC'), the actual logic is focused on improving code quality and operational safety without any evidence of malicious intent or data exfiltration.