Openclaw Ref

OpenClaw 配置、CLI、排错、模型管理完整参考手册。修改 openclaw.json、执行 CLI 命令、排查问题时必须查阅此 Skill。

This skill is a local reference manual and is internally consistent with its stated purpose. It does not ask for secrets or install code. Before enabling an agent to autonomously use it, consider: (1) the skill's runtime advice includes using a 'read' operation to open files under ~/.openclaw and workspace files — ensure those locations don't contain sensitive API keys or secrets you don't want the agent to read; (2) review the 'System prompts' and any injected docs for explicit 'ignore previous instructions' or other prompt-injection strings if you plan to grant the skill autonomous invocation; (3) because the skill can guide configuration edits, keep backups (as the docs recommend) before applying changes. If you are comfortable with an agent reading OpenClaw config files, this skill is appropriate to install.

Type: OpenClaw Skill Name: openclaw-ref Version: 1.0.0 The skill bundle is a comprehensive documentation and reference manual for the OpenClaw platform, covering configuration, CLI commands, troubleshooting, and security best practices. It contains only markdown files (SKILL.md and various reference docs) intended to guide an AI agent in managing the OpenClaw environment correctly. There is no evidence of malicious code, data exfiltration, or harmful prompt injections; rather, the instructions emphasize safety measures like using environment variables for keys and performing backups before configuration changes.