Adversarial plan review using two different AI models. Supports static mode (fixed roles) and alternating mode (models swap writer/reviewer each round, fully...
Search and discover OpenClaw skills from various sources. Use when: user wants to find available skills, search for specific functionality, or discover new s...
定义多 Agent 团队两种核心协作模式：后台 spawn 实现统一调度与汇总，Discord @mention 实现角色外显与公开协作。
Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external t...
Build and debug Kimi API workflows for chat, coding, reasoning, and tool-calling with live model checks, retries, and safe routing.
Security audit framework for AI agent skills, MCP servers, and packages. Your LLM does the analysis — we provide structure, prompts, and a shared trust database.
Route plain-language requests for Pi, Claude Code, Codex, OpenCode, Gemini CLI, or ACP harness work into either OpenClaw ACP runtime sessions or direct acpx-...
Cache and use skills from ClawHub and GitHub as if locally installed. Stores remote skills in local cache folder for offline use.
基于毛泽东思想与五位历史帝王智慧，提供战略分析、矛盾分析与组织设计的多角色决策支持系统。
Triage ideas, problems, and feature requests into the right format: proposal doc, feature issue, or bug report. Repo-aware — discovers templates and docs str...
Generate a structured GitHub repo digest with briefing summary, categorized changes (breaking/major features/minor features/bug fixes), community discussions...
Export and import AI agent avatar (aka agentar) instances as portable .claw packages for backup, sharing, and migration.
Export and import OpenClaw instances as portable .claw packages for backup, sharing, and migration. Use when: user wants to back up, share, migrate, or resto...
Install, search, update, and manage skills from ClawHub (the public OpenClaw skill registry). Use when the user wants to install a skill by slug (e.g. "clawh...
AI 驱动的多语言代码审查工具，自动检测代码质量、潜在漏洞，生成 PR 描述和单元测试用例。