Expertise-aware model router with semantic domain scoring, context-overflow protection, and security redaction. Automatically selects the optimal AI model using weighted expertise scoring (Feb 2026 be
代码审查、重构建议、安全漏洞检查、命名规范、复杂度分析、注释文档生成. Use when you need code reviewer cn capabilities. Triggers on: code reviewer cn, 圈复杂度估
Assist with programming tasks using Claude CLI. Use when OpenClaw needs to perform coding tasks, create new programs, modify existing code, or get programmin...
Stop sending 'format this JSON' to Opus. Stop sending 'redesign the auth system' to Haiku. Smart Model Router picks the right brain for every task — decision...
Automatically read relevant context before major actions. Loads TODO.md, roadmap.md, handoffs, task plans, and other project context files so the AI operates with full situational awareness. Use when
Smart LLM routing brain for OpenClaw. Auto-dispatches tasks to Claude, GPT, Gemini, DeepSeek, Kimi via Evolink API. Cascade strategy cuts costs 60-85%. One A...
完整的 AI 驱动编程工作流。包含：(1) 多团队并行开发（OpenClaw + Claude Code/Codex/OpenCode），(2) 一人公司模式（单日 90+ 提交），(3) Playwright 自动化测试（E2
Resume multi-session projects with full context retention. Use when returning to previous work, needing conversation history, recalling past decisions, or br...
A lateral thinking engine for stuck moments. When logical, systematic approaches have failed, Dream State imports solution patterns from completely unrelated...
Structured Read→Plan→Execute→Verify→Report protocol for any task with side effects. Prevents false "done" reports, blind retries, and scope creep. Activate f...
Local git operations for project management. Use when: (1) creating branches for new features/issues, (2) committing and pushing code, (3) pulling latest cha...
Generate changelogs from git commit history with conventional commit parsing. Use when asked to generate a changelog, create release notes, summarize git his...
Autonomously breaks coding tasks into spec, plan, code, and QA phases, executing all heavy work via Claude Code with multi-account rate limit rotation.
Deterministically coordinates autonomous planning and execution across available skills under strict guardrails. Use only when the user explicitly activates this skill by name to run autonomously unti
Write messages to your future self — or your future team — that unlock when specific code conditions are met. "Dear future me: if you're reading this, someon...
Delegate coding tasks to Codex, Claude Code, or Pi agents via background process. Use when: (1) building/creating new features or apps, (2) reviewing PRs (sp...
--- name: emp description: EMP Skill for OpenClaw – empathetic, role-based task routing version: 0.1.0 homepage: https://github.com/zzj0402/emp metadata: {"clawdbot":{"emoji":"🦒","requires":
Transforms your git history into poetry — sonnets from sprint logs, haiku from hotfixes, limericks from legacy code, and epic ballads from major rewrites. Tu...
--- name: cc-godmode description: "Self-orchestrating multi-agent development workflows. You say WHAT, the AI decides HOW." metadata: clawdbot: emoji: "🚀" author: "cubetribe" version:
Structured 5-phase AI-assisted development workflow (requirements → architecture → code generation → debugging → iteration). Use when the user mentions "vibe...
Standardized Git commit message templates using changelog-style categories. Use when creating Git commits with structured format - Added (new features), Chan...
UI/UX design intelligence for web and mobile. Includes 50+ styles, 161 color palettes, 57 font pairings, 161 product types, 99 UX guidelines, and 25 chart ty...
# gemini.md You are a senior full-stack software engineer with 20+ years of production experience. You value correctness, clarity, and long-term maintainability over speed. --- ## Scope & Authori
Agent communication protocol skill. Provides: inter-agent messaging, context snapshot/restore, event-driven collaboration, model dispatch notifications, sub-...