发现优质的 AI Agent 技能

<context> You are a pragmatic coding assistant that writes clean, maintainable code. Your style is concise, direct, and solution-focused. You never over-engineer. You write code directly — you do not write tutorials or explain before implementing. </context>

> **Purpose:** Public repo for the AdaptiveTest OpenClaw skill. Contains the skill file, API reference docs, and ClawHub metadata. > **Owner:** James Williams - Woodstock Software LLC > **GitHub Org:** https://github.com/woodstocksoftware

> **Purpose:** Spec-only repo for the AdaptiveTest OpenClaw skill. Contains the skill file, API reference docs, and specs for backend/marketing work in other repos. > **Owner:** James Williams - Woodstock Software LLC > **GitHub Org:** https://github.com/woodstocksoftware

Source: obra/superpowers subagent-driven-development skill Adapted for OpenClaw (sessions_spawn instead of Claude Code Task tool)

Autonomous spec → plan → code → QA pipeline powered by Claude Code. All heavy computation runs through Claude Code (Max subscription). OpenClaw only orchestrates.

Check live rate-limit usage for **Claude.ai** and **OpenAI/Codex** plans, then apply pacing tiers to avoid hitting limits.

使用 Claude Code CLI 自动完成编程任务。

Generate optimized loop commands for automating Claude Code, Gemini CLI, or Grok CLI with PROMPT.md.

Query the Multisage API for multi-expert AI answers. Multisage sends your question to Claude, GPT, and Gemini simultaneously, then synthesizes their responses into a single, well-rounded answer — highlighting where they agree, disagree, and what unique insights each provides.

> System-level directives. All Claude Code agents MUST obey.

scripts/search "米兰今日天气 2026" --max-results 5 scripts/search task "@dual 对比 Claude 与 GPT-4 在代码生成上的差异" --max-results 5

Run Claude Code in background — zero OpenClaw tokens while it works. Results delivered to WhatsApp or Telegram automatically.