菜单
Knowledge Base RAG - retrieve and answer questions from indexed knowledge (blog translations, skills docs, project docs, memory archives). Use when user asks questions that might be answered by accumulated knowledge, wants to search across the knowledge base, or asks "我们知识库里有什么关于X的". Also use for ingesting new content into the knowledge base.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
将任意主题转化为高质量蓝图风格信息图（PNG）。模板驱动 + AI 结构化，5 主题 × 4 布局 × 2 字体 = 40 种视觉变体。当用户说"生成信息图""做一张图""infographic""blueprint""一页总结"时触发。
High-performance web crawler that converts web pages to clean Markdown.
Reference documentation for AI agent capabilities including browser automation, web crawling with crawl4ai, and Codex development. Use when you need guidance on using browser automation, crawl4ai for web scraping, or Codex CLI for code generation.
Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.
Auto-discover, index, and inject coding standards from any codebase. Use when user asks to "discover standards", "extract conventions", "document patterns", or "shape a spec" for a project.
| name | kb-rag |
| description | Knowledge Base RAG - retrieve and answer questions from indexed knowledge (blog translations, skills docs, project docs, memory archives). Use when user asks questions that might be answered by accumulated knowledge, wants to search across the knowledge base, or asks "我们知识库里有什么关于X的". Also use for ingesting new content into the knowledge base. |
| description_zh | 知识库 RAG 检索：从已索引的知识（博客翻译、技能文档、项目文档、记忆归档）中检索和回答问题。 |
| Collection | Content | Path |
|---|---|---|
| kb-articles | Blog translations & analysis | output/blog-translations/ |
| kb-skills | Skill documentation | skills/**/SKILL.md |
| kb-captures | Conversation insight captures | content-pipeline/captures/ |
| kb-docs | Project documentation | docs/ |
| memory-dir | Daily notes & archives | memory/ |
| memory-root | Core memory index | MEMORY.md |
| memory-alt | Alt memory | memory.md |
Run the RAG script for end-to-end retrieve + generate:
python3 skills/kb-rag/scripts/rag_query.py "question"
Options:
-c <collection> — limit to specific collection (e.g. kb-articles)-k <N> — top-K chunks (default 8)-m <model> — LLM model (default gemini-3.1-pro-high)--retrieve-only — skip LLM, just show retrieved chunks--json — JSON outputExamples:
# General KB question
python3 skills/kb-rag/scripts/rag_query.py "OpenClaw 2026.2.13 有什么重要更新"
# Search only blog articles
python3 skills/kb-rag/scripts/rag_query.py "Agent 自主付费" -c kb-articles
# Just retrieve, no generation
python3 skills/kb-rag/scripts/rag_query.py "Peter Steinberger 的创业哲学" --retrieve-only
Direct qmd commands for quick lookups:
# Hybrid search (best quality)
qmd query "search terms" -n 5
# Vector similarity (better for semantic/fuzzy)
qmd vsearch "search terms" -n 5
# Full-text BM25 (exact term matching)
qmd search "search terms" -n 5
# Limit to collection
qmd query "search terms" -c kb-articles -n 5
New .md files dropped into indexed directories are auto-picked up on next qmd update && qmd embed.
qmd collection add /path/to/dir --name collection-name --mask "**/*.md"
qmd update && qmd embed
qmd update # re-index all collections
qmd embed # regenerate embeddings
Note: OpenClaw runs qmd update every 5 minutes automatically. Run manually only when immediate indexing is needed.
qmd vsearch (pure vector) instead of qmd query (hybrid)