发现优质的 AI Agent 技能
聚合 Claude Skills、LangChain、AutoGPT 等优质资源,助力开发者快速构建智能应用
Clawdio — Auditory Intelligence for AI Agents
Clawdio, powered by VAIL (Voice AI Layer), gives AI agents **auditory perception** by transforming long-form human audio into structured data, semantic reports, and machine-readable markdown.
YouTube Archiver
Use this skill to import YouTube playlists into markdown files and optionally enrich notes with transcript, summary, and tagging.
使用特定后端
python .claude/skills/pdf-process/script/pdf_parser.py \ '{"name": "pdf_to_markdown", "arguments": {"file_path": "/path/to/document.pdf", "output_dir": "/path/to/output", "backend": "pipeline"}}' python .claude/skills/pdf-process/script/pdf_parser.py \ '{"name": "pdf_to_markdown", "arguments": {"file_path": "/path/to/document.pdf", "output_dir": "/path/to/output", "start_page": 0, "end_page": 5}}' ```
Use specific backend
python .claude/skills/pdf-process/script/pdf_parser.py \ '{"name": "pdf_to_markdown", "arguments": {"file_path": "/path/to/document.pdf", "output_dir": "/path/to/output", "backend": "pipeline"}}' python .claude/skills/pdf-process/script/pdf_parser.py \ '{"name": "pdf_to_markdown", "arguments": {"file_path": "/path/to/document.pdf", "output_dir": "/path/to/output", "start_page": 0, "end_page": 5}}' ```
Team Brief Template
<!-- Formal exception: team briefs are orchestration artifacts consumed by the lead/orchestrator. Canonical format is Markdown for readability and coordination. The XML-equivalent 8 core tags are still REQUIRED conceptually and must be explicitly mapped. Markdown sections below are the normative representation of those tags. -->
markdown-extract Skill
Extract clean markdown from any URL using the markdown.new API.
Feishu Card Skill
Send rich interactive cards to Feishu (Lark) users or groups. Supports Markdown (code blocks, tables), titles, color headers, and buttons.
StripFeed
Convert any URL to clean Markdown optimized for LLM consumption. Strips ads, navigation, scripts, and noise. Returns token counts so you know exactly how much context you're using.
DocuClaw Skill
DocuClaw provides a sovereign data infrastructure for processing and archiving documents. It uses multimodal LLMs to extract structured information from scans, photos, and emails, storing everything in human-readable, version-controllable Markdown files.
DeepReader
The default web content reader for OpenClaw agents. Automatically detects URLs in messages, fetches content using specialized parsers, and saves clean Markdown with YAML frontmatter to agent memory.
qmd - Quick Markdown Search
Local search engine for Markdown notes, docs, and knowledge bases. Index once, search fast.