القائمة
High-performance web crawler that converts web pages to clean Markdown.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
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。
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.
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.
استنادا إلى تصنيف SOC المهني
| name | crawl4ai |
| description | High-performance web crawler that converts web pages to clean Markdown. |
A high-performance web crawler designed for AI agents. It fetches web pages and converts them into clean, LLM-friendly Markdown, stripped of ads and navigation clutter.
Use this skill when you need to:
Do NOT use this for:
Browser Subagent.This skill uses a Python script engine.py managed by uv (or pip).
To crawl a URL, run the following command structure using run_command.
Important:
uv command is preferred as it handles virtual environments automatically.# Option 1: Using uv (Recommended)
cd "<skill-directory>" # resolve from skill location
uv run scripts/engine.py --url "https://example.com"
# Option 2: Using python (if uv is not available, requires dependencies installed)
cd "<skill-directory>" # resolve from skill location
pip install -r pyproject.toml # (pseudo-command, install dependecies first)
python scripts/engine.py --url "https://example.com"
The command prints a JSON object to stdout.
{
"success": true,
"url": "...",
"content": "# Markdown Content...",
"metadata": {...}
}
Always check "success". If false, checking "error".