← Back to Skills Marketplace
hanqiudeng

EASY_CRAWL4AI

by aesopdeng · GitHub ↗ · v1.0.0 · MIT-0
cross-platform ✓ Security Clean
301
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install easy-crawl
Description
Use Crawl4AI to fetch and convert complex webpages, including dynamic content, into Markdown for summarization, data extraction, or analysis.
README (SKILL.md)

技能:全能网页爬取与智能解析 (Crawl4AI)

1. 环境依赖与安装 (Prerequisites)

如果系统尚未安装 Crawl4AI,Agent 应参考以下步骤进行环境部署:

  1. 核心库安装: pip3 install crawl4ai (注意:尝试pip或者pip3)
  2. 浏览器内核初始化: python3 -m playwright install chromium (下载 Playwright 所需的 Chromium 内核)
  3. 验证安装: crwl --help

2. 技能描述

当用户提供 URL 并要求“总结内容”、“提取数据”或“分析网页”时触发。利用 Crawl4AI 引擎将复杂网页(含动态 JS 渲染)精准转化为 Markdown 格式。


3. 核心指令集

读取 URL 内容到控制台:

crwl {url} -o markdown

读取 URL 内容到文件:

crwl {url} -o markdown > {file_name}.md

4. 使用示例

用户指令 预期的 Agent 行为 (Command)
"帮我看看这个网页:[URL]" crwl {URL} -o markdown
"总结这个文章:[URL]" crwl {URL} -o markdown > article.md

5. 约束与安全

  • 隐私申明: 不得爬取登录后可见的内容。
Usage Guidance
This skill appears coherent for converting web pages to Markdown, but it will cause the agent to install a PyPI package and download a Chromium browser binary. Before installing: (1) consider running the installs inside a virtual environment or sandbox so system Python/site-packages are not modified; (2) verify the 'crawl4ai' package on PyPI or inspect its source to ensure it matches expectations; (3) be aware the agent will fetch arbitrary external URLs you provide—do not give URLs that require login or contain sensitive data; (4) expect a large browser download from Playwright; (5) if you need stricter guarantees, ask the skill author for a pinned package version, checksum, or a known upstream project URL.
Capability Analysis
Type: OpenClaw Skill Name: easy-crawl Version: 1.0.0 The skill bundle provides instructions for using the legitimate Crawl4AI library to crawl and parse web content into Markdown. It includes standard installation steps (pip install crawl4ai, playwright install) and command-line usage for the crwl utility in SKILL.md. No malicious behavior, data exfiltration, or suspicious indicators were identified.
Capability Assessment
Purpose & Capability
Name/description (Crawl4AI: fetch & convert pages to Markdown) align with the runtime instructions which install 'crawl4ai' and Playwright and run the 'crwl' CLI to fetch URLs and produce Markdown.
Instruction Scope
Instructions are focused: install the Python package and Playwright, then run 'crwl {url} -o markdown' (optionally redirect to a file). They do require the agent to fetch arbitrary external URLs (expected for a crawler); the SKILL.md explicitly disallows crawling logged-in content. The instructions do not ask the agent to read unrelated files or secrets.
Install Mechanism
This is an instruction-only skill (no install spec in the registry). It tells the agent to 'pip3 install crawl4ai' and 'python3 -m playwright install chromium' — both are standard but involve network downloads (PyPI packages and browser binaries). That is proportionate to the functionality but will write to the system environment unless run inside a virtualenv or sandbox.
Credentials
The skill declares and requires no environment variables, credentials, or config paths. There are no requests for unrelated secrets or tokens.
Persistence & Privilege
The skill does not request 'always: true' and does not modify other skills. Its runtime actions (installing packages, downloading Chromium, writing output files) are standard for this functionality but do change the local environment.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install easy-crawl
  3. After installation, invoke the skill by name or use /easy-crawl
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- 首次上传 - 极简爬取网站内容转存为AI易读的Markdown文件
Metadata
Slug easy-crawl
Version 1.0.0
License MIT-0
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is EASY_CRAWL4AI?

Use Crawl4AI to fetch and convert complex webpages, including dynamic content, into Markdown for summarization, data extraction, or analysis. It is an AI Agent Skill for Claude Code / OpenClaw, with 301 downloads so far.

How do I install EASY_CRAWL4AI?

Run "/install easy-crawl" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is EASY_CRAWL4AI free?

Yes, EASY_CRAWL4AI is completely free, licensed under MIT-0. You can download, install and use it at no cost.

Which platforms does EASY_CRAWL4AI support?

EASY_CRAWL4AI is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created EASY_CRAWL4AI?

It is built and maintained by aesopdeng (@hanqiudeng); the current version is v1.0.0.

💬 Comments