AI Agent Skills for website2markdown — convert any URL to Markdown. Compatible with Claude Code, OpenClaw, Cursor, and AgentSkills-compatible agents.
# website2markdown-skills
> Convert any web page to clean Markdown from your AI agent. One command install, auto-discovered.
[](LICENSE)
[](https://md.genedai.me)
[](https://github.com/Digidai/website2markdown)
[](https://www.npmjs.com/package/@digidai/mcp-website2markdown)
## Quick Install
**Pick your agent, run one command:**
```bash
# Claude Code
git clone https://github.com/Digidai/website2markdown-skills ~/.cursor/skills/website2markdown
# OpenAI Codex CLI
git clone https://github.com/Digidai/website2markdown-skills ~/.codex/skills/website2markdown
# Cursor CLI
git clone https://github.com/Digidai/website2markdown-skills ~/.cursor/skills/website2markdown
# OpenClaw (via ClawHub)
npx clawhub@latest install website2markdown
# Cursor / Windsurf / Other agents
git clone https://github.com/Digidai/website2markdown-skills .cursor/skills/website2markdown
```
That's it. Open a new session and the skill is auto-discovered.
### Verify
```
You: Read this article: https://example.com
Agent: [Uses md.genedai.me API → returns clean Markdown]
```
### Update
```bash
cd ~/.cursor/skills/website2markdown && git pull
```
## What It Does
Teaches your AI agent to convert **any URL** to clean Markdown — JS-heavy SPAs, paywalled content, anti-bot pages, and 21 Chinese/international platforms.
```
You: Read this WeChat article: https://mp.weixin.qq.com/s/abc123
Agent: [Calls md.genedai.me with force_browser=true]
# 深度解析:大模型在企业的落地实践
> 作者:张三 | 2026-03-25
## 核心观点
1. 大模型的应用场景正在从实验室走向生产环境...
```
```
You: Compare these 3 blog posts and summarize the differences
Agent: [Uses batch API to fetch all 3 in one request, then compares]
```
```
You: Crawl the CloAgent that generates comprehensive documentation, API references, architecture diagrams, and developer onboarding guides from existing code.
Agent configuration for systematic bug investigation that traces issues from error logs through the codebase to root cause with suggested fixes.
Agent for integrating third-party APIs including SDK setup, type generation, error handling, retry logic, and rate limit management.
Cursor's built-in autonomous coding agent that can make multi-file edits, run terminal commands, search the codebase, and iteratively build features with minimal human intervention.
Cloud-based autonomous coding agent that runs in the background on remote sandboxed environments, handling complex multi-step tasks while you continue working.
Cursor's multi-file editing agent within Composer mode that can create, edit, and delete files across your entire project in a single conversation.