通过 markdown.new 服务从任意网址获取精简、专为代理优化的 Markdown 内容。当 web_fetch 或浏览器无法提供干净内容,或需要节省令牌的网页版本以进行深度分析时使用。
通过 markdown.new 服务从任意网址获取精简、专为代理优化的 Markdown 内容。当 web_fetch 或浏览器无法提供干净内容,或需要节省令牌的网页版本以进行深度分析时使用。
Fetch clean, token-efficient Markdown from URLs via markdown.new when web_fetch or browser tools fail
Fetch clean, agent-optimized Markdown from any URL using the markdown.new service. Use when web_fetch or browser fails to provide clean content, or when you need a token-efficient version of a web page for deep analysis.
直接复制以下提示词,发送给你的 AI 助手即可完成安装。
---
name: mdnew
description: Fetch clean, agent-optimized Markdown from any URL using the markdown.new service. Use when web_fetch or browser fails to provide clean content, or when you need a token-efficient version of a web page for deep analysis.
---
# mdnew
Fetch clean Markdown from any URL using the `markdown.new` three-tier conversion pipeline (Header Negotiation -> Workers AI -> Browser Rendering).
## Usage
Run the script with a target URL:
```bash
python3 scripts/mdnew.py <url>
```
## Why use mdnew?
1. **Token Efficiency**: Reduces content size by up to 80% compared to raw HTML.
2. **Clean Data**: Strips boilerplate, ads, and nav menus, leaving only core content.
3. **JS Execution**: Automatically handles JS-heavy pages via Cloudflare Browser Rendering fallback.
4. **Agent-First**: Includes `x-markdown-tokens` tracking to help manage context windows.
文件内容直接读取自技能仓库,仅供安装前审阅;以实际下载的压缩包为准。