md-fetch-summarize
Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of <url>". Proactively suggest when the user pastes a URL and asks what it contains. (munder-difflin)
来源信息
- 仓库
- HarnessMD/munder-difflin
- 最近来源活动
- 2026年6月15日 20:57
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 8,785
- 分支
- 1,219
安装方式
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
检查来源文件
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- name
- md-fetch-summarize
- version
- 1.0.0
- description
- Fetch a URL and return a concise markdown summary of its content. Read-only: no files are written; the summary is returned as output only. Use when asked to "fetch and summarize", "summarize this URL", "what does this page say", or "get the content of <url>". Proactively suggest when the user pastes a URL and asks what it contains. (munder-difflin)
- allowed-tools
- ["WebFetch","Bash"]
## Fetch & Summarize
Given a URL, fetch its content and return a concise markdown summary.
Steps:
1. Fetch the page with `WebFetch` (or `Bash` with `curl -sL <url> | head -200` as a fallback).
2. Extract the main content — ignore nav, footer, ads, and boilerplate.
3. Return a structured summary with:
- **Title** (the page's `<title>` or heading)
- **One-paragraph overview** of what the page is about
- **Key points** as a bullet list (max 5)
- **Source** — the URL fetched
Do not save or write the fetched content anywhere. Return the summary directly.
在 GitHub 查看