FE

Download Markdown content instead of HTML when available.

Install

mkdir -p .claude/skills/fetch-url-md && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/16988" && unzip -o skill.zip -d .claude/skills/fetch-url-md && rm skill.zip

Installs to .claude/skills/fetch-url-md

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Fetch web content with automatic markdown version detection using curl. Use when Claude needs to retrieve documentation from websites that offer both HTML and markdown formats. First checks if a .md version exists (more efficient and cleaner), then falls back to HTML if unavailable. Ideal for fetching documentation from sites like ui.shadcn.com, GitHub wikis, or any documentation site that mirrors content in markdown format.
428 chars✓ has a “when” triggerlonger than Claude Code's old 250-char listing cap (fine on current versions)
Beginner

Key capabilities

  • Parse the original URL to extract base and path
  • Check for the existence of a `.md` version of a URL using a HEAD request
  • Fetch content from the `.md` URL if it exists
  • Fall back to fetching content from the original HTML URL if no `.md` version is found
  • Handle HTTP 200 OK for existing Markdown versions
  • Handle HTTP 404 Not Found for non-existent Markdown versions

How it works

This skill fetches web content by first constructing a `.md` version of the provided URL and checking its existence with a HEAD request. If the `.md` version is found, it fetches that content; otherwise, it falls back to fetching the original HTML content.

Inputs & outputs

You give it
A web URL, e.g., `https://ui.shadcn.com/docs/components/radix/aspect-ratio`
You get back
The content of the Markdown version of the URL, or the HTML content if Markdown is unavailable

When to use fetch-url-md

  • Fetching documentation
  • Retrieving Markdown mirrors
  • Web scraping documentation

About fetch-url-md

Automates the process of checking for and retrieving a .md version of a URL, falling back to HTML if a Markdown version is unavailable.

Fetch web content with automatic markdown version detection using curl. Use when Claude needs to retrieve documentation from websites that offer both HTML and markdown formats. First checks if a .md version exists (more efficient and cleaner), then falls back to HTML if unavailable. Ideal for fetchi

When not to use it

  • When the content is known to exist only in HTML format
  • When the content is not expected to have a Markdown mirror
  • When the task does not involve retrieving documentation from websites

Limitations

  • Relies on the convention of `.md` suffix for Markdown versions
  • Assumes `curl` is available for HTTP requests
  • Does not explicitly handle all HTTP 3xx redirect scenarios beyond following or falling back

How it compares

This skill automates the process of prioritizing and retrieving Markdown content over HTML, providing a more efficient and cleaner source for documentation when available, unlike simply fetching the original URL.

Compared to similar skills

fetch-url-md side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
fetch-url-md (this skill)06moReviewBeginner
baoyu-url-to-markdown94moReviewIntermediate
web-to-markdown76moNo flagsIntermediate
firecrawl-core-workflow-a01moReviewBeginner

Try saying

Example prompts that trigger this skill in your AI assistant.

You might also like

baoyu-url-to-markdown

JimLiu

Fetch any URL and convert to markdown using Chrome CDP. Supports two modes - auto-capture on page load, or wait for user signal (for pages requiring login). Use when user wants to save a webpage as markdown.

942

web-to-markdown

davila7

Use ONLY when the user explicitly says: 'use the skill web-to-markdown ...' (or 'use a skill web-to-markdown ...'). Converts webpage URLs to clean Markdown by calling the local web2md CLI (Puppeteer + Readability), suitable for JS-rendered pages.

734

firecrawl-core-workflow-a

jeremylongshore

Execute FireCrawl primary workflow: Core Workflow A. Use when implementing primary use case, building main features, or core integration tasks. Trigger with phrases like "firecrawl main workflow", "primary task with firecrawl".

00

okf-to-web

yzfly

把符合 OKF v0.1 的知识包打包成单个自包含且经过压缩(minify)的 HTML 文件, 内嵌导航, Markdown 阅读器与概念关系图谱, 数据不出页面, 无需后端. 适用场景包括把 OKF bundle 变成一个可分享的单文件网页, 离线浏览知识库, 生成对标官方 viz.html 的可视化. 当用户提到 okf to web, OKF 转单文件网页, 可视化 OKF, minify 知识库, 或要一个自包含 HTML 时触发.

00

defuddle

ludotype

Extract clean markdown content from web pages using Defuddle CLI, removing clutter and navigation to save tokens. Use instead of WebFetch when the user provides a URL to read or analyze, for online documentation, articles, blog posts, or any standard web page. Do NOT use for URLs ending in .md — tho

00

qmd

tobi

Search personal markdown knowledge bases, notes, meeting transcripts, and documentation using QMD - a local hybrid search engine. Combines BM25 keyword search, vector semantic search, and LLM re-ranking. Use when users ask to search notes, find documents, look up information in their knowledge base, retrieve meeting notes, or search documentation. Triggers on "search markdown files", "search my notes", "find in docs", "look up", "what did I write about", "meeting notes about".

2669

Search skills

Search the agent skills registry