Web Fetch

Fetch a URL and save the body to a temp file so you can pipe it through rg / jq / awk instead of dumping the whole page into the conversation. Use this whenever a user gives you a URL to read - articles, docs, PRs, gists, README files, blog posts, anything HTTP. Returns a path on disk; the agent then greps the path for the relevant section and quotes only what matters. Strongly preferred over the built-in webfetch tool when (a) the page is more than a few KB, (b) the user wants to find a specific phrase / table / code block on the page, (c) you need to keep the long page out of context, or (d)

6 starsWriting & Content

Install

skills CLI (Claude Code, Cursor, Codex and more)

npx skills add code-yeongyu/web-fetch --skill web-fetch

Manual install

git clone --depth 1 https://github.com/code-yeongyu/web-fetch.git /tmp/web-fetch
mkdir -p ~/.claude/skills
cp -r /tmp/web-fetch/. ~/.claude/skills/web-fetch

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# web-fetch

Fetch a URL, write the body to `$TMPDIR/web-fetch-<runid>/`, print the path. Pipe the path through `rg` / `jq` / `awk` to surgically extract what you need.

## Why this skill exists

The built-in `webfetch` tool dumps the whole rendered page into the conversation. For anything bigger than a few KB that drowns the context window. The fix is dead simple: **write the page to disk, then grep it**.

That is all this skill does. One curl call, one Cloudflare-aware retry, HTML → Markdown via stdlib, save to a temp dir, print the path. No providers, no fallback chain, no fancy machinery. The same shape as `pi-webfetch` and `opencode/webfetch`, but as a standalone skill that works from any agent (Claude Code, OpenCode, pi, hermes, openclaw, whatever speaks Bash).

## When to use it

Trigger this skill any time the user hands you a URL and the goal is to read its content. Examples:

- "Fetch <https://docs.python.org/3/library/asyncio.html> and tell me about TaskGroup."
- "Read the README at <https://github.com/anthropics/anthropic-sdk-python>."
- "What does this article say about <topic>? <URL>"
- "Pull <PR url>, what's the key change?"
- "Fetch the page and pull out only the deprecated section."

If the URL is `https://example.com` and you only need 3 lines, the built-in tool is fine. Use this skill when the page is **non-trivially large** or you want to **filter before reading**.

## How to invoke it

Read the full skill on GitHub

Details

Skill name: web-fetch
Repository: code-yeongyu/web-fetch
License: MIT
Repo updated: 12 June 2026

FAQ

What does the Web Fetch skill do?

How do I install the Web Fetch skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add code-yeongyu/web-fetch --skill web-fetch. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Web Fetch popular?

It lives in code-yeongyu/web-fetch, which has 6 GitHub stars and 0 forks.

Related skills

Doc Builder

naggarwal1/doc-builder

Turn rough content into a clean, branded, responsive interactive HTML document. Trigger on "interactive doc", "HTML doc", "turn this into a doc", "make this look good", "style this", or when the user wants a document output instead of a PDF. Covers pitch decks, investor updates, sales proposals, one-pagers, articles, memos, strategy docs. Output is a single self-contained HTML file with TOC, collapsibles, slide nav for decks, and paged layouts for proposals. Works on mobile and prints cleanly.

Writing & Content

Understandable

hsheimbuch/understandable

Makes Claude's prose easy to read on the first pass, using findings from the 2026 study "Why is AI-generated language so hard to understand?" (Clark, Martin, and Mahowald). Use it when the user says a reply is dense, cryptic, jargon-heavy, hard to follow, or "Claudish", or asks for plainer or clearer wording. Also use it when writing or editing prose that people will read closely, such as explanations, end-of-task summaries, documentation, READMEs, and pull request descriptions. It can cover Claude's own replies for the rest of a session, or rewrite and check text and files that the user suppl

Writing & Content

Seedance Storyboard

ouxxyy/storyboard-scavenger

将任何想法转换成 AI 视频分镜提示词（Kling 可灵 / Seedance 即梦 / Sora 等）。当用户想要生成视频、制作短视频、创作分镜、使用可灵/Kling、Seedance/即梦、Sora、Runway 等 AI 视频工具时调用。

Writing & Content

Stop Slop Zh

wdkang123/stop-slop-zh

Remove predictable AI writing patterns from Chinese prose. Use when drafting, editing, rewriting, or reviewing Chinese blogs, reports, essays, product analysis, and social posts to make them specific, natural, and authorial without changing facts.

Writing & Content

Speedread Report

jordan-gibbs/speedread-skill

Turn a markdown summary/report into a pop-up RSVP speed-reader the user can consume at 500+ WPM. Use when the user asks for a report, summary, digest, or research writeup they want to "speedread", or says things like "make me a report and load it into the reader". Writes the report as markdown, injects it into a self-contained HTML reader, and opens it in the browser.

Writing & Content

Skill Registry

dungnotnull/game-account-phishing-protection-agent-skill

Complete documentation of skill registration, resolution, execution, and validation for the game-account-phishing-protection harness. Includes input/output JSON schemas, dependency management, and lifecycle hooks.

Writing & Content

Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.