メニュー
Fetches web content with intelligent content extraction, converting HTML to clean markdown. Use for documentation, articles, and reference pages http/https URLs.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | web-fetch |
| description | Fetches web content with intelligent content extraction, converting HTML to clean markdown. Use for documentation, articles, and reference pages http/https URLs. |
Fetch web content using curl | html2markdown with CSS selectors for clean, complete markdown output.
Use site-specific selectors for best results:
# Anthropic docs
curl -s "<url>" | html2markdown --include-selector "#content-container"
# MDN Web Docs
curl -s "<url>" | html2markdown --include-selector "article"
# GitHub docs
curl -s "<url>" | html2markdown --include-selector "article" --exclude-selector "nav,.sidebar"
# Generic article pages
curl -s "<url>" | html2markdown --include-selector "article,main,[role=main]" --exclude-selector "nav,header,footer"
| Site | Include Selector | Exclude Selector |
|---|---|---|
| platform.claude.com | #content-container | - |
| docs.anthropic.com | #content-container | - |
| developer.mozilla.org | article | - |
| github.com (docs) | article | nav,.sidebar |
| Generic | article,main | nav,header,footer,script,style |
For sites without known patterns, use the Bun script which auto-detects content:
bun ~/.claude/skills/web-fetch/fetch.ts "<url>"
cd ~/.claude/skills/web-fetch && bun install
When a site isn't in the patterns list:
# Check what content containers exist
curl -s "<url>" | grep -o '<article[^>]*>\|<main[^>]*>\|id="[^"]*content[^"]*"' | head -10
# Test a selector
curl -s "<url>" | html2markdown --include-selector "<selector>" | head -30
# Check line count
curl -s "<url>" | html2markdown --include-selector "<selector>" | wc -l
--include-selector "CSS" # Only include matching elements
--exclude-selector "CSS" # Remove matching elements
--domain "https://..." # Convert relative links to absolute
| Method | Anthropic Docs | Code Blocks | Complexity |
|---|---|---|---|
| Full page | 602 lines | Yes | Noisy |
--include-selector "#content-container" | 385 lines | Yes | Clean |
| Bun script (universal) | 383 lines | Yes | Clean |
Wrong content selected: The site may have multiple articles. Inspect the HTML:
curl -s "<url>" | grep -o '<article[^>]*>'
Empty output: The selector doesn't match. Try broader selectors like main or body.
Missing code blocks: Check if the site uses non-standard code formatting.
Client-rendered content: If HTML only has "Loading..." placeholders, the content is JS-rendered. Neither curl nor the Bun script can extract it; use browser-based tools.
Review product and feature risk before an AI coding agent starts implementation.
Use Xquik for X data and confirmation-gated X actions: tweet search, user lookup, follower export, media download, monitors, webhooks, MCP, and SDK workflows.
Use Xquik from Hermes Agent for X search, posting, replies, likes, retweets, follows, DMs, monitors, extraction jobs, draws, media, and trends.
Discover and extract sitemaps from any website using SitemapKit. Use this skill whenever the user wants to find pages on a website, get a list of URLs from a domain, audit a site's structure, crawl a sitemap, check what pages exist on a site, or do anything involving sitemaps or site URL discovery — even if they don't explicitly say "sitemap". Requires the sitemapkit MCP server configured with a valid SITEMAPKIT_API_KEY.
GitHubのプルリクエスト（PR）を作成する際に使用します。変更のコミット、プッシュ、PR作成を含む完全なワークフローを日本語で実行します。「PRを作って」「プルリクエストを作成」「pull requestを作成」などのリクエストで自動的に起動します。
Canton Network open-source ecosystem guide covering DAML SDK, Canton runtime, and Splice applications. Use when working with Canton Network, DAML smart contracts, or building decentralized applications.