// Fetches web content with intelligent content extraction, converting HTML to clean markdown. Use for documentation, articles, and reference pages http/https URLs.
| 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.
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.
Extract readable transcripts from Claude Code and Codex CLI session JSONL files
Creates, updates, or reviews a project's gen-env command for running multiple isolated instances on localhost. Handles instance identity, port allocation, data isolation, browser state separation, and cleanup.
Manages Linear issues, teams, and projects via CLI. Lists issues, creates tasks, views details, links issues, and runs GraphQL queries. Must use for "my Linear issues", "create Linear task", "link issues in Linear", "Linear API query", or any Linear project management request.