Skill
Data
Skill
/mcp
Use crawlberg mcp reference documentation.
Install
$ npx -y skills add xberg-io/crawlberg --skill mcp --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/mcp
Context preview
The summary Claude sees to decide when to auto-load this skill.
Use crawlberg mcp reference documentation.
SKILL.md
mcp.SKILL.mdname: "mcp" description: "Use crawlberg mcp reference documentation."
<!-- This file is auto-generated by alef — DO NOT EDIT. --> <!-- alef:hash:34de71e606bffc40dbee2c2a91d1e2ab4ff3de3ab689236df9a96abca748dc2b --> <!-- To regenerate: alef docs --> <!-- To verify freshness: alef verify -->
crawlberg MCP Reference
Use this skill when integrating crawlberg through Model Context Protocol tools, prompts, or resources.
- `batch_crawl`: Crawl multiple seed URLs concurrently. Returns crawl results for all seeds.
- `batch_scrape`: Scrape multiple URLs concurrently. Returns results for all URLs.
- `crawl`: Crawl a website following links. Returns content for all discovered pages up to max_depth/max_pages.
- `download`: Download a document from a URL. Returns metadata about the downloaded file.
- `generate_citations`: Convert markdown links into numbered citations with an appended reference list.
- `get_version`: Get the current crawlberg library version.
- `interact`: Execute browser actions on a page. Actions may mutate page or application state.
- `map`: Discover all pages on a website via links and sitemaps. Returns a list of discovered URLs.
- `scrape`: Scrape a single URL and extract content as markdown or JSON. Returns page content, metadata, links, and images.
Ships withcrawlberg
Turn any website into clean, structured data. Point Crawlberg at a URL and get back Markdown, metadata, and links — from a single page or a whole site — in the language you already use.
Get the whole plugin
Stats
188
Stars
29
Forks
Active
Maintenance
Rust
Language
MIT
License
5h ago
Last commit
7mo ago
Created
3h ago
Added