Summary
A web crawler that converts scraped content into LLM-friendly markdown while claiming to cut tokens by 80%. It bundles DuckDuckGo search, single-page scraping, and full-site crawling with sitemap support. The main hook is "fit_markdown" mode that strips navigation, sidebars, and ads to leave just titles, body text, and code blocks. Handles JavaScript-rendered pages with configurable wait strategies. No API keys needed, which is nice for quick scraping tasks. The bilingual documentation suggests a Chinese-speaking author targeting both markets. If you're regularly feeding scraped docs into Claude and tired of hitting context limits, this might save you some preprocessing work.
Install to Claude Code
npx -y skills add lancelin111/crawl4ai-skill --skill crawl4ai-skill --agent claude-codeInstalls into .claude/skills of the current project.
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →
Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →Files
SKILL.md
Select a file.
Featured
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →An agent that runs the SEO playbooks that move rankings and ships PRs you control.
Get founding access →Connect Claude to +800M contacts, +150M companies. Find & Enrich leads in chat.
Try For Free →First SeenJun 3, 2026
