git log --oneline --stat
HEAD
- Stars
- 4.1k
- Forks
- 140
- Updated
- May 5, 2026
repo --stat
stars
4.1k
forks
140
last update
May 5, 2026
license
MITv2.0.0
quickstart.sh
3 steps
- Install
// Drops SKILL.md into ~/.claude/skills/
$ claude skills add firecrawl-scraper - Invoke
// Run from any project directory
$ claude --skill firecrawl-scraper "query last week's signups" - Iterate
// Re-run with edits — Claude keeps the skill loaded
$ claude --skill firecrawl-scraper "now refactor it"
firecrawl-scraper/
references
- references/
- SKILL.mdopen
- README.mdopen
SKILL.md
readonly
- name:
- Firecrawl Scraper
- slug:
- firecrawl-scraper
- version:
- v2.0.0
- license:
- MIT
- author:
- @firecrawl
- categories:
- tags:
- #firecrawl#scraping#web#crawler#extraction
- description:
Production web scraping via Firecrawl. Handles JS sites, anti-bot, rate-limits.
features.md
4 capabilities
// What you can do with it
- Scrape (/v1/scrape) — fetches a single URL and returns Markdown, cleaned HTML, links, and metadata. Renders JS and waits for content before extracting.
- Crawl (/v1/crawl) — submits an async crawl job, polls the job id, and streams results as pages complete, honoring includePaths/excludePaths, limit, and maxDepth.
- Extract / JSON mode — pass a JSON Schema or a natural-language prompt and get typed objects back. Also surfaces JSON-LD, OpenGraph, and microdata it finds on the page.
- Map (/v1/map) — quickly enumerate a site's URLs before committing to a full crawl.
README.md
firecrawl-scraper/README.md
8 sections
Loading README…
$ cat reviews/
Reviews
// No reviews yet. Be the first.
Loading review form…