firecrawl-map — Claude Code skill: map a site's URLs
Lists a site's URLs and filters them by a search term. Useful when you know the domain but not the exact page.
npx skills add firecrawl/cli --skill firecrawl-map -a claude-codeWhat firecrawl-map does
The skill hands your agent the firecrawl map command, which walks a site and writes the URLs it finds to a file. On a large site, add --search to keep only matches for a word like authentication. Saving the output under .firecrawl/ makes it easy to feed those URLs into scrape or crawl next.
Authentication is required. There is no free tier for map without credentials, and the CLI starts an interactive sign-in when none are present. Plan for that before wiring the command into a script or CI job where nobody can type a response.
The usual pattern is map first, scrape second: locate the right page with map --search, then pull its content. Run firecrawl map --help for the full option list, including sitemap handling and subdomains.
What it helps with
- locate the exact URL of a page on a large site
- list every address on a domain
- filter pages by a keyword
- save a site map to a file for later use
- pick pages to scrape or crawl next
Example prompts for the agent
- Find the authentication page on
https://docs.example.comand save the list to.firecrawl/filtered.txt - Map all URLs on the site, limit 500, output as JSON
- Map the site and show me which pages to download next
How to install firecrawl-map
1Skills CLI (Vercel)
npx skills add firecrawl/cli --skill firecrawl-map -a claude-code2Manually: put the files in place
~/.claude/skills/firecrawl-map/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/firecrawl-map/
1Skills CLI (Vercel)
npx skills add firecrawl/cli --skill firecrawl-map -a codex2Manually: put the files in place
.agents/skills/firecrawl-map/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add firecrawl/cli --skill firecrawl-map -a cursor2Manually: put the files in place
.cursor/skills/firecrawl-map/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install firecrawl/cli firecrawl-map2Manually: put the files in place
.github/skills/firecrawl-map/SKILL.md1Skills CLI (Vercel)
npx skills add firecrawl/cli --skill firecrawl-map -a gemini-cli2Platform CLI
gemini skills install https://github.com/firecrawl/cli --path skills/firecrawl-mapManually: put the files in place
.devin/skills/firecrawl-map/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add firecrawl/cli --skill firecrawl-map -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about firecrawl-map
How do I install firecrawl-map in Claude Code?
Run npx skills add firecrawl/cli --skill firecrawl-map -a claude-code. The skill lands in ~/.claude/skills/firecrawl-map/SKILL.md.
What does firecrawl-map do?
It collects a site's URLs and can narrow them down by a search term. That helps when you know the domain but not the page path.
Does firecrawl map need an API key?
Yes, the command requires authentication. With no credentials, the CLI prompts for an interactive login.
