docs2skill by Spicrawl
Star on GitHub

Turn any docs site into an agent skill.

Paste a docs URL. Get files Claude Code, Codex and Cursor can use.

The demo reads up to 5 pages; the CLI does the whole site.

$ npx skills add OfficialSpicrawl/docs2skill

Then run npm install in the installed folder.

Generated files

docs.spicrawl.com · 8 pages

---name: spicrawl-docsdescription: "Use when working with Spicrawl: Spicrawl is a web data API for agents: fetch, render and extract any URL as markdown, HTML or structured JSON with one request."---↑ always loaded# SpicrawlSpicrawl is a web data API for agents: fetch, render and extract any URL as markdown, HTML or structured JSON with one request.## Reference### Pages- [Spicrawl](references/index.md): Spicrawl is a web data API for agents: fetch, render and extract any URL as markdown, HTML or structured JSON with on...↑ on demand- [Authentication](references/authentication.md): Authenticate Spicrawl API calls with a Bearer API key, choose live or test keys, and grant the scopes each route needs.- [Credits](references/credits.md): What each Spicrawl request costs by rendering tier, what is free, and how to cap spend with max\_cost and batch budgets.- [Errors](references/errors.md): Every Spicrawl error code with its HTTP status, whether to retry, what it means and which parameter to change.- [Quickstart](references/quickstart.md): Get a Spicrawl API key, scrape your first page as markdown with curl, Python, TypeScript or the CLI, and read the res...- [Rate limits](references/rate-limits.md): How Spicrawl limits request rate, concurrency, live sessions and monthly credits, the headers that report each limit,...- [Response headers](references/response-headers.md): Every header Spicrawl returns on /v1/scrape: request id, credits, rendering tier, target status, proxy, cache state,...### Agents- [AI app builders](references/agents-app-builders.md): Connect Spicrawl's hosted MCP server to Replit Agent, v0, Lovable and Bolt so the builder can read web pages, and cal...## How to useOpen only the reference files you need for the task, not all of them. Each file is one page as markdown, with its source URL on the second line.

How it works

  1. Find

    sitemap or links

  2. Read

    pages as markdown

  3. Write

    files, no model

Run it yourself

$ git clone https:/​/​github.com/​OfficialSpicrawl/​docs2skill && cd docs2skill && npm install
$ export SPICRAWL_API_KEY=spicrawl_live_...
$ node llms-txt.mjs https:/​/​docs.spicrawl.com --max 8 --skill spicrawl-docs
Discovering pages on https://docs.spicrawl.com/ ...
Fetching 8 pages, about 8 credits (1 per page).
  8/8 pages done
Wrote out/llms.txt and out/llms-full.txt
8 pages; skipped 0 failed, 0 blocked (HTTP 4xx/5xx), 0 empty.
Wrote skill out/spicrawl-docs/ (SKILL.md + 8 reference files) and out/AGENTS.md
✓

Give your agent the docs.

Free key. 1,000 credits a month.