Skip to content
Firecrawl Build: Scrape

Firecrawl Build: Scrape Skill

by Firecrawl firecrawl/skills

Integrate Firecrawl's /scrape endpoint into product code — turn a known URL into markdown, HTML, links, metadata or screenshots, with sensible defaults baked in.

GitHub Docs
Development
Added to Onei
v0.1.0
ISC

Install

Install with the skills CLI

One command for Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf and dozens of other agents. Needs Node.js; the skill is fetched straight from firecrawl/skills.

$ npx skills add firecrawl/skills --skill firecrawl-build-scrape

Run it in a terminal. The CLI finds the agents installed on your machine, asks which ones to add the skill to, and whether to install it into the folder you ran it from or for all your projects.

Other ways to install

  1. Open the skill on GitHub and download the folder that holds its SKILL.md.
  2. Put it at ~/.claude/skills/firecrawl-build-scrape/, where Claude Code picks it up in every project.

No scripts or references next to it? Saving the SKILL.md alone as ~/.claude/skills/firecrawl-build-scrape/SKILL.md works too.

Using another agent? Its personal skills folder
Codex
~/.agents/skills/
Cursor
~/.cursor/skills/
GitHub Copilot
~/.copilot/skills/
Gemini CLI
~/.gemini/skills/
Windsurf
~/.codeium/windsurf/skills/
OpenCode
~/.config/opencode/skills/
Open folder on GitHub

About

  • Guides /scrape integration for single-page extraction
  • Recommends markdown and onlyMainContent as defaults
  • Escalation rules to /search and /interact when scrape is the wrong tool
  • Covers ingestion, enrichment, changelog and pricing extraction patterns
  • Supports hosted Firecrawl or a self-hosted deployment

Firecrawl's build skills are for the case where you are shipping a feature that calls Firecrawl, not for an agent browsing the web on its own behalf. This one covers /scrape: the page-level primitive you reach for when the application already has a URL and needs its content.

What the skill actually contributes is judgement about defaults, which is where most first integrations go wrong. Return markdown unless the feature genuinely needs another format. Turn on onlyMainContent for article-shaped pages so navigation and footer chrome do not pollute the extraction. Add rendering waits only when a page demonstrably needs them, rather than as a reflex that slows every request.

It also encodes escalation rules, so an agent picks the right endpoint instead of forcing /scrape to do everything: if you do not have the URL yet, start from firecrawl-build-search; if getting the content requires clicking, typing or multi-step navigation, move up to firecrawl-build-interact. That routing is the difference between a working integration and a scraper that silently returns an empty shell for every JavaScript-heavy page.

Common patterns it targets are knowledge ingestion from known URLs, company and product page enrichment, pricing and changelog extraction, and page-level monitoring. Requires a Firecrawl account and FIRECRAWL_API_KEY; FIRECRAWL_API_URL points it at a self-hosted deployment instead. ISC-licensed, published by Firecrawl.

Try it

Once installed, ask your agent something like:

Add a Firecrawl-backed endpoint that takes a docs URL and stores its main content as markdown.

SKILL.md

The instructions your agent loads, as published by Firecrawl.

SKILL.md
name
firecrawl-build-scrape
description
Integrate Firecrawl `/scrape` into product code for single-page extraction. Use when an app already has a URL and needs markdown, HTML, links, screenshots, metadata, or structured page output. Prefer this skill over broader crawl patterns when the feature is page-level.
license
ISC
metadata
author: firecrawl version: "0.1.0" homepage: https://www.firecrawl.dev source: https://github.com/firecrawl/skills
inputs
- name: FIRECRAWL_API_KEY description: Firecrawl API key for hosted Firecrawl requests. required: true - name: FIRECRAWL_API_URL description: Optional base URL for self-hosted Firecrawl deployments. required: false

Firecrawl Build Scrape

Use this when the application already has the URL and needs content from one page.

Use This When
  • the feature starts from a known URL
  • you need page content for retrieval, summarization, enrichment, or monitoring
  • you want the default extraction primitive before considering /interact
Default Recommendations
  • Return markdown unless the feature truly needs another format.
  • Use onlyMainContent for article-like pages where nav and chrome add noise.
  • Add waits or other rendering options only when the page needs them.
Common Product Patterns
  • knowledge ingestion from known URLs
  • enrichment from a company, product, or docs page
  • pricing, changelog, and documentation extraction
  • page-level quality checks or monitoring
Escalation Rules
  • If you do not have the URL yet, start with [firecrawl-build-search](../firecrawl-build-search/SKILL.md).
  • If content requires clicks, typing, or multi-step navigation, escalate to [firecrawl-build-interact](../firecrawl-build-interact/SKILL.md).
Implementation Notes
  • Keep the integration narrow: one feature, one URL, one extraction contract.
  • Treat /scrape as the default primitive for downstream LLM or indexing pipelines.
  • Request richer formats only when the consumer needs them, such as links, screenshots, or branding data.
Docs (Source of Truth)

Read the source-of-truth page for your project language before writing integration code:

See Also
  • [firecrawl-build](../firecrawl-build/SKILL.md)
  • [firecrawl-build-search](../firecrawl-build-search/SKILL.md)
  • [firecrawl-build-interact](../firecrawl-build-interact/SKILL.md)
Install

Related Skills

See all Firecrawl Build: Scrape alternatives

Skill: MCP Builder

by Anthropic

Anthropic's guide for building high-quality MCP servers end to end — research, tool design, implementation in TypeScript or Python, testing, and a 10-question evaluation suite.

Development

Skill: geo-sleuth

by Oldcircle

Featured

Find where a photo was taken: EXIF, OCR, OpenStreetMap, skyline and satellite matching, with coordinates, error radius and evidence images.

Development
1259 views 440 copies
Browse all skills →