Skip to content
cccskills
FreePublished on GitHubEnglish overview

firecrawl-build-scrape

Integrate single-page extraction into an application using Firecrawl scrape. Retrieve Markdown, HTML, links, screenshots, metadata, or structured data from a known URL, and configure how recently cached content may be reused.

OriginalShow the original 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.

firecrawl/firecrawl
AI rating70/ 100See how to install

Good for

  • Preparing known web pages for summarization
  • Enriching records from company or product pages
  • Extracting pricing, changelogs, or documentation
  • Implementing page checks and monitoring

Overview

What it does

This skill helps you integrate Firecrawl’s /scrape into an application to retrieve information from a single, known URL. Choose Markdown, HTML, links, screenshots, metadata, or structured output to suit the feature. For articles, it helps you consider onlyMainContent to focus extraction on the main text. Rendering waits and similar options are added when needed.

When it helps

Use it to import a page for summarization when you already know its URL, or to enrich company and product information. It also suits extracting pricing pages, changelogs, and documentation, as well as implementing quality checks and monitoring for individual pages.

Example requests

  • “Add a workflow that retrieves the article text from a specified URL as Markdown.”
  • “Retrieve a pricing page and make its cache state and retrieval time available for checking.”

Notes

Hosted Firecrawl requires FIRECRAWL_API_KEY. Use maxAge to limit the age of reused data; set it to 0 to skip index reuse. Check metadata.cacheState and metadata.cachedAt to see the actual state. A successful retrieval alone does not establish whether a service described on the page is still active. Consider /interact if the page requires clicks or typing.

This overview was written by AI (OpenAI Codex) from the public SKILL.md. Check the original below for the exact behavior.

Objective evaluation

AI rated this skill on four points using only the contents of its SKILL.md. Stars and popularity are not taken into account.

Clear instructionsIs it clear when to use it and what it does?
AGoodIt explicitly identifies single-page retrieval from a known URL and lists the available output formats.
Concrete stepsAre steps, inputs, outputs, and examples spelled out?
BPartly lackingIt specifies `maxAge: 0` and metadata fields to inspect, but provides no implementation procedure.
SafetyAre sending data, deleting files, and running commands disclosed?
BPartly lackingIt involves external `/scrape` requests, but provides no procedure for reviewing the URLs sent.
Easy setupDoes it need few tools or API keys, and are they documented?
BPartly lackingIt names `FIRECRAWL_API_KEY` and an optional deployment URL, but provides no setup procedure.

The total counts each point as A = 25, B = 15, C = 5. Rated by AI (OpenAI Codex) as of Oct 20, 2026. Treat it as a guide and read the original before installing.

Disagree? Request a re-evaluation

Tell us which point is wrong and why. No login needed. We will check it against the SKILL.md, redo the evaluation, and show the result here.

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

Files included (2)

  • SKILL.md3.7 KB
  • references/freshness-and-liveness.md2.3 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

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.

Freshness and Liveness

  • Firecrawl reuses recently indexed content, which is what makes repeat reads of the same URL fast. Set maxAge (milliseconds) to bound how old a reused copy may be, or maxAge: 0 to skip index reuse for a freshness-critical read.
  • Read metadata.cacheState and metadata.cachedAt to see what you actually got.
  • A successful scrape reports what the page returned. Whether the thing the page describes is still active is a source-specific judgment your code makes.
  • See references/freshness-and-liveness.md for the tradeoff, the metadata, and the decision rule.

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

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

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

firecrawl-build

FreeSummaryAI rating 80

Build web search, page content retrieval, structured data extraction, and browser interactions into applications with Firecrawl. The skill guides endpoint selection, credentials, SDK or REST integration, and verification with a real request.

  • Adding web search to an application
  • Extracting structured data from known URLs
  • Building website clicks and form filling into a workflow
firecrawl/firecrawl193.2KUpdated Oct 20, 2026

firecrawl-build-interact

FreeSummaryAI rating 70

Integrate Firecrawl browser actions into application code to retrieve content that requires clicks, form entry, or pagination. Use it for multi-step page interactions and workflows that need to preserve the browser session after scraping.

  • Retrieving content revealed by clicks
  • Working with search forms and filters
  • Collecting results across multiple pages
firecrawl/firecrawl193.2KUpdated Oct 20, 2026

firecrawl-build-onboarding

FreeSummaryAI rating 100

Set up Firecrawl in an application, from browser authentication and API key configuration to choosing an SDK, a library for calling the service. Add the first request and verify that the integration works.

  • Adding Firecrawl to a new application
  • Saving an API key in project configuration
  • Choosing an SDK for the project language
firecrawl/firecrawl193.2KUpdated Oct 20, 2026

firecrawl-build-search

FreeSummaryAI rating 70

Build web discovery into applications and agent workflows with Firecrawl search. Turn a query into candidate URLs, select useful sources, and decide whether to retrieve page content for further extraction or answers with cited sources.

  • Finding web sources for answers with citations
  • Discovering companies, competitors, or topics
  • Creating a shortlist of pages for deeper research
firecrawl/firecrawl193.2KUpdated Oct 20, 2026

See all skills by firecrawl

Report a problem with this skill