Skills firecrawl-scrape
📦

firecrawl-scrape

Content revision r1 Safe ⚙️ External commands🌐 Network access📁 Filesystem access

Scrape Web Pages Into Clean Markdown

Web pages can be hard to extract cleanly when scripts render important content. This skill uses Firecrawl to scrape URLs into LLM-ready markdown and optional formats.

Supports: Claude Codex Code(CC)
🥉 77 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "firecrawl-scrape" from https://skillstore.io/skills/firecrawl-firecrawl-scrape.md and its manifest at https://skillstore.io/api/skills/firecrawl-firecrawl-scrape/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/firecrawl-firecrawl-scrape.md Signed manifest GET /api/skills/firecrawl-firecrawl-scrape/manifest Signed lockfile GET /api/skills/firecrawl-firecrawl-scrape/lockfile

Test it

Using "firecrawl-scrape". Scrape a product page and summarize it.

Expected outcome:

  • Saved clean markdown for the page.
  • Returned the page title, key sections, and important links.
  • Provided a short summary of pricing and feature details.

Using "firecrawl-scrape". Compare documentation and blog pages from one site.

Expected outcome:

  • Scraped both URLs concurrently.
  • Separated shared topics from page-specific details.
  • Flagged links that may need deeper review.

Using "firecrawl-scrape". Ask a focused question about a pricing page.

Expected outcome:

  • Used query mode for the requested page.
  • Answered only from the scraped page content.
  • Noted when the page did not include the requested detail.

Security Audit

Safe
v4 • 7/5/2026 Open versioned report

All static findings are documentation artifacts in SKILL.md, including command examples, inline option names, example.com URLs, and sibling markdown links. No prompt injection, data exfiltration intent, or executable code was found in the reviewed file.

1
Files scanned
69
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (16)
SKILL.md:22-40 SKILL.md:40-46 SKILL.md:46-47 SKILL.md:47-48 SKILL.md:48-49 SKILL.md:49-50 SKILL.md:50-51 SKILL.md:51-52 SKILL.md:52-53 SKILL.md:53-57 SKILL.md:57 SKILL.md:58-59 SKILL.md:59-60 SKILL.md:60-61 SKILL.md:61 SKILL.md:62-67
🌐 Network access (2)
SKILL.md:33 SKILL.md:39
📁 Filesystem access (3)
SKILL.md:66 SKILL.md:67 SKILL.md:68
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/firecrawl-firecrawl-scrape/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/firecrawl-firecrawl-scrape/security.svg)](https://skillstore.io/skills/firecrawl-firecrawl-scrape?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/firecrawl-firecrawl-scrape?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/firecrawl-firecrawl-scrape/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/firecrawl-firecrawl-scrape.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

firecrawl. (2026). firecrawl-scrape security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/firecrawl-firecrawl-scrape/audits/4

BibTeX citation

@techreport{firecrawl-firecrawl-firecrawl-scrape-2026, author = {firecrawl}, title = {firecrawl-scrape security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/firecrawl-firecrawl-scrape/audits/4}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "firecrawl-scrape security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "firecrawl" date-released: "2026-07-05" url: "https://skillstore.io/skills/firecrawl-firecrawl-scrape/audits/4" identifiers: - type: other value: "skillstore:firecrawl-firecrawl-scrape:audit:4" description: "Skillstore immutable audit report identifier"

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
85
Content
68
Community
83
Spec Compliance

What You Can Build

Research Source Capture

Researchers can scrape source pages into markdown before summarizing or extracting claims.

Product Page Review

Product teams can collect pricing, feature, or FAQ content from specific pages.

Developer Documentation Intake

Developers can pull clean docs content from a URL before analysis or migration.

Try These Prompts

Scrape One Page 
Scrape https://example.com/docs into clean markdown and save the result under .firecrawl.
Capture Main Content 
Scrape https://example.com/blog with main content only, then summarize the page sections.
Extract Multiple Pages 
Scrape these three URLs concurrently and compare their main topics: https://example.com, https://example.com/blog, https://example.com/docs.
Ask A Targeted Question 
Scrape https://example.com/pricing and answer this question from the page: What is included in the enterprise plan?

Best Practices

  • Quote URLs before running scrape commands.
  • Save full markdown first when you need detailed analysis.
  • Use query mode only for narrow questions because it uses extra credits.

Avoid

  • Do not scrape pages without permission or a valid reason.
  • Do not use query mode when full page review is required.
  • Do not store sensitive page captures in shared folders.

Frequently Asked Questions

Does this skill need Firecrawl installed?
Yes. It needs the Firecrawl CLI or npx command available to the agent.
Can it handle JavaScript-rendered pages?
Yes. It can wait before scraping so rendered content has time to load.
Can it scrape multiple URLs?
Yes. It can scrape several URLs concurrently when Firecrawl allows the requested concurrency.
What output formats are supported?
It can request markdown, links, screenshots, HTML, raw HTML, and JSON.
Is WebFetch required?
No. The skill uses Firecrawl commands for page extraction.
Should I use query mode for every page?
No. Use query mode for focused questions because it costs extra Firecrawl credits.

Developer Details

Author

firecrawl

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/firecrawl/cli/tree/main/skills/firecrawl-scrape/

Ref

30c73eac2afe762f6aa9c4553158769369d47351

Maintenance freshness

7/18/2026

Usage

8 downloads · 81 views

File structure

📄 SKILL.md

More from firecrawl

View all

Related Skills

View all