Skip to content
SkillModel-led1,944 tokens in use

seo-firecrawl

Crawl and map whole sites, scrape JavaScript pages and search inside a site with Firecrawl from Claude Code, then hand the pages to the audit agents.

31,134 stars on the repository MIT LicenseAgriciDaniel/claude-seo · extensions/firecrawl/skills/seo-firecrawl
/plugin marketplace add AgriciDaniel/claude-seo /plugin install claude-seo@agricidaniel-claude-seo
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing seo-firecrawl costs

61tokens idle
1,944tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

shelldetected

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Excellent
  • Frontmatter15/15
  • Structure17/25
  • Examples15/15
  • Output15/15
  • Size15/15
  • Resources10/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent
  • Runs shell commands−5

    does this on the machine, and the frontmatter does not say so

    SKILL.md, line 22

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Excellent
  • Development activity96
  • Maintenance100
  • Community72
  • Maturity32
  • Momentum40

seo-firecrawl is the Firecrawl extension of Claude SEO. It offers four commands (crawl, map, scrape and search) backed by the Firecrawl MCP server, which renders JavaScript and handles sites that block simple fetches.

It explains which tool to use when: map for a fast URL list, crawl for content at scale, scrape for one JavaScript-rendered page, and the local fetch script for static pages with no API cost.

What You Get

  • Full-site crawl with include and exclude path patterns
  • Fast site mapping with a URL pattern breakdown
  • Single-page scrape with JavaScript rendering, markdown and screenshots
  • Site-scoped search for content gaps and internal link ideas
  • A guide for combining crawl data with the technical, sitemap, content and schema checks
  • An error table for credit, rate-limit and timeout problems

Common Use Cases

  • Find orphan pages by comparing a site map with the XML sitemap
  • Detect broken links and redirect chains across a section
  • Extract titles, descriptions and H1s for a content inventory
  • Audit single-page apps built with React or Vue

What Makes It Unique

It is written for audits: each command lists SEO patterns, credit costs and the cross-skill steps that follow, such as sitemap coverage and thin-content detection. It also tells the model when the free local fetch script is the better choice.

Under The Hood

The skill is one instruction file with no scripts. It first checks that a Firecrawl tool is available and otherwise points to the extension installer, which configures the Firecrawl MCP server with your API key. All crawling happens on Firecrawl’s service, which receives the URLs you give it and uses your credits. Fetched content is treated as untrusted data.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers