firecrawl-seo-audit Skill for Claude: What It Does and How to Install It

Makes your agent audit a site's on-page and technical SEO from its real page source and return prioritized fixes with evidence.

Installs: 32.2K; on skills.sh
Stars: 214; on GitHub
Updated: Nov 2026; last repo commit

This skill makes your agent inspect a website's titles, meta descriptions, headings, canonicals, robots directives, structured data and internal links. It fetches the raw page source with Firecrawl and checks the head markup before it says anything is missing.

It returns findings with affected URLs, evidence, impact, a fix and a way to verify it, and it says what it could not measure. It needs a Firecrawl API key and the Firecrawl CLI, and it is told not to edit your site.

Good for

SEO specialists auditing page source and templates
Developers checking metadata, canonicals and structured data
Marketers comparing pages against target keywords

Install firecrawl-seo-audit

Claude Code

Copy this prompt.

Install the firecrawl-seo-audit skill in Claude Code. Run this command:

/plugin marketplace add firecrawl/firecrawl-workflows
/plugin install firecrawl-workflows@firecrawl-workflows

Then check that it loaded and tell me how to use it.

2
Paste it into Claude Code. It shows the change and asks before running it.

Pick one route. The plugin routes install the whole firecrawl-workflows plugin: 16 skills (counted from the skills list in its plugin.json), and the repo tree has no hooks, agents or MCP config files. The skills-only routes install just firecrawl-seo-audit. The skill drives the Firecrawl CLI and needs a Firecrawl API key. Install the Firecrawl CLI first, since the skill runs firecrawl commands: npm install -g firecrawl-cli (Firecrawl CLI docs), or npx -y firecrawl-cli@latest init -y --browser to install it, sign in and add the shared skills in one step. Then run firecrawl login or export FIRECRAWL_API_KEY. Who pays: the Firecrawl account that owns the key. Every call uses credits; a new account starts on the free plan with 1,000 credits a month and no card. Per Firecrawl's billing docs: map 1 credit per call; scrape 1 credit per page; search 2 credits per 10 results; Alexandria data tools cost the price listed on each tool, while discovery is free.

Built from the package data we hold. Not yet tested by us. Source.

What's in the skill

When it loads

Inspect a website's titles, meta descriptions, headings, canonicals, structured data and internal links for on-page and technical SEO issues. Use for SEO audits, page-source checks, broken-link reviews or comparing pages for target keywords, even without an explicit request to scrape. Return source-backed findings and prioritized fixes. Excludes generic SEO explanations, standalone copywriting and functional website testing.

Key facts

Author: Firecrawl (frontmatter author, and the repo owner)
License: ISC (frontmatter and the README)
Installs on skills.sh: 32,181 (Nov 2, 2026)
GitHub stars: 214 for the whole firecrawl/firecrawl-workflows repo (Nov 2, 2026)
Last repo commit: Nov 1, 2026
What it includes: 1 file: SKILL.md (bundles no scripts)
Needs: A Firecrawl API key (FIRECRAWL_API_KEY) with credits, and the Firecrawl CLI (npm install -g firecrawl-cli)
Part of: The firecrawl-workflows plugin: 16 skills in its Claude plugin.json (counted), 19 skill folders in the repo tree
Works in: AI coding agents, per the README. The repo also ships plugin manifests for Claude Code, Codex and Cursor

What it includes

Uses your URLs, or firecrawl map to discover pages for a wider audit
Records the inspected scope, since a sample does not prove full-site coverage.
Network · Scope the pages
Scrapes markdown, rawHtml and links with --max-age 0
Omits --only-main-content so metadata checks see the full page. If raw HTML or headers are missing, dependent checks are marked unverified.
Runs code · Fetch the page source
Titles, descriptions, headings, alt text, links, canonicals, robots and structured data
Relates each finding to the page's purpose and separates crawl rules from indexing directives.
Read · Run the checks
Runs firecrawl search and inspects the comparison pages
Keeps the query, location and observation date. It does not infer volume, traffic or ranking causes from result order.
Network · Compare keywords
Finds third-party ranking, keyword or backlink data and checks its costs first
Uses find-tools, then list with --include-costs, then runs the chosen capability only when its source, domain and period fit.
Runs code · Alexandria measurements
Findings with URLs, evidence, impact, fix and how to verify
Separates confirmed defects from opportunities and unverified concerns. No overall score and no traffic forecast.
Read · Audit report

From the official docs

Permissions

Medium risk

It can call paid third-party data providers through Firecrawl and accepts nothing on your behalf, per SKILL.md. Tell it not to run provider measurements unless you want them.

What it can do

Read your data
Create and change things
Delete things
Read-only mode

Watch out for

Provider data calls can have a cost
SKILL.md has the agent inspect a provider contract with --include-costs before running it. Firecrawl's docs say a tool run costs the price listed on the tool and discovery is free, so check the cost shown before you approve each provider call. github.com
Third-party data terms need your approval
On THIRD_PARTY_DATA_TERMS_REQUIRED the agent must give you the terms URL, and an organization admin must accept them. SKILL.md says never to accept terms without your explicit approval. github.com
It fetches pages with your API key
Every scrape and search goes through Firecrawl. Point it only at sites you are allowed to audit. github.com
It spends your Firecrawl credits
Every call is billed in credits to the account behind the key. Per Firecrawl's billing docs: map 1 credit per call; scrape 1 credit per page; search 2 credits per 10 results; Alexandria data tools cost the price listed on each tool, while discovery is free. A free account has 1,000 credits a month, so a large run can use it up. docs.firecrawl.dev

Security advisories

No published security advisories as of Nov 2, 2026.

Technical details

Turning on read-only	No read-only mode is documented in SKILL.md. Use version control for files it writes.
Talks to	Firecrawl hosted service. The site you audit and search-result pages it inspects. Third-party Alexandria data providers when ranking, keyword or backlink data is requested
Sign-in and keys	SKILL.md declares FIRECRAWL_API_KEY as a required input and says Alexandria requires authenticated CLI access. It does not say where the credentials are kept.
Scopes	Runs Firecrawl map, scrape and search commands with your API key May run Alexandria find-tools, list and scrape commands for third-party measurements Spends credits on the Firecrawl account that owns your API key

Questions

What does the firecrawl-seo-audit skill do?

It makes your agent audit a website's on-page and technical SEO. It fetches real page source with Firecrawl and returns prioritized, evidence-backed fixes.

How do I install it in Claude Code or Codex?

Use the install box at the top of this page. Each client has a plugin route and skills CLI commands. Install the Firecrawl CLI first (npm install -g firecrawl-cli, per its docs), then run firecrawl login or set FIRECRAWL_API_KEY.

Who pays for it?

You do, through the Firecrawl account that owns your API key. Firecrawl bills in credits, and a new account starts on the free plan with 1,000 credits a month and no card. Per its billing docs: map 1 credit per call; scrape 1 credit per page; search 2 credits per 10 results; Alexandria data tools cost the price listed on each tool, while discovery is free. Check your balance with firecrawl credit-usage.

Will it edit my website?

SKILL.md says not to edit the website as part of the audit and not to broaden it into an unrequested crawl. It reports fixes for you to make.

Does it give a score or traffic forecast?

No. SKILL.md says not to invent an overall score or forecast traffic gains. It also says not to infer search volume, traffic, indexing status or Core Web Vitals from scrape output.

What are the Alexandria tools it mentions?

They are third-party data providers reached through the Firecrawl CLI, used only for ranking, keyword or backlink numbers. SKILL.md says they need authenticated CLI access, and if unavailable the agent reports the unmeasured fields and continues the page audit.

Is it safe to install?

It is a single SKILL.md file and bundles no scripts. When it runs, your agent calls Firecrawl with your API key and may query paid provider data. Read the costs it shows before you approve a provider call, and never let it accept data terms for you.

Information

updated Nov 2, 2026

Repository: firecrawl/firecrawl-workflows
Folder: skills/firecrawl-seo-audit

firecrawl/firecrawl-workflows skills.sh

Sources

Docs, issue trackers and discussions this page is built from.

Show all 8

firecrawl-seo-audit SKILL.md · github.com
firecrawl-workflows README · github.com
firecrawl-workflows plugin.json · github.com
firecrawl-workflows marketplace.json · github.com
firecrawl-workflows Codex plugin.json · github.com
Firecrawl CLI docs · docs.firecrawl.dev
Firecrawl billing and credits · docs.firecrawl.dev
firecrawl/cli README · github.com