Skip to content
SkillModel-led2,820 tokens in use

seo-audit

Run a full-site SEO audit that crawls up to 500 pages, hands work to specialist agents and returns a scored report with a prioritized action plan.

31,135 stars on the repository MIT LicenseAgriciDaniel/claude-seo · skills/seo-audit
/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-audit costs

42tokens idle
2,820tokens 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

shelldetectedwrites filesdetected

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
  • Frontmatter11/15
  • Structure25/25
  • Examples9/15
  • 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 187
  • Writes files−8

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

    SKILL.md, line 187

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-audit is the site-wide entry point of the claude-seo plugin. It renders the homepage, detects the business type, crawls internal links and delegates to up to seventeen specialist agents for technical SEO, content, schema, sitemap, performance, visual checks, AI search, agent readiness, local, maps, Google data, analytics, backlinks, clustering, search experience, drift and e-commerce.

The results are aggregated into a 0 to 100 SEO Health Score with weighted categories and written to a folder of Markdown and JSON files, with an optional PDF report.

What You Get

  • FULL-AUDIT-REPORT.md with findings per category
  • ACTION-PLAN.md sorted Critical, High, Medium, Low
  • audit-data.json envelope and per-category findings files
  • Desktop and mobile screenshots when Playwright is available
  • An optional A4 PDF report with charts and an implementation roadmap

Common Use Cases

  • Audit a client site before a proposal
  • Run a pre-launch check on a new site
  • Re-audit after a migration and compare against the action plan
  • Combine Search Console, Matomo and backlink data into one report

What Makes It Unique

It orchestrates the rest of the plugin: each category is owned by a specialist skill, optional data sources join only when credentials are detected, and every subagent writes partial findings early so a budget limit does not lose work. It also lists confirmed Google updates before attributing any traffic change.

Under The Hood

The skill is an orchestration recipe. It runs shell commands that start Python scripts through the claude-seo launcher to render pages with a headless browser, check which credentials exist and generate the PDF, and it crawls the target site over the network with a limit of five concurrent requests and a one second delay. It writes the audit folder of reports, JSON and screenshots to disk. A Shopify path swaps in a signed crawl. Fetched pages and API responses are treated as untrusted data, and the skill tells the agent never to change browser sandbox settings itself. The frontmatter does not declare the shell or file access.

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