mcpbeat Sign in

SEO Audit Skill for Claude

Audit a website for SEO problems and prioritize a practical fix plan. Use for whole-site audits or a broad request to improve a site.

824 tokens
context cost
SKILL.md, read when the skill is used
2
files
plus reference files
0
copies elsewhere
how many repositories repackaged it
834
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/AgriciDaniel/chatgpt-seo --skill seo-audit

What comes with it

194 bytes besides the instruction
agents/openai.yaml

The instruction itself

7 sections, as written by the author

Website SEO audit

Input

A site URL or a supplied crawl. Use any stated business goal, market and page inventory.

Evidence and runtime

If a skill-resource reader fails to open a linked supporting file, try the

available file or execution tool using the installed plugin root returned by

the host or resolved from this skill's location. Do not hardcode a home folder,

version, or working directory. Distinguish a failed reader call from an absent

file, and files actually attempted from files not attempted. Report a resource

as unavailable only after the supported access paths have failed. If no file

or execution access is available, continue within the evidence you can read

and state that limit.

Read the operating contract when this

workflow is selected. Use runtime and data paths

when choosing a tool or handling missing data. Recheck relevant

search facts and primary sources

before date-sensitive claims. For a quantitative diagnostic, read

scoring; unavailable categories stay unknown.

Supporting resources

Read only the resources needed for the selected part of this task:

  • technical coverage.
  • editorial checks.
  • markup decisions.

Workflow

  • Start with the homepage and detect the page families that support the business: products, services, locations, articles, documentation or landing pages.
  • Discover a bounded representative sample using available links, sitemap entries or a supplied crawl. Record discovery method, visited URLs and failed requests. A suggested first pass is the homepage and one or two pages from each material family; state the sampling limit.
  • Inspect technical controls, intent and content quality, metadata and internal links, structured data, performance evidence, image purpose and AI-search accessibility. Use narrow bundled skills only for the relevant depth.
  • Identify repeated template defects separately from individual-page issues. Confirm an apparent indexing blocker is unintended before escalating it.
  • Synthesize findings into a dependency sequence: verified blockers first, then important templates/pages, then measurable content and search-experience improvements.
  • Read the scoring reference if a score is useful. With unavailable field/lab performance or other category evidence, withhold the overall score and show coverage.

Deliverable

A report using ../../assets/audit-template.md, an evidence ledger, and a fix backlog with owner role, dependency, effort assumption and success check. Produce files when the host supports them.

Boundary

Do not claim a complete crawl, actual index status, measured CWV or traffic growth without the corresponding evidence.

Adapted from the public Claude SEO seo-audit workflow.

How to use it

Copy the folder

Take agricidaniel/seo-audit from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.