mcpbeat Sign in

SEO Page Skill for Claude

Inspect and improve one page for search intent, metadata, content, links and markup. Use for page-level SEO reviews.

799 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-page

What comes with it

208 bytes besides the instruction
agents/openai.yaml

The instruction itself

7 sections, as written by the author

Single-page SEO review

Input

A page URL, supplied HTML or a draft, plus a target query if known.

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:

  • page usefulness.
  • reader decision fit.
  • page controls.
  • schema decisions and the fact-agreement helper when JSON-LD is present.

Workflow

  • Classify the page purpose and the user task. Open the page when possible; distinguish source, rendered view and a supplied draft.
  • Check title/description usefulness, heading hierarchy, canonical and robots observations, internal link destinations, and the page's ability to satisfy its intended task.
  • Review first-hand detail, factual support, author or organization accountability, content freshness and missing decision information. Treat length and density as editorial diagnostics.
  • Inspect image purpose and JSON-LD agreement with visible facts. If Python is available, use ../../scripts/analyze_html.py on a supplied snapshot for repeatable tag evidence.
  • Separate confirmed defects from rendering or performance hypotheses. Give rewritten title/description options only from known page facts.
  • Where edits are requested, provide a scoped draft or patch, then a validation checklist tailored to the affected page.

Deliverable

A page diagnosis with evidence, ordered changes, suitable metadata drafts and any requested code. Include limitations and avoid an unsupported overall score.

Boundary

Exactly one H1 and character-count previews are clarity conventions, not evidence of penalties. Missing source content needs rendered evidence.

Adapted from the public Claude SEO seo-page workflow.

How to use it

Copy the folder

Take agricidaniel/seo-page 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.