mcpbeat Sign in

SEO Technical Skill for Claude

Diagnose crawlability, indexing controls, canonicals, rendering, redirects and performance evidence. Use for technical SEO issues.

786 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-technical

What comes with it

186 bytes besides the instruction
agents/openai.yaml

The instruction itself

7 sections, as written by the author

Technical SEO

Input

A site/page URL, crawl export, source snapshot, response headers, or deployment comparison.

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 and performance evidence.
  • supplied crawl inputs.
  • field and lab CWV report template.

Workflow

  • Check crawl access and index controls separately. Review robots groups, meta directives and supplied X-Robots-Tag headers without assuming the page should be public.
  • Trace canonical intent, duplicate/parameter URLs, redirects, pagination and sitemap alignment from evidence. Do not canonicalize distinct useful paginated or filtered pages indiscriminately.
  • Compare initial HTML with a rendered observation when available. Identify missing primary content, crawlable links and mobile/desktop parity risks.
  • Use actual response data for status, TLS and redirects. A generic browser error cannot establish a specific HTTP code or WAF cause.
  • Assess LCP, INP and CLS using named field or lab data and the current-search-facts reference. HTML-only performance concerns are hypotheses.
  • Give the smallest fix that addresses the observed defect and the exact post-change check. Review the impact of any robots, noindex or canonical change before applying it.

Deliverable

A technical findings table, affected templates/URLs, a dependency-ordered patch plan, and verification commands or browser checks supported by the host.

Boundary

Do not require headless Chromium, invent crawler fetch limits, recommend IndexNow for Google, or submit URLs without explicit authorization.

Adapted from the public Claude SEO seo-technical workflow.

How to use it

Copy the folder

Take agricidaniel/seo-technical 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.