mcpbeat Sign in

SEO Cluster Skill for Claude

Group keywords into useful page targets and an internal-link architecture using intent and available SERP overlap. Use for topic clusters.

746 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-cluster

What comes with it

193 bytes besides the instruction
agents/openai.yaml

The instruction itself

7 sections, as written by the author

Topic clustering

Input

A seed/topic or keyword inventory, with optional measured SERP results and locale.

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:

  • intent, page differentiation and overlap sensitivity.

Workflow

  • Normalize exact duplicates without erasing distinct intent. Keep measured volume/difficulty separate from generated keyword candidates.
  • Read clustering. With measured SERP URLs, compute or explain overlap for a stated locale, date and top-N sample. Without SERPs label the grouping semantic and provisional.
  • Split mismatched intents/page types even when keywords share words. Avoid one page per minor variant and avoid merging distinct customer tasks.
  • Check transitive bridge clusters against a representative page/medoid so an A-B and B-C overlap does not automatically justify A-C consolidation.
  • Map clusters to existing suitable URLs, new page candidates and hub/spoke links. Preserve useful pages; a merge proposal needs content and redirect evidence.
  • Prioritize from business relevance and measured data, or clearly stated assumptions. Produce a map/table when it helps review the architecture.

Deliverable

A cluster-to-URL table with intent, evidence type, representative keyword, known metrics, link plan and review flags.

Boundary

Do not claim live SERP overlap or search demand when using semantic grouping alone. Clustering does not authorize content publication or redirects.

Adapted from the public Claude SEO seo-cluster workflow.

How to use it

Copy the folder

Take agricidaniel/seo-cluster 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.