mcpField
S
seo-cluster

seo-cluster

github.com/agricidanielMarketing & growth89474 installsUpdated 2w ago
Repository

About seo-cluster

seo-cluster is a ChatGPT skill for grouping keywords into topic and intent clusters and mapping them to site pages. It distinguishes measured SERP evidence from provisional semantic grouping and produces a cluster-to-URL plan without authorizing publication or redirects.

Key features

  1. 01Normalizes duplicates while preserving intent
  2. 02Groups keywords using SERP evidence or semantics
  3. 03Separates differing intents and page types
  4. 04Checks overlap across connected clusters
  5. 05Maps clusters to existing and candidate URLs
  6. 06Suggests hub-and-spoke links

Use cases

  1. 01Organize a keyword inventory into topic groups
  2. 02Map clusters to current and planned pages
  3. 03Review possible page overlap before consolidation
  4. 04Prioritize content architecture using available data

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/agricidaniel/chatgpt-seo --skill seo-cluster

After installing, type/seo-clusterin Claude Code to confirm it loaded.

Details

From the project README

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:

Workflow

  1. Normalize exact duplicates without erasing distinct intent. Keep measured volume/difficulty separate from generated keyword candidates.
  2. 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.
  3. Split mismatched intents/page types even when keywords share words. Avoid one page per minor variant and avoid merging distinct customer tasks.
  4. Check transitive bridge clusters against a representative page/medoid so an A-B and B-C overlap does not automatically justify A-C consolidation.
  5. Map clusters to existing suitable URLs, new page candidates and hub/spoke links. Preserve useful pages; a merge proposal needs content and redirect evidence.
  6. 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.

Comments

Markdown supported