keyword-clustering
Skill2 starsChanged 53 days agoMITView on GitHub
Cluster keywords by intent and map each cluster to an existing or proposed page, including cannibalization checks. Use when the user has a keyword list, saved keywords, Search Console queries or a domain to map to pages.
- Reads credentials
16 other projects use a version of this, 12 of them edited.
Adopted by
Most recently taken up by
- teemukarjaluoto/seo-sauna-mcpedited, first seen Nov 16, 2026
- harborrank/harborrank-skillsedited, first seen Nov 16, 2026
- winsley-jeune/harborrank-skillsedited, first seen Nov 15, 2026
- kostja94/marketing-skillstheir own version, first seen Nov 8, 2026
- foverse/seoverseedited, first seen Nov 8, 2026
- akii-technologies-ltd/akii-seo-ai-search-optimizertheir own version, first seen Nov 1, 2026
Used with
Projects with it also use openseo-release-notes, openseo-review-web-content and 3 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
JwuthriSkillopenseo-release-notes
Cut an OpenSEO release — bump the version, draft user-facing release notes from commits since the last tag, run a review + subagent-verification pass, and open a "release: vX.X.X" PR. Use when the user asks to prepare a release, bump the version, or write release notes.
Also in 6 projects that use this
JwuthriSkillopenseo-review-web-content
Write and review content for the OpenSEO website (web/) — blog posts, guides, feature pages, FAQs. Distills the philosophy for on-brand, useful, accurate content. Use whenever adding or editing user-facing prose in web/content or web/src.
Also in 5 projects that use this
ten9876Skillpapercuts
Read-only AetherSDR issue triage that surfaces the UX papercuts, bugs, and regressions you can fix AND prove today with the agent automation bridge. Use when the user says $papercuts or /papercuts, or asks to "find papercuts", "what can I fix and prove today", "triage bridge-provable issues", "what UX bugs can the bridge close", "sort issues by priority I can knock out", or otherwise wants a curated, lifecycle-aware (design→code→prove) shortlist of issues — NOT the label-and-respond /triage workflow. This is the discovery step that feeds /fb. Strictly read-only: it never labels, comments, closes, or edits issues.
Also in 4 projects that use this
- +2 more from Jwuthri
Other versions16 projects use a version of this.
Word for word · 0
None found.
Edited · 12
- every-app/open-seo★ 28k60% same
- Jwuthri/Tracely-ai★ 1.3k47% same
- VladSez/easy-invoice-pdf★ 1.1k47% same
- jwuthri-cloud/Tracely-ai★ 97947% same
- petera2c/simple-table★ 23347% same
- foverse/seoverse★ 460% same
- harborrank/harborrank-skills★ 214% same
- ventra-rocket/EchoSEO★ 247% same
- winsley-jeune/harborrank-skills★ 214% same
- ictlondon/kraftskills★ 047% same
2 more not listed
Wrote their own version · 4
- kostja94/marketing-skills★ 1.1ksame name
- mtarcure/claude-vibe-squad★ 220same name
- akii-technologies-ltd/akii-seo-ai-search-optimizer★ 80same name
- searchfit/searchfit-seo★ 9same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- AGENTS.mdAGENTS.md
- competitive-landscapeSkill
- competitor-analysisSkill
- keyword-researchSkill
- link-prospectingSkill
- local-seoSkill
- seo-auditSkill
- seo-coachSkill
- seo-project-setupSkill
- seo-reportSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 4 are common, 1 is distinctive, and 10 are very specific to this project.
4
Common
Most of the 15 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 14
Use the installed agenticseo command.
- Very specific: line 21
If keywords are not provided, use agenticseo saved list for saved sets, agenticseo research for seed discovery, or agenticseo ranked when …
- Very specific: line 25
Run agenticseo context first and ground the mapping in it: the saved keyPages are the existing pages clusters should map to, and the …
- Very specific: line 27
Before paying, check researchLog.
- Very specific: line 48
When Search Console is connected, start from real queries and the pages already ranking for them: agenticseo gsc performance --dimensions …
- Very specific: line 49
Use agenticseo ranked for domain- or page-driven clustering.
- Very specific: line 50
Use agenticseo local businesses and agenticseo local serp when proximity, local packs or Google Business results decide whether terms …
- Common: line 51
Remove duplicates, irrelevant terms and terms that clearly require a different product or audience.
- Very specific: line 62
Ask before applying cluster tags with agenticseo saved add ...
- Very specific: line 68
If a report template applies (see seo-report), its sections and tone replace this list.
- Common: line 81
Do not over-cluster tiny keyword sets.
- Common: line 82
Do not rely on lexical similarity alone.
- Very specific: line 83
Do not replace tags broadly without explicit confirmation (--replace-tags replaces a keyword's tags).
- Common: line 84
If existing URL data is missing, label target pages as proposed.
- Distinctive: line 85
Search Console positions are averages over the date range, and its clicks are not GA4 sessions.
“Common” is measured: kept by at least 6 in 10 of the 15 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
<!-- Adapted from OpenSEO plugins/openseo/skills/keyword-clustering/SKILL.md (https://github.com/every-app/open-seo, MIT, Copyright (c) 2026 Ben Senescu) for the AgenticSEO CLI. -->Keyword clustering
Goal
Group keywords into page-level clusters and decide which existing or new page should target each cluster. This is a keyword mapping workflow, not just a semantic grouping exercise.
Use the installed agenticseo command. Search Console and saved keywords are free; research lookups are billed by DataForSEO and need DATAFORSEO_API_KEY.
Required inputs
- A keyword list, saved keyword tag, seed topic or target domain
- Optional existing URLs/pages to map against
If keywords are not provided, use agenticseo saved list for saved sets, agenticseo research for seed discovery, or agenticseo ranked when the user starts from a target domain.
Project context
- Run
agenticseo contextfirst and ground the mapping in it: the savedkeyPagesare the existing pages clusters should map to, and the business and goal decide which clusters are worth targeting. If there is no project, set one up asseo-project-setupstep 1 describes. - This skill needs key pages. If none are saved, run a minimal inline setup: ask the user for the pages that matter, or propose a shortlist from the site, an audit (
agenticseo audit pages) or Search Console and confirm it, write it tokeyPagesin.agenticseo/context.json({ "url", "role"?: "hub" | "spoke" | "money" | "other", "topic"?, "notes"? }), then continue. Never front-load the full interview; suggestseo-project-setupat the end for the rest. - Before paying, check
researchLog. If the same research ran within the last 30 days, reuse its evidence and say so instead of buying it again. - On finish, write back what is durable: new or corrected
keyPagesentries with the topic each page now targets, and append{ "entryDate": "<today from agenticseo context>", "summary": "Keyword clustering: <keyword set>. Verdict: <conclusion>. Evidence: <paths>" }toresearchLog. Runagenticseo contextto validate.
Deliver as a report
Deliver through the seo-report skill. If that skill is not available, say so and stop before writing the report.
Commands
agenticseo saved list [--tags TAG,...]: fetch an existing keyword set, optionally filtered by tags, with its latest metrics.agenticseo research "SEED"...: expand a seed when the user starts from a topic.agenticseo ranked DOMAIN: exact ranking keywords and URLs when the user starts from a domain or page.agenticseo gsc performance --dimensions query,page: when Search Console is connected, real queries mapped to the pages already earning impressions, and cannibalization (one query splitting impressions across several URLs). Free; it exits 2 when not connected.agenticseo keywords TERM...: volume, difficulty and intent for the final candidates.agenticseo serp "QUERY"...: validate whether keywords belong on the same page by checking SERP overlap and intent, up to 10 queries per call.agenticseo local serp "QUERY" --near LAT,LNG: for local SEO clusters, when Maps or local-pack intent should affect page mapping.agenticseo saved add KEYWORD... --tags TAG,...: optionally tag the final clusters after the user confirms.
Workflow
- Gather the candidate keyword set.
- When Search Console is connected, start from real queries and the pages already ranking for them:
agenticseo gsc performance --dimensions query,page --limit 1000. - Use
agenticseo rankedfor domain- or page-driven clustering. - Use
agenticseo local businessesandagenticseo local serpwhen proximity, local packs or Google Business results decide whether terms belong on location pages.
- When Search Console is connected, start from real queries and the pages already ranking for them:
- Remove duplicates, irrelevant terms and terms that clearly require a different product or audience.
- Build clusters around intent and page type:
- Same SERP intent and similar ranking pages belong together.
- Different intent, buyer stage or SERP format should be split.
- Similar words do not guarantee the same cluster.
- For important borderline terms, run a small batch of
agenticseo serpchecks to compare the ranking URLs. - Assign each cluster to:
- An existing URL, if supplied and appropriate
- A new page recommendation, if no existing page fits
- A do-not-target / later bucket, if weak or off-strategy
- Identify cannibalization risk when several pages would target the same intent. When Search Console is connected, confirm it from real data: the same query sending impressions to several URLs in
agenticseo gsc performance --dimensions query,page. - Ask before applying cluster tags with
agenticseo saved add ... --tags.
Output format
Title: Keyword Clustering: <site or keyword set> — <date> (see seo-report; omit the site when it is the project's domain).
If a report template applies (see seo-report), its sections and tone replace this list.
Sections in this order:
- The map: one or two opening sentences: how many clusters, how many pages to create, how many to update, and any cannibalization found.
- Clusters: a table of cluster, primary keyword, intent, target page and priority. Keep secondary keywords in the per-cluster briefs, not in this table.
- Page briefs: one finding per cluster: the page type and the searcher's problem, then the page to create or update. List required sections and internal links underneath.
- Cannibalization: a table of the query, the competing URLs and which one to keep, only when there is real evidence for it.
- What to do next: an ordered list, including the tag suggestions and the explicit ask before applying them.
- How this report was made: opens with the skill link line from
seo-report, pointing athttps://github.com/kid7st/agenticseo/blob/main/.agents/skills/keyword-clustering/SKILL.md("AgenticSEO Keyword Clustering skill"), then where the keywords came from (with costs and evidence paths for paid lookups), and a note labelling target pages as proposed when no URL data was supplied.
Guardrails
- Do not over-cluster tiny keyword sets. If there are fewer than 10 usable terms, produce a simple map.
- Do not rely on lexical similarity alone. SERP intent wins.
- Do not replace tags broadly without explicit confirmation (
--replace-tagsreplaces a keyword's tags). - If existing URL data is missing, label target pages as proposed.
- Search Console positions are averages over the date range, and its clicks are not GA4 sessions; compare them, do not add them.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

