keyword-research
Skill30 starsChanged 5 months agoMITView on GitHub
Build a prioritized keyword cluster map using the 6 Circles Method — keywords at the intersection of positioning alignment, customer language, competitor blind spots, workable search volume, real expertise, and business intent. Use when the user asks 'what keywords should I target', 'what should I write about', 'find SEO opportunities', 'plan my content strategy', 'what does my audience search for', or before any SEO content is written. Produces a Keyword Map: scored keywords grouped into topic clusters, each cluster mapped to the article that should target it, ready to hand to content production.
59 other projects use a version of this.
Adopted by
Most recently taken up by
- gaznil/seo-skills-by-gazniltheir own version, first seen Nov 16, 2026
- gaznilmuzammil12-prog/seo-skills-by-gazniltheir own version, first seen Nov 16, 2026
- teemukarjaluoto/seo-sauna-mcptheir own version, first seen Nov 16, 2026
- harborrank/harborrank-skillstheir own version, first seen Nov 16, 2026
- winsley-jeune/harborrank-skillstheir own version, first seen Nov 15, 2026
- asospy/asospy-agent-skillstheir own version, first seen Nov 15, 2026
Used with
Projects with it also use link-prospecting, seo-project-setup and 10 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.
JwuthriSkilllink-prospecting
Find link prospects, discover contact paths, and draft outreach from SERPs and backlink signals.
Also in 13 projects that use this
JwuthriSkillseo-project-setup
Set up a durable local SEO workspace with project context, notes, goals, positioning, preferences, MCP checks, and Search Console data intake.
Also in 13 projects that use this
Ethan-paseyaSkillreview-analysis
Amazon review and VOC analysis using SellerSprite MCP. Use when the user runs `/review-analysis {ASIN} {SITE}` to analyze positive and negative reviews, identify product pain points, listing mismatch, service risks, and product improvement actions.
Also in 6 projects that use this
akii-technologies-ltdSkillkeyword-clustering
Cluster and organize keywords into topical groups for SEO. Use when the user asks to "cluster keywords", "group keywords", "organize keywords", "keyword mapping", "topic clusters", "keyword grouping", "build a content plan", "pillar pages", "topical authority", "semantic clustering", or pastes a list of keywords.
Also in 14 projects that use this
Kungfookenny123Skillapp-marketing-context
When the user wants to create or update their app marketing context document. Also use when the user mentions "app context", "marketing brief", "app positioning", or when starting any ASO or app marketing project. This is the foundation skill — all other skills check for this context first.
Also in 4 projects that use this
Kungfookenny123Skillmetadata-optimization
When the user wants to optimize App Store metadata — title, subtitle, keyword field, or description. Also use when the user mentions "optimize my title", "ASO metadata", "keyword field", "character limits", "app description", or "write my subtitle". For keyword discovery, see keyword-research. For full ASO audits, see aso-audit.
Also in 4 projects that use this
- +4 more from Jwuthri
Other versions59 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 59
- every-app/open-seo★ 28ksame name
- Ryze-AI-Adgent/open-seo-mcp-skills★ 8.4ksame name
- nowork-studio/toprank★ 4.2ksame name
- nowork-studio/notfair-plugin★ 4.2ksame name
- Jwuthri/Tracely-ai★ 1.3ksame name
- liangdabiao/amazon-sorftime-research-MCP-skill★ 1.1ksame name
- VladSez/easy-invoice-pdf★ 1.1ksame name
- kostja94/marketing-skills★ 1.1ksame name
- jwuthri-cloud/Tracely-ai★ 979same name
- indranilbanerjee/digital-marketing-pro★ 934same name
49 more not listed
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 repository39 other files it gives its agents.
- brand-assetSkill
- creative-strategistSkill
- image-generationSkill
- orchestratorSkill
- original-designSkill
- product-photographySkill
- product-videoSkill
- remotion-script-writerSkill
- social-graphicsSkill
- talking-headSkill
- accessibility-excellenceSkill
- color-systemSkill
- component-architectureSkill
- design-engineer-mindsetSkill
- design-foundationSkill
- error-handling-recoverySkill
- frontend-orchestratorSkill
- interaction-physicsSkill
- layout-systemSkill
- loading-statesSkill
- performance-optimizationSkill
- typography-systemSkill
- visual-hierarchy-refactoringSkill
- brand-voiceSkill
- content-atomizerSkill
- direct-response-copySkill
- email-sequencesSkill
- lead-magnetSkill
- newsletterSkill
- orchestratorSkill
- positioning-anglesSkill
- seo-contentSkill
- seo-strategySkill
- tweet-writerSkill
- product-design-reviewSkill
- fable-like-implementationSkill
- foundation-sprintSkill
- sol-orchestratorSkill
- sprint-runnerSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 3 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 54 edited versions we read keep these.
3
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 12
Use before writing SEO content, when planning a content calendar, or when the user wants to know what their audience searches for.
- Very specific: line 13
If no positioning statement exists, run skills/marketing/positioning-angles first (or infer a provisional one and label it) — circle 1 is …
- Very specific: line 14
If the user wants the *full* organic program — link building, technical SEO, programmatic pages, domain authority — use …
- Very specific: line 15
If keywords already exist and the user wants the article written, go straight to skills/marketing/seo-content.
- Distinctive: line 31
Run the circles as sequential filters: generate wide in circles 1–2, then cut in 3–6.
- Very specific: line 41
Check each surviving keyword against the competitors' content (crawl their blog/sitemap or search site:competitor.com <keyword>).
- Distinctive: line 50
Keep only keywords where the user can honestly out-write the current top results — first-hand experience, proprietary data, a named …
“Common” is measured: kept by at least 6 in 10 of the 54 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
Keyword Research
Produce a keyword map: a scored, clustered list of search terms worth targeting, each tied to the content that should win it. Governing principle: a keyword is only worth targeting if it survives all six circles — aligned with the positioning, phrased in the customer's language, under-served by competitors, actually searched, winnable with the user's real expertise, and connected to revenue. Traffic that fails circle 6 is vanity.
When to use / when not to
- Use before writing SEO content, when planning a content calendar, or when the user wants to know what their audience searches for.
- If no positioning statement exists, run
skills/marketing/positioning-anglesfirst (or infer a provisional one and label it) — circle 1 is unworkable without it. - If the user wants the full organic program — link building, technical SEO, programmatic pages, domain authority — use
skills/marketing/seo-strategy; this skill is the keyword-selection layer only. - If keywords already exist and the user wants the article written, go straight to
skills/marketing/seo-content.
Intake
One batch; reuse anything already produced by skills/marketing/orchestrator or skills/marketing/positioning-angles:
- Your positioning statement (or: what you sell, to whom, and what makes it different).
- Your 2–3 closest competitors' websites.
- Any sources of raw customer language — support tickets, sales calls, reviews, community threads — or paste examples of how customers describe the problem.
- Site status: domain age, roughly how much content published, any current rankings? (Determines how competitive a keyword you can win.)
- Access to a keyword tool (Ahrefs, Semrush, Google Keyword Planner)? If yes, the user runs volume lookups when asked; if no, proceed with estimates.
Don't stall: with a positioning statement and a recognizable market you can draft the full map from knowledge and web research — label all volumes and difficulty as estimates and list them for the user to verify in a tool.
Workflow — the 6 Circles Method
Run the circles as sequential filters: generate wide in circles 1–2, then cut in 3–6.
Circle 1 — Positioning alignment (seed)
Expand the positioning statement into 20–40 seed keywords. Take each element of the claim (audience, problem, mechanism, outcome) and list the searches that element implies. Rule: seeds come from the angle, not the category. "Project management tool for remote teams" seeds remote-team keywords (async standups, distributed team communication), not generic project management keywords the incumbents own.
Circle 2 — Customer language (rephrase)
Rewrite every seed in the words customers actually type, harvested from the intake sources. Kill jargon: if customers say "remote work tools", drop "distributed workforce management solutions". Add the question-form variants ("how do I…", "best X for Y", "X vs Y") — those carry the clearest intent.
Circle 3 — Competitor blind spots (cut or boost)
Check each surviving keyword against the competitors' content (crawl their blog/sitemap or search site:competitor.com <keyword>).
- Competitors rank with strong, current content → cut, unless the user has a decisively better asset.
- Competitors ignore it or cover it thinly/outdated → boost priority. These gaps are the map's best entries.
Circle 4 — Search volume (screen)
Screen for workable volume. Heuristic (label it as such): target roughly 100–10,000 searches/month — below ~100 rarely repays an article; above ~10,000 is usually incumbent territory for a young domain. Decision rules: established domain with authority (from intake Q4) → the upper bound relaxes; brand-new domain → stay in the low hundreds-to-low-thousands band. If no tool access, estimate from autocomplete breadth, "People also ask" density, and ad presence — and flag every estimate.
Circle 5 — Expertise (cut)
Keep only keywords where the user can honestly out-write the current top results — first-hand experience, proprietary data, a named mechanism, or a sharper niche take. If the user can't add anything the top 3 results lack, cut the keyword regardless of volume.
Circle 6 — Business intent (score)
Score what remains by distance to revenue:
- High: buying/comparison intent — "best X for Y", "X vs Y", "X pricing", "X alternative".
- Medium: problem-aware how-tos the offer solves — "how to manage remote teams".
- Low: informational adjacency — "remote work statistics". Keep low-intent keywords only as cluster support, never as the cluster head.
Cluster and prioritize
Group survivors into topic clusters (one head keyword + 3–8 supporting keywords that one strong article or hub can cover). Priority order: high intent + competitor blind spot first, then high intent + contested, then medium intent gaps. Propose the top 3–5 clusters and have the user confirm the order before content production starts.
Required output format
# Keyword Map — [Brand]
**Positioning it serves:** "[claim from skills/marketing/positioning-angles]"
**Volume/difficulty source:** [tool name | estimates — user to verify]
## Priority clusters
### Cluster 1: [name] — Priority: HIGH
Target article: "[working title]" — intent: [high/med] — feeds: [lead magnet / product page]
| Keyword | Role | Est. volume | Competition note | Intent |
|---|---|---|---|---|
| [head keyword] | Head | ~N/mo | [gap / thin / contested] | High |
| [supporting] | Support | ... | ... | ... |
### Cluster 2: ...
(3–5 clusters total)
## Cut list (why keywords were rejected)
- "[keyword]" — failed circle [n]: [one-line reason]
(representative sample, not exhaustive)
## Assumptions & verification queue
- [every estimated volume or inferred competitor read, listed for tool verification]
**Next step:** write Cluster 1's target article via skills/marketing/seo-content.Quality bar (check before delivering)
- Every cluster head passed all six circles; the failing circle is named for every cut shown.
- No cluster head is a generic category term the incumbents own.
- Every keyword uses customer phrasing — zero internal jargon survives.
- All volumes labeled with their source; estimates explicitly flagged, never presented as tool data.
- Every cluster names the article that targets it and the business asset it feeds.
- 3–5 clusters delivered, priority-ordered and user-confirmed — not an undifferentiated keyword dump.
Integration
- Upstream:
skills/marketing/positioning-anglessupplies the claim that seeds circle 1;skills/marketing/orchestratorroutes here on awareness and scale paths. - Downstream:
skills/marketing/seo-contentconsumes the cluster map one cluster at a time (head keyword + supports + working title cross the boundary);skills/marketing/seo-strategyconsumes it as the keyword layer of a full program;skills/marketing/content-atomizeruses cluster themes to steer repurposing.
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.

