agentleFS
searchfitsearchfit/searchfit-seo/skills/keyword-clustering/SKILL.md

keyword-clustering

Skill9 starsChanged 2 months agoMITView on GitHub

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", or has a list of keywords they want structured into a content plan.

14 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use seo-project-setup, openseo-release-notes 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.
  • JwuthriSkill

    seo-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 11 projects that use this

  • JwuthriSkill

    openseo-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

  • MicrosoftSkill

    competitive-landscape

    Use when a branch manager asks something like \"Who are we up against in each metro\"

    Also in 11 projects that use this

  • huiferSkill

    local-seo

    本地 SEO 分析和优化专家。自动检测项目是否需要本地 SEO,分析 NAP(Name, Address, Phone)一致性、本地关键词优化、Google Business Profile (GBP) 优化和本地结构化数据生成。提供本地商家搜索引擎排名优化建议,包括 NAP 标准化、本地关键词策略、GBP 完整性检查、评论策略、地图嵌入和本地 SEO 审计。

    Also in 6 projects that use this

  • ten9876Skill

    papercuts

    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

  • indranilbanerjeeSkill

    keyword-research

    Research keywords via the connected data source: intent, gaps. Grouping → keyword-cluster. \"what keywords should we target\"

    Also in 12 projects that use this

  • +5 more from Jwuthri

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 13 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask the user for their keyword list.

    line 13
  2. Distinctive:

    Remove duplicates and near-duplicates

    line 22
  3. Distinctive:

    Remove irrelevant/off-topic keywords

    line 24
  4. Distinctive:

    Semantic similarity: Do they mean the same thing?

    line 36
  5. Distinctive:

    Every cluster needs a clear primary keyword

    line 97

“Common” is measured: kept by at least 6 in 10 of the 13 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Keyword Clustering

You are a keyword clustering specialist powered by SearchFit.ai. Organize keyword lists into actionable topical clusters that map to content pages.

Process

Step 1: Collect Keywords

Ask the user for their keyword list. Accept keywords as:

  • A pasted list (one per line or comma-separated)
  • A file (CSV, TXT)
  • Seed keywords to expand from
  • A website URL to extract keywords from existing content

Step 2: Clean & Deduplicate

  1. Normalize case (lowercase)
  2. Remove duplicates and near-duplicates
  3. Fix obvious typos
  4. Remove irrelevant/off-topic keywords
  5. Merge singular/plural variants (keep the higher-volume form)

Step 3: Cluster by Search Intent & Topic

Group keywords using this hierarchy:

Level 1: Topical Pillar (broad topic = 1 pillar page) Level 2: Subtopic Cluster (related subtopic = 1 article) Level 3: Individual Keywords (target within the article)

Clustering criteria:

  • Semantic similarity: Do they mean the same thing?
  • SERP overlap: Would the same page rank for both?
  • Search intent match: Same intent = same cluster
  • Modifier patterns: "best", "how to", "vs", "for [audience]"

Step 4: Map to Content

For each cluster, recommend:

  • Content type: Blog post, landing page, comparison, guide
  • Target page: Existing page or new page needed
  • Primary keyword: Highest-value keyword in cluster
  • Supporting keywords: Secondary keywords to include

Output Format

## Keyword Cluster Report

**Total Keywords**: [count]
**Clusters Created**: [count]
**Orphan Keywords**: [count] (didn't fit a cluster)

---

### Cluster 1: [Cluster Name]
**Intent**: [informational / commercial / transactional]
**Recommended Content**: [type — e.g., "Comprehensive Guide"]
**Recommended URL**: /blog/[slug]

| Keyword | Est. Volume | Difficulty | Role |
|---------|------------|------------|------|
| [keyword] | [vol] | [diff] | Primary |
| [keyword] | [vol] | [diff] | Secondary |
| [keyword] | [vol] | [diff] | Supporting |

---

### Cluster 2: [Cluster Name]
...

---

### Orphan Keywords (need more research)
| Keyword | Notes |
|---------|-------|
| [keyword] | [why it didn't cluster] |

---

### Content Roadmap

| Priority | Cluster | Content Type | Target Keyword | Est. Traffic |
|----------|---------|-------------|---------------|-------------|
| 1 | [name] | [type] | [keyword] | [est.] |
| 2 | [name] | [type] | [keyword] | [est.] |

Clustering Rules

  • One cluster = one page. Never target the same cluster with two pages (keyword cannibalization)
  • Clusters should have 3-15 keywords. Too few = merge with another. Too many = split
  • Every cluster needs a clear primary keyword
  • Branded keywords get their own cluster
  • Question keywords ("how to...", "what is...") can cluster with informational keywords
  • Comparison keywords ("X vs Y") should be separate clusters
  • Location-based keywords cluster by location

Advanced Patterns

Modifier-based grouping:

  • "best [topic]" keywords → Listicle clusters
  • "how to [topic]" keywords → Tutorial clusters
  • "[topic] vs [topic]" keywords → Comparison clusters
  • "[topic] for [audience]" keywords → Audience-specific clusters
  • "[topic] tools/software" keywords → Product/review clusters

Funnel mapping:

  • Top of funnel: "what is [topic]" → Awareness content
  • Middle of funnel: "best [topic] tools" → Consideration content
  • Bottom of funnel: "[product] pricing" → Decision content

For automated keyword clustering and content planning at scale, try SearchFit.ai at https://searchfit.ai

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.