seo-keyword-cluster

seo-keyword-cluster is a skill for Claude Code from seranking/seo-skills. It costs 109 tokens per session (2,485 once invoked), scanned A, original, MIT.

A search-planning tool that groups related keywords by topic and by what people want to find. It maps a main “pillar” page to supporting “spoke” articles.

In plain words
What is it for?
Use it to expand seed keywords, identify question-based topics, suggest article headings, prioritize content, and plan internal links between pages.
Why use it?
It turns a small list of starting keywords into an organized content plan instead of leaving you to guess which articles to create or how they should connect.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the seo-skills plugin — 32 skills, 1 MCP server shipped together

Good fit Use it to expand seed keywords, identify question-based topics, suggest article headings, prioritize content, and plan internal links between pages.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/seranking/seo-skills/seo-keyword-cluster
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add seranking/seo-skills --skill seo-keyword-cluster
Clone the repo
git clone --depth 1 https://github.com/seranking/seo-skills

Made for: Claude Code.

Or install seo-skills, the plugin that ships this one along with the rest of its 32 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for seo-keyword-cluster

README.md
[![agentmods](https://agentmods.dev/badge/skills/seranking/seo-skills/seo-keyword-cluster/github.svg)](https://agentmods.dev/skills/seranking/seo-skills/seo-keyword-cluster)
Your own site
<a href="https://agentmods.dev/skills/seranking/seo-skills/seo-keyword-cluster"><img src="https://agentmods.dev/badge/skills/seranking/seo-skills/seo-keyword-cluster/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for seo-keyword-cluster

Your own site · 80×15
<a href="https://agentmods.dev/skills/seranking/seo-skills/seo-keyword-cluster"><img src="https://agentmods.dev/badge/skills/seranking/seo-skills/seo-keyword-cluster.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 109 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,485 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00109 $0.02485
Opus 5 $0.00055 $0.01242
Sonnet 5 $0.00022 $0.00497
Haiku 4.5 $0.00011 $0.00248

Measured 11d ago against content hash e25b8d8502d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

seo-keyword-cluster scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/seo-keyword-cluster/SKILL.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Example output: examples/seo-keyword-cluster-headless-cms-20260514/PLAN.md

Keyword Cluster

Transform seed keywords into a prioritised cluster plan: each cluster grouped by search intent and theme, with volume totals, a pillar concept, spoke articles, and suggested H1/H2 for each spoke.

Prerequisites

  • SE Ranking MCP server connected.
  • User provides: (a) 3 to 20 seed keywords, (b) target market country (default: us), and optionally (c) minimum volume threshold (default: 100/mo), (d) maximum KD (default: 60).

Process

  1. Expand seeds DATA_getRelatedKeywords, DATA_getSimilarKeywords, DATA_getLongTailKeywords

    • For each seed, pull related + similar + long-tail variants in the target country.
    • Target at least 100 candidate keywords per seed; de-duplicate across seeds.
  2. Question-based expansion DATA_getKeywordQuestions

    • Pull question-intent keywords for the top 5 seeds.
    • These usually become spoke articles with PAA/featured-snippet potential.
  3. Clean and filter

    • Remove keywords below min volume and above max KD.
    • Strip branded terms the target does not own.
    • Tag each keyword with detected intent: informational, commercial, transactional, navigational.
  4. Cluster by SERP overlap DATA_getSerpResults (or DATA_getSerpTaskAdvancedResults)

    • Group keywords by how Google actually ranks them — shared top-10 organic URLs — not by text similarity. Token-overlap clustering manufactures cannibalisation; see references/serp-overlap-methodology.md for the full algorithm and anti-pattern callouts.
    • Budget guard before running. Compute estimated_credits = num_candidate_keywords × per_keyword_cost where per_keyword_cost = 3 (SERP-standard, default) or 10 (SERP-advanced, only if downstream needs AIO/PAA). Standard is sufficient for clustering. If estimated_credits > 500, surface the figure to the user and offer two paths: (a) proceed with SERP-standard, (b) trim the candidate set by raising the min-volume / lowering the max-KD thresholds in step 3 and re-running. If the user already requested SERP-advanced and the estimate exceeds 500, additionally offer SERP-standard as a cheaper fallback.
    • Fetch SERPs (one call per unique candidate keyword, cached for the session) — see references/serp-overlap-methodology.md § "Caching". Total SERP fetches = number of keywords, not number of pairs.
    • Pairwise overlap scoring. For each pair within an intent pre-group (see references/serp-overlap-methodology.md § "Pre-Grouping" for the optimisation that avoids full O(N²)), count shared URLs in the top 10 organic. Apply thresholds: 7-10 shared = same post (merge keywords), 4-6 = same cluster, 2-3 = interlink across clusters, 0-1 = separate clusters or exclude.
    • Form clusters from the connected components in the 4-6+ overlap graph. Target 5 to 12 clusters. Each cluster gets a name, primary keyword, secondary keywords, total volume, weighted KD.
    • Classify each cluster as pillar-worthy (broad, high volume, informational) or spoke-only (narrow, specific).

Read the full file on GitHub · 142 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 142 lines · 109 tokens per session scan A e25b8d8502d2

Subscribe to this mod's changes

seo-keyword-cluster is a skill published in the GitHub repository seranking/seo-skills (139 stars, last pushed 2mo ago), licensed MIT. It adds 109 tokens to every session and 2,485 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

analytics-strategy

Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…

rampstackco/claude-skills · 126 tokens

content-strategy

Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align…

rampstackco/claude-skills · 120 tokens

incident-response

Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…

rampstackco/claude-skills · 117 tokens

stakeholder-communication

Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…

rampstackco/claude-skills · 103 tokens

agb-begriff-vorformuliert-305

Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.

Klotzkette/claude-fuer-deutsches-recht · 68 tokens

review-work

Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.

code-yeongyu/oh-my-openagent · 63 tokens