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.
npx skills add seranking/seo-skills --skill seo-keyword-clustergit clone --depth 1 https://github.com/seranking/seo-skillsWrote 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.
[](https://agentmods.dev/skills/seranking/seo-skills/seo-keyword-cluster)<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.
<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>- NVIDIA SkillSpector pass
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.
| Model | Per session | Once 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 |
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.
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
-
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.
-
Question-based expansion
DATA_getKeywordQuestions- Pull question-intent keywords for the top 5 seeds.
- These usually become spoke articles with PAA/featured-snippet potential.
-
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.
-
Cluster by SERP overlap
DATA_getSerpResults(orDATA_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.mdfor the full algorithm and anti-pattern callouts. - Budget guard before running. Compute
estimated_credits = num_candidate_keywords × per_keyword_costwhereper_keyword_cost = 3(SERP-standard, default) or10(SERP-advanced, only if downstream needs AIO/PAA). Standard is sufficient for clustering. Ifestimated_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).
- Group keywords by how Google actually ranks them — shared top-10 organic URLs — not by text similarity. Token-overlap clustering manufactures cannibalisation; see
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.
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.
- 11d ago First seen · 142 lines · 109 tokens per session scan A e25b8d8502d2
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.
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.…
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…
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…
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…
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.
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.