Use when planning a topic cluster (hub + spokes) for a new content area. The agent researches the space, identifies the hub topic, maps the spokes, and produces a specific content plan with internal linking strategy.
npx skills add https://github.com/inhouseseo/superseo-skills --skill topic-cluster-planning
Builds a hub-and-spoke architecture for a new content area. Hub = a broad pillar page that owns the topic. Spokes = specific articles that target long-tail keywords and link up to the hub. Done right, this signals topical authority to Google and concentrates link equity on the pages that matter.
Seed topic or broad keyword (required). Example: "email marketing", "keto diet", "small business accounting".
Optionally: your domain, so the agent can check what you've already published in this space.
You are a senior SEO content strategist specializing in topical authority architecture. You think in clusters, not individual articles.
Google the seed topic. Read:
Note:
The hub is the one page that deserves to own the broad topic. It should:
Hub content type options:
State your recommended hub format with reasoning.
From the PAA questions, related searches, and competitor coverage, identify 8-15 specific spoke topics. Each spoke should:
For each spoke, specify:
Rule of thumb: a spoke should answer a question the hub can only summarize.
Draw the link graph:
Critical: the first link from any spoke TO the hub is what Google's algorithm weights most heavily. Make sure it's contextual (within the article body), with a descriptive anchor text.
Don't publish the hub first. Publish 3-4 high-quality spokes first, then the hub with links to them. Then publish the remaining spokes, each linking back to the now-established hub.
This prevents the hub from launching as a link-less orphan that has nothing to point to.
| # | Spoke Topic | Target Keyword | Content Type | Words | Hub Anchor Text |
|---|---|---|---|---|---|
8-15 rows. Sorted by priority: highest-impact/easiest-to-rank first.
A simple list showing which spokes link to which other spokes. Not every spoke needs to link to every other — just the naturally related ones.
3-5 authoritative external sources the hub should cite. (Not competitors — actual authoritative sources: research papers, industry standards, government/university resources, or the primary creators of the concepts you're discussing.)
For each spoke, use content-brief with the spoke's target keyword to produce a writer-ready brief. Then write-content to write the article.
Load from references/ only when the step calls for them.
first-link-weight-evidence.md — the evidence behind "the first link in the body is weighted most heavily" and why it matters for spoke → hub linking (Step 4, when briefing the writer on anchor placement)publishing-sequence-decisions.md — the full decision framework for "don't publish the hub first" and the exceptions (Step 5, when the user pushes back on the staggered launch)spoke-selection-worked-example.md — a full cluster worked end-to-end (seed → hub → 12 spokes → link map) for a sample niche, to anchor Step 3 when spoke selection feels arbitrarytopic-cluster-strategy.md — the theory behind hub-and-spoke architecture and topical authority signals (background, optional)pillar-page-template.md — exact H1/H2 structure for the hub page (Step 2, after the hub format is chosen)Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers. Trigger when user mentions writing docs, creating proposals, drafting specs, or similar documentation tasks.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Generates creative domain name ideas for your project and checks availability across multiple TLDs (.com, .io, .dev, .ai, etc.). Saves hours of brainstorming and manual checking.
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
Implements Manus-style file-based planning for complex tasks. Creates task_plan.md, findings.md, and progress.md. Use when starting complex multi-step tasks, research projects, or any task requiring >5 tool calls.
Creative research ideation and exploration. Use for open-ended brainstorming sessions, exploring interdisciplinary connections, challenging assumptions, or identifying research gaps. Best for early-stage research planning when you do not have specific observations yet. For formulating testable hypotheses from data use hypothesis-generation.
Comprehensive GitHub project management with swarm-coordinated issue tracking, project board automation, and sprint planning
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree. Use when user wants to stress-test a plan, get grilled on their design, or mentions "grill me".
Take inhouseseo/topic-cluster-planning from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.