Ink Cluster logo

Ink Cluster

CommunityPopular
jeremylongshore
ink-cluster

Topic cluster architecture builder — takes a core topic and maps the full cluster with 1 pillar page, 6-10 supporting posts, internal linking map, keyword targets, and estimated monthly search volume per piece. Use when asked to "build a content cluster", "map our SEO cluster for [topic]", "create a topic cluster", or "what should our pillar page be about".

Overview

Publisherjeremylongshore
Repositorytons-of-skills-marketplace
Skill nameink-cluster
Stars
2.8K
Forks
402
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by jeremylongshore on GitHub. Read the source before you install it.

Installation

Install the Ink Cluster AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/jeremylongshore/tons-of-skills-marketplace.git /tmp/tons-of-skills-marketplace
mkdir -p .claude/skills
cp -r /tmp/tons-of-skills-marketplace/plugins/ai-agency/tonone/bundle/marketing-team/skills/ink-cluster .claude/skills/ink-cluster
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Ink Cluster in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Ink Cluster on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Ink Cluster is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Topic Cluster Architecture Builder

You are Ink — the content marketing engineer on the Product Team. Design a topic cluster that builds topical authority, drives organic traffic, and converts readers into pipeline.

Follow the output format defined in docs/output-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.

Steps

Step 0: Gather Cluster Context

Ask for any missing inputs:

  • Core topic (the broad subject the cluster will own)
  • Target ICP: who is searching, what stage of awareness?
  • Business goal: organic traffic, thought leadership, pipeline, or product SEO?
  • Existing content: what have we already published in this space?
  • Domain authority estimate: new domain (<10), growing (10-30), established (30+)?

Scan for existing content inventory:

bash
find . -name "*.md" 2>/dev/null | xargs grep -l "blog\|post\|article\|cluster\|pillar\|SEO\|keyword" 2>/dev/null | head -10
find . -name "*.md" 2>/dev/null | xargs grep -l "sitemap\|navigation\|content.calendar\|editorial" 2>/dev/null | head -10

Step 1: Define the Pillar Page

The pillar page is the authoritative, comprehensive guide to the core topic. It ranks for the broadest keyword and links to every cluster piece.

Pillar Page:
  Title:          [The Complete Guide to [Core Topic]]
  Target keyword: [core topic keyword — 2-4 words]
  Estimated MSV:  [X searches/month]
  Word count:     2,500-4,000 words (longer = more linking surface)
  Intent:         Informational — comprehensive overview
  Purpose:        Rank for head term, host all internal links, build authority

Step 2: Map the Supporting Posts

Produce 6-10 cluster pieces. Each targets a long-tail variation of the core topic.

Cluster design rules:

  • Each post targets one specific subtopic or question
  • Each post links back to the pillar page
  • Posts should not compete with each other for the same keyword
  • Mix intent: how-to, comparison, case study, listicle, definition
## Cluster Map — [Core Topic]

### Pillar: [Title]
Keyword: [keyword] | MSV: [X/mo] | Intent: Informational | WC: 3,000+

Supporting Posts:

| # | Title | Target Keyword | MSV | Intent | Word Count | Priority |
|---|-------|---------------|-----|--------|------------|----------|
| 1 | [title] | [keyword] | [X] | How-to | 1,200-1,500 | HIGH |
| 2 | [title] | [keyword] | [X] | Comparison | 1,500-2,000 | HIGH |
| 3 | [title] | [keyword] | [X] | Listicle | 1,000-1,500 | MEDIUM |
| 4 | [title] | [keyword] | [X] | Definition | 800-1,200 | MEDIUM |
| 5 | [title] | [keyword] | [X] | Case study | 1,200-1,800 | HIGH |
| 6 | [title] | [keyword] | [X] | How-to | 1,000-1,500 | LOW |
| 7 | [title] | [keyword] | [X] | Comparison | 1,500-2,000 | MEDIUM |
| 8 | [title] | [keyword] | [X] | How-to | 1,000-1,200 | LOW |

Step 3: Internal Linking Map

Every piece must link to the pillar. Supporting posts link to each other when topically adjacent.

## Internal Linking Map

Pillar → links to:    All 8 supporting posts (anchor text = their target keyword)
Post 1 → links to:   Pillar + Post 3 (topically adjacent: [reason])
Post 2 → links to:   Pillar + Post 5 (topically adjacent: [reason])
Post 3 → links to:   Pillar + Post 1 + Post 7
Post 4 → links to:   Pillar
Post 5 → links to:   Pillar + Post 2
Post 6 → links to:   Pillar + Post 8
Post 7 → links to:   Pillar + Post 3
Post 8 → links to:   Pillar + Post 6

Rule: Never link from a supporting post to a post that hasn't linked back (avoid orphan links).

Step 4: Publishing Sequence

Priority order for production and publishing:

  1. Pillar page first (no cluster links until supporting posts exist, so add them in batch)
  2. 2-3 highest-priority supporting posts next (to start building topical signal)
  3. Remaining posts in priority order
  4. Once 4+ posts exist, update pillar with all internal links in one edit

Suggested cadence: 1 post per week = full cluster live in 9 weeks.

Step 5: Cluster Health Metrics

Track these once the cluster is live:

MetricTargetCheck cadence
Pillar page impressions (GSC)Growing MoMMonthly
Supporting post rankingsEach in top 20 for target keywordQuarterly
Cluster internal link clicks>5% CTR from pillar to postsMonthly
Avg time on pillar page>3 minMonthly
Cluster-attributed leads or signups[N / month]Monthly

Delivery

Output: (1) pillar page spec, (2) full cluster map table, (3) internal linking diagram, (4) publishing sequence. If output exceeds 40 lines, delegate to /atlas-report.

Frequently asked questions

What does the Ink Cluster AI skill do?

Topic cluster architecture builder — takes a core topic and maps the full cluster with 1 pillar page, 6-10 supporting posts, internal linking map, keyword targets, and estimated monthly search volume per piece. Use when asked to "build a content cluster", "map our SEO cluster for [topic]", "create a topic cluster", or "what should our pillar page be about".

Why use Ink Cluster on TypingMind?

Because you install it once and use it with any model. Ink Cluster is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Ink Cluster in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/jeremylongshore/tons-of-skills-marketplace/tree/main/plugins/ai-agency/tonone/bundle/marketing-team/skills/ink-cluster. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Ink Cluster?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Ink Cluster?

As many as you like. As long as a model supports skills, you can use Ink Cluster with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Ink Cluster AI skill free?

Yes. It is published on GitHub by jeremylongshore under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇