Content Matrix logo

Content Matrix

CommunityPopular
charlie947
content-matrix

Generate 24 to 40 LinkedIn post ideas in a single table by pairing the user's content pillars with 8 proven content formats. Based on the Justin Welsh content matrix. Use this skill whenever the user says "give me post ideas", "content matrix", "what should I post about", "generate post ideas", "content ideation", or "map out my content for the month". Pulls from about-me.md and voice.md if they exist, otherwise asks for pillars and context.

Overview

Publishercharlie947
Repositorysocial-media-skills
Skill namecontent-matrix
Stars
3.6K
Forks
836
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 charlie947 on GitHub. Read the source before you install it.

Installation

Install the Content Matrix 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/charlie947/social-media-skills.git /tmp/social-media-skills
mkdir -p .claude/skills
cp -r /tmp/social-media-skills/skills/content-matrix .claude/skills/content-matrix
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Content Matrix 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 Content Matrix 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 Content Matrix 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.

Content Matrix

Codex and Claude runtime

  • Use this skill in Codex or Claude with the tools actually available in the current task. AskUserQuestion examples describe the questions, not a required API: use an available question tool within its limits, or ask in chat. Reuse answers and source material already supplied.
  • Work in the user-selected project. Read its about-me.md, voice.md and relevant brand files before personalised work. Confirm the intended author if files conflict or contain starter defaults. Ask for missing facts or run voice-builder; never inherit the maintainer's identity, accounts or private files.
  • Resolve bundled references/ relative to this skill folder. For an explicitly requested profile refresh, read and update the canonical about-me.md, voice.md or newsletter-voice.md in place, preserving unrelated user facts and rules. Consumers must reread those canonical files. Use a new filename only for new deliverables that would collide with unrelated existing files. Installation alone never starts an interview or writes files. Do not write persistent learnings unless requested.
  • Use supplied evidence first. Verify external claims through available search/source tools when needed. If a source or integration is unavailable, name the missing capability and offer supplied text/export input. Never invent facts, first-person experience, metrics or a successful tool run.
  • Connect only services needed for the chosen route through the user's existing account. Never print credentials or overwrite connections. Drafting, saving and reviewing do not authorise publishing, sending messages or changing accounts.

CRITICAL: Auto-start on load

When this skill triggers, go straight to Step 1. Do not summarise. Start input gathering immediately.

Step 1. Gather inputs

Check the project for about-me.md. If it exists, read it and pre-fill the description of who the user is. Skip that question and tell the user what you pulled.

If about-me.md is missing, ask:

Give me at least two paragraphs describing who you are, what you do, and what you like to discuss. The more specific you are, the more relevant the ideas.

Wait for response.

Then call AskUserQuestion:

json
[
  {
    "question": "What are your content pillars?",
    "header": "Pillars",
    "multiSelect": false,
    "options": [
      {"label": "I will type them", "description": "I have 3 to 4 content pillars to use"},
      {"label": "Pull from voice.md", "description": "Use the topics already defined in my voice files"},
      {"label": "Suggest them for me", "description": "Based on my about-me.md, recommend 4 pillars"}
    ]
  }
]

If the user types their own, accept 3 to 5 pillars. If fewer than 3, ask for more.

If the user picks "Suggest them for me", read about-me.md, propose 4 pillars covering their positioning, and ask them to confirm or edit before continuing.

Step 2. Build the matrix

Generate a markdown table with:

  • X axis (columns): 8 content formats, always in this order:
    1. Actionable
    2. Motivational
    3. Analytical
    4. Contrarian
    5. Observation
    6. X vs Y
    7. Present vs Future
    8. Listicle
  • Y axis (rows): the user's 3 to 5 pillars

Every cell contains one specific, concrete post idea tailored to the pillar and format. Not generic. Not reusable across pillars.

Format definitions to apply when filling each cell:

  • Actionable: Ultra-specific how-to. Teaches the reader to do one thing.
  • Motivational: Inspirational story about someone who did something extraordinary in the niche.
  • Analytical: Breakdown of why something works the way it does.
  • Contrarian: Go against the common advice in the niche and back it up.
  • Observation: A hidden, silent, or underdiscussed trend the user has noticed.
  • X vs Y: Compare two entities (tools, styles, frameworks, companies).
  • Present vs Future: Current state vs a specific prediction, with the why.
  • Listicle: A list of resources, tips, mistakes, lessons, or steps.

Each cell's idea should be a specific headline, not a theme. Good: "A 3-line hook formula for product launches". Bad: "Hooks".

Step 3. Output (surface-aware)

Pick the output mode based on the surface you are running on. Do not output the table in a fenced markdown code block — that renders as monospace plain text and makes a 5×8 grid hard to scan.

  • An available interactive chart/table surface: render the matrix as an interactive chart / interactive table widget. Pillars as rows, formats as columns, each cell holding one specific headline. The user should be able to click a cell to see the full headline and any expansion notes. Do not also dump the table as markdown — the chart is the deliverable.
  • A file-capable assistant such as Codex or Claude Code: save the matrix to content-matrix-YYYY-MM-DD.md in the current working directory and print the same table inline in the response as a plain markdown table (no triple-backtick wrap). Confirm the file path so the user can open it.
  • Fallback (no interactive chart, no file-system tools): output a plain markdown table inline. Still no code-fence wrap.

Below the table or chart, add one sentence naming the single strongest idea across the matrix and why.

Step 4. Offer the next move

Ask:

Any cell here you want me to write as a full post? Reference the cell by pillar + format (for example "Hooks × Contrarian") and I will hand it to the post-writer or post-formatter skill.

When file tools are available, also offer to append the drafted post into the same content-matrix-YYYY-MM-DD.md file under the cell reference.

Rules

  • Minimum 3 pillars, maximum 5. More than 5 dilutes the matrix.
  • Every cell idea must be specific to that pillar AND that format. Do not reuse the same idea across pillars.
  • Tune the language to the user's voice if voice.md exists.
  • British English unless voice.md specifies American.
  • Never use em dashes.

Frequently asked questions

What does the Content Matrix AI skill do?

Generate 24 to 40 LinkedIn post ideas in a single table by pairing the user's content pillars with 8 proven content formats. Based on the Justin Welsh content matrix. Use this skill whenever the user says "give me post ideas", "content matrix", "what should I post about", "generate post ideas", "content ideation", or "map out my content for the month". Pulls from about-me.md and voice.md if they exist, otherwise asks for pillars and context.

Why use Content Matrix on TypingMind?

Because you install it once and use it with any model. Content Matrix 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 Content Matrix in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/charlie947/social-media-skills/tree/main/skills/content-matrix. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Content Matrix?

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 Content Matrix?

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

Is the Content Matrix AI skill free?

Yes. It is published on GitHub by charlie947 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 👇