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.
Resumen
Content Matrix
Codex and Claude runtime
- Use this skill in Codex or Claude with the tools actually available in the current task.
AskUserQuestionexamples 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.mdand relevant brand files before personalised work. Confirm the intended author if files conflict or contain starter defaults. Ask for missing facts or runvoice-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 canonicalabout-me.md,voice.mdornewsletter-voice.mdin 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:
[
{
"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:
- Actionable
- Motivational
- Analytical
- Contrarian
- Observation
- X vs Y
- Present vs Future
- 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.mdin 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.
Archivos 1 archivo
Instálala a mano
Deska ejecuta esto por ti, para cada agente que elijas. Para ejecutarlo tú en una terminal:
npx skills add charlie947/social-media-skills --skill content-matrixMás de charlie947
- gemini-carouselcharlie947Generate a branded slide-by-slide LinkedIn carousel using Gemini. Takes source content, builds a design brief, waits for approval, then outputs per-slide image generation prompts. 1080x1350 vertical format. Use this skill whenever the user says "carousel", "build a carousel", "turn this into a carousel", "gemini carousel", or wants multi-slide LinkedIn content. Always includes an approval gate between brief and image generation.1 instalaciones en skills.sh0
- hook-generatorcharlie947Generate 6 clickbait-style LinkedIn hook variations for any topic. Two-line hooks built on the formula: a 40-char opening line, a 40-char bold contrast line. Uses supplied numbers and genuine first-person experience when available. Use this skill whenever the user says "write me hooks", "hook ideas", "generate hooks", "I need a hook for a post about...", or pastes a topic and asks for openers. Fast output, no preamble.1 instalaciones en skills.sh0
- reels-scriptingcharlie947Turn a reference Instagram Reel into a script for your own Reel, tuned to your voice and repurposed from your newsletter content. Takes a Reel URL or Notion reference link, uses Apify to scrape the video, sends it to Gemini 2.5 Flash for full transcript + hook + structure analysis, then writes a new script applying the same patterns to your newsletter topic. Use this skill whenever the user says "script a reel", "reels scripting", "turn this into a reel", pastes an Instagram Reel URL, or references their Notion outlier reels database. The URL-to-video-analysis route needs APIFY_API_TOKEN and GOOGLE_AI_API_KEY; supplied input can skip the corresponding stages.1 instalaciones en skills.sh0
- voice-buildercharlie947Build a personalised voice profile inside a Codex or Claude project from a short interview plus 3 to 5 sample pieces of writing. Works for any content format: LinkedIn posts, newsletters, essays, emails, blog posts, tweets, or any other published writing. Use this skill at the start of any project where the user wants the assistant to learn who they are and how they write before drafting new content. Trigger whenever the user says "build my voice", "learn my voice", "set up my content system", "onboard me", "train on my writing", "train on my posts", "I want Claude to sound like me", or drops a batch of writing samples into chat at the start of a project. Also trigger for first-time users who need a voice foundation before writing anything. Always produces two files (about-me.md and voice.md) saved into the project root.1 instalaciones en skills.sh0
- youtube-thumbnailcharlie947Generate a branded YouTube thumbnail from a video title. Uses a reference photo of the creator, high-CTR thumbnail principles, and brand colours to produce a ready-to-generate image prompt for Gemini. Use this skill whenever the user says "thumbnail", "youtube thumbnail", "build me a thumbnail", or wants a video cover image before writing the script. The thumbnail-first workflow mirrors the graphic-first approach for LinkedIn: sells the video before anyone hears a word of the script.1 instalaciones en skills.sh0