Content Repurposer
Reshapes one edited piece for LinkedIn, X, newsletter, and short video, each to its own length and structure spec, then runs check_lengths.py against the channel limits. Every version has to stand alone.
Part of The Content Engine, a seven skill pipeline. Get every file in one place.
Where it came from
- Source: Part of The Content Engine suite, seven skills built from the one agent per task workflow Mark Fershteyn described on the GTM AI Podcast with Coach K. Published as received.
- Frameworks applied: Per-channel length and structure specs, check_lengths.py validation, hook reuse across channels
Why it was chosen
Copy-pasting one post across channels reads like copy-paste. Writing to each channel's native shape from the same idea keeps the point and changes the format.
Known weakness, published as found: Channel limits change. Check the spec table against current platform rules before trusting it.
How to use it
- 1.Copy the SKILL.md text below, or download the raw file.
- 2.Create a folder named exactly content-repurposer in your agent's skills directory.
- 3.Save the file inside that folder as SKILL.md.
- 4.Ask the agent one of the trigger requests below.
- 5.Check the output against what you already know before it leaves your desk.
Ask it this
- repurpose this into a LinkedIn post and an X thread
- cut this for a short video script
- one piece, every channel
Do not use it for
- interview me about this topic
- cut this draft in half
The SKILL.md file
--- name: content-repurposer description: Turns one finished piece into channel-ready versions (LinkedIn post, X thread, newsletter section, short video script) and runs a script to check each against its channel limits. Use when the user says "repurpose this," "turn this into a LinkedIn post," "make an X thread from this," "cut this for video," "adapt this for other platforms," "one piece, every channel," or when the content-engine runs Step 5. Does not interview, draft, or edit the source piece. --- # Content Repurposer One job: reshape one finished piece for each channel. Same idea, native format. Each version must work alone. Someone who only sees the X thread should get the full point. ## STEP 1 (REQUIRED): Load inputs 1. Read `edited.md`. If it hasn't passed the editor, stop and run content-editor first. 2. Read `hooks.md` and take the recommended hook. Use the runner-up for the second channel so you test both. 3. Read `learnings.md` if present. Channel rules there override this skill. 4. Ask which channels the user wants if they didn't say. Default: all four below. ## STEP 2 (REQUIRED): Write each version to its spec | Channel | Length | Structure | Close | |---|---|---|---| | LinkedIn | 150 to 300 words | Hook, short lines, 1 to 2 sentences per paragraph, one list max | One question or challenge. Max 3 hashtags at the end | | X thread | 5 to 8 posts, each under 280 characters | Post 1 stands alone and holds the hook. One idea per post | Last post: the takeaway plus a link placeholder | | Newsletter section | 300 to 500 words | Hook, the story, the proof, one takeaway | One action the reader can take this week | | Video script (45 sec) | 100 to 130 words | Hook spoken in the first 3 seconds. One point only | One clear call to action | ### Example: one fact across channels **Source fact:** "Our 4 SDRs cut account research from 45 minutes to 8 with one Claude skill." - **LinkedIn line:** "45 minutes per account. Now 8.\nSame 4 SDRs. One Claude skill." - **X post:** "Our SDRs spent 45 min researching each account. One Claude skill got it to 8. Here's the skill:" - **Video open (spoken):** "My SDRs got 37 minutes back on every single account. Here's how." ## STEP 3 (REQUIRED): Run the length check Write all versions to `repurposed.md` using these exact headings, then run the script: ```markdown ## LinkedIn ## X Thread 1/ ... 2/ ... ## Newsletter ## Video Script ``` ```bash python scripts/check_lengths.py repurposed.md ``` Fix every FAIL and re-run until PASS. ## Output: `repurposed.md` All versions under the headings above, ready to copy and paste. Then one line to the user: "4 versions ready. LinkedIn uses hook #1, X uses hook #3." ## Edge cases - **Source is short** (under 250 words): skip the newsletter version and say why. - **User wants a channel not listed** (carousel, email, YouTube description): ask for one example they like, match its structure, and add a rule to `learnings.md` after the retro. - **A fact needs more context on one channel:** add context, never new facts.
Common questions
- What does the Content Repurposer skill do?
- Reshapes one edited piece for LinkedIn, X, newsletter, and short video, each to its own length and structure spec, then runs check_lengths.py against the channel limits. Every version has to stand alone.
- Where does the Content Repurposer skill come from?
- Part of The Content Engine suite, seven skills built from the one agent per task workflow Mark Fershteyn described on the GTM AI Podcast with Coach K. Published as received.. It was written by The Revenue AI Report against a 12 criterion quality rubric and graded in an independent scoring pass.
- Why was the Content Repurposer skill chosen for this library?
- Copy-pasting one post across channels reads like copy-paste. Writing to each channel's native shape from the same idea keeps the point and changes the format.
- When should the Content Repurposer skill not be used?
- Do not use it for: interview me about this topic Or: cut this draft in half
- How do I install the Content Repurposer SKILL.md file?
- Download the file, create a folder named exactly content-repurposer inside your agent's skills directory, and save the file inside it as SKILL.md. The agent loads it when a request matches the description.
Raw file: https://www.therevenueaireport.com/agent-skills/content-repurposer/SKILL.md. Plain-language skills with worked examples live in the Skills and Prompts library.
