agentleFS
sergebulaevsergebulaev/x-skills/skills/x-repurposer/SKILL.md

x-repurposer

Skill163 starsChanged 5 months agoMITView on GitHub

Repurpose existing content into a native X (Twitter) post or thread. Take a LinkedIn post, blog, YouTube script, or newsletter and rewrite it for X: re-hook for the no-fold first line, refit to 280 chars or a thread, strip off-platform artifacts, run the humanizer, publish via Publora on approval. Not for writing from scratch (use x-post-writer or x-thread-builder), not for auditing a draft (use x-humanizer --mode audit).

2 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Not for a blank-page draft (use x-post-writer for a tweet, x-thread-builder for a thread) and not for reviewing an already-X draft (use …

    line 19
  2. Distinctive:

    Strip off-platform artifacts: Remove "link in bio", "smash subscribe", "read more below", hashtag walls, @-handles that only exist …

    line 32
  3. Distinctive:

    Keep the source's claim and facts intact.

    line 49
  4. Distinctive:

    Never paste the source verbatim and trim.

    line 51
  5. Distinctive:

    Do not hard-sell the user's product.

    line 53
  6. Distinctive:

    ALL CAPS first line for intensity.

    line 59

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

X Repurposer

Turn something you already made into a tweet or thread that reads like it was born on X. Repurposing is not copy-paste. A post that killed on LinkedIn will die on X if you paste it: wrong hook, wrong length, wrong rhythm, and artifacts ("link in bio", hashtag walls) that scream off-platform.

This skill transforms, it does not generate. It reads your source, keeps the idea, and rebuilds the delivery for X.

When to use

  • "Turn this LinkedIn post into a tweet / thread"
  • "Repurpose my blog post / newsletter / YouTube script for X"
  • "This worked on Threads, adapt it for X"
  • "I have a rough idea in another format, make it native here"

Not for a blank-page draft (use x-post-writer for a tweet, x-thread-builder for a thread) and not for reviewing an already-X draft (use x-humanizer --mode audit).

How it works

Voice profile first (all drafts). If ../../references/voice-profile.md has filled: yes, load it and match the user's voice fingerprint, hard rules, and CTA/link style throughout. If it is not filled, mention once that x-humanizer --mode profile can learn their voice from a few posts, then proceed with the generic voice rules.

Story bank next. If ../../references/story-bank.md has filled: yes, load it and take every concrete detail (numbers, dates, named projects, positions) from there instead of asking mid-draft. Never invent a figure, a date or a client name that is not in the bank or supplied by the user in this conversation. If the bank has nothing that fits, ask the user, or say once that x-humanizer --mode interview fills it in 20 to 40 minutes. A draft with a plausible invented number is worse than a draft with none: one is vague, the other is a retraction.

  1. Take the source. Any format: a post, a paragraph, a script, a caption, a transcript, a bullet list, a link to read. Ask for the source and the goal (replies / reposts / likes / bookmarks) if not given.
  2. Extract the spine. Strip the source platform's shell and pull out the one claim, the one story, or the one number worth keeping. Most repurposing fails because it keeps the words instead of the point.
  3. Choose the container. One claim or number -> single tweet. A teach or a build -> thread (hand structure to x-thread-builder's shapes). A LinkedIn carousel or a listicle -> a thread, one slide per tweet, hook rebuilt. A long video -> a thread that delivers the payoff, not a summary.
  4. Re-hook for X. X has no "see more" fold: line one must land the whole punch. The source's hook almost never survives; write a new first line using a 2026 X formula (see ../../references/hook-formulas.md), picked by the goal.
  5. Refit the format. 280 chars on a standard account (emoji count as 2). One idea per tweet, line breaks as beats. Cut the source's connective tissue; X rewards compression.
  6. Strip off-platform artifacts. Remove "link in bio", "smash subscribe", "read more below", hashtag walls, @-handles that only exist elsewhere, and any "as I wrote on LinkedIn" throat-clearing. A repurposed post should not admit it was repurposed.
  7. Humanizer pass. Run the scrub: 2026 AI vocab by density, em dashes above the cap (at most one per tweet, never swapped for a period), stacked rule-of-three triads, generic openers and reveal bridges. Leave a single tweet's rhythm alone; on a thread never insert a punch tweet for variance. Keep the user's real numbers and named entities from the source. Canonical rules: x-humanizer V3.
  8. Approval card. Show: source -> X mapping (what became what), the container (tweet or N-tweet thread), formula used, char counts, primary goal.
  9. On approval. Publish via lib.publish(kind="post", draft_text=<approved>, target_url="https://x.com/compose/tweet", platforms=[<X_PLATFORM_ID>], scheduled_time=<iso_or_None>). Publora auto-splits an over-length draft into a numbered thread.

Native-fit rules (source -> X)

  • LinkedIn post -> X: cut ~40%. LinkedIn tolerates warm-up; X does not. The LinkedIn hook is usually too long; rewrite it.
  • Blog / newsletter -> X: pick the single most quotable claim as the hook, then thread the supporting beats. Do not summarize the whole piece.
  • YouTube script -> X: lead with the video's payoff, not its intro. "Here's what I found" beats "In this video".
  • Carousel / listicle -> thread: one item per tweet, each with its own micro-hook, not a wall.
  • Instagram / TikTok caption -> X: strip emoji density and hashtag blocks; X reads them as noise.

Hard rules

Global voice rules: see root SKILL.md Voice rules. Additional skill-specific rules:

  • Keep the source's claim and facts intact. Repurposing changes the delivery, never the meaning or the numbers.
  • The new first line must stop the scroll on its own. If it needs line two, rewrite it.
  • Never paste the source verbatim and trim. Rebuild the hook and rhythm from the spine.
  • One specific number where the source offers one. Keep it.
  • Do not hard-sell the user's product. One natural mention max.

Anti-patterns (skill will refuse)

  • Copy-pasting the source with light edits (that is not repurposing).
  • Keeping the source platform's artifacts ("link in bio", "smash subscribe", hashtag walls).
  • ALL CAPS first line for intensity. Carry it with word choice.
  • Em dashes above the cap (more than one in a tweet), or an em dash swapped for a period.
  • "The result?" / "Here's what" reveal bridges and staccato stacks added during the rewrite.
  • Rule-of-three lists without specifics.
  • "leverage", "fundamentally", "game-changer", "deep dive".
  • An external link in the tweet body (offer a reply).
  • Meta throat-clearing ("I originally posted this on...").

Resources

  • ../../references/hook-formulas.md - the 11 X formula skeletons to re-hook with
  • ../../references/algorithm-heuristics.md - 2026 X ranking rules (length, timing, signals)

Related skills

  • x-post-writer - write a fresh tweet from scratch
  • x-thread-builder - structure a multi-tweet thread (repurposer hands long builds here)
  • x-humanizer - scrub AI tells, plus --mode audit to review the result

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.