agentsclimarketplace

Cross platform reformatter

Skill SkillMedev/skills/skills/cross-platform-reformatter

The open Skill Me catalog — every hosted skill as a portable, MIT-licensed SKILL.md

Install
npx -y skills add SkillMedev/skills --skill cross-platform-reformatter

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 4 stars4 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Re-expresses one finished piece of content as the native-equivalent post on each target channel, holding the core idea constant while flexing length, structure, register, and conventions per platform. Use when you have a single written post, article, script, or message and need the same idea posted natively on LinkedIn, X, Instagram, TikTok, YouTube Shorts, or a newsletter. Do NOT use when fanning one long-form asset out into different asset types (clip, quote card, blog) - use content-repurposing instead; do NOT use when writing one fresh caption from a topic - use social-caption-writer instead.

SKILL.md

5.4 KB, ~1.1k tokens by cl100k_base, as published. Nobody here has run it

Cross-Platform Reformatter

Take one existing piece and ship the same idea as a native post on each requested channel - not the same text with hashtags swapped.

Workflow

  1. Extract the core: pull the single transferable idea plus its proof (the stat, story, or takeaway). This stays constant across every version; everything else is rebuilt around it.
  2. Confirm the target channels. Reformat only the channels the user named; do not invent a full distribution stack. If they named none, ask which channels.
  3. Rebuild - do not truncate - for each target, in its native grammar:
    • LinkedIn: text-first, ~1300-2000 chars, short lines with white space, professional-but-human, one clear insight.
    • X: a tight single post under 280, or a thread where each post stands alone; punchy, no corporate tone.
    • Instagram: caption ~125-150 chars or a short narrative; the image/Reel carries the weight.
    • TikTok: a spoken script with a verbal hook in the first two seconds; conversational, written to be said aloud.
    • YouTube Shorts / Reels: the same script logic with on-screen text beats.
    • Newsletter: longest form; keep the nuance the social cuts drop.
  4. Apply native conventions per channel: hashtags 3-5 on Instagram, 1-2 on LinkedIn/X, a couple of discovery tags at most on TikTok; use features as intended (carousels/Reels on IG, document posts and polls on LinkedIn, threads and quote-posts on X); tune emoji density to the channel.
  5. Hold voice, shift register: keep signature phrasing so the brand stays recognizable; go more formal on LinkedIn, looser on TikTok and X; drop jargon that does not travel to a casual feed.
  6. If output feeds a calendar, note sequencing: long-form first (the anchor), then the atomized versions pointing back to it, staggered over days rather than dumped at once.
  7. Label each version with its target channel and format on delivery.

Worked example

Source: a newsletter section arguing that most A/B tests are called too early, with the proof point "tests stopped at 50 conversions flip their winner a third of the time."

Bad (truncated, not rebuilt) - X:

Most A/B tests are called too early. Teams stop tests when they see an early leader, but tests stopped at 50 conversions flip their winner a third of the time. You need to pre-commit to a sample size and… (1/4)

This is the newsletter paragraph chopped at 280 characters with a thread number stapled on - the first post doesn't stand alone, the hook is buried, and the register is still newsletter-formal.

Good - X:

Your A/B test winner is probably fake.

Tests stopped at 50 conversions flip their winner a third of the time.

Pick the sample size before you launch, or you're just reading tea leaves.

Good - LinkedIn (same core, rebuilt):

We killed a "winning" variant last quarter.

It had beaten control for two straight weeks. Then we let the test run to the pre-set sample size - and the result flipped.

That's not bad luck. Tests stopped at ~50 conversions flip their winner about a third of the time.

The fix is boring and unpopular: decide the sample size before launch, and don't peek.

What's the earliest you've been burned by calling a test?

Same idea, same proof point, two different structures: X leads with the punch and stands alone; LinkedIn opens with a story, breathes with white space, and ends with a conversation prompt.

Deliverable

Produce a channel-labeled post set containing, for each requested channel:

  1. The rebuilt post in that channel's native structure, length, and register - script form (with hook timing and on-screen beats) for TikTok/Shorts, text form for the rest.
  2. The conventions applied - hashtags at the channel's norm, feature notes (carousel, poll, thread) where relevant.
  3. A one-line core statement at the top of the set, so anyone can verify every version carries the same idea and proof.
  4. Sequencing notes (anchor first, atomized versions staggered and linking back) if the set feeds a calendar.

Quality bar

  • Every version reads as if written for that channel first, not resized from another.
  • The core idea and its proof survive intact in each version.
  • Lengths, hashtag counts, and structure match the channel's real norms.
  • No version is the source text with only hashtags or emoji changed.

Do NOT

  • Do not truncate the long version to fit a short one - a shorter post needs a different structure, not fewer words.
  • Do not post the same text verbatim across channels.
  • Do not produce versions for channels the user did not ask for.
  • Do not force a piece onto a channel where it will flop; if it genuinely fits only one channel (a niche technical thread, a platform-specific trend), say so instead of shipping a weak version.
  • Do not turn one source into a spread of new asset types (clip, quote card, blog paragraph) - that is content-repurposing's job.

Gives 0 of the 12 instructions most docs writing skills give in ~1.1k tokens

Counted across 1,637 of the 3,044 authors here whose files we hold, read 2026-08-06

  • announce the skill at startin 54 of 1637, across 21 files
  • convert legacy doc files before editingin 45 of 1637, across 7 files
  • predict questions readers might askin 42 of 1637, across 3 files
  • Generate clarifying questions for initial contextin 42 of 1637, across 3 files
  • Create document scaffold with placeholder textin 42 of 1637, across 3 files
  • Brainstorm content options for each sectionin 42 of 1637, across 3 files
  • Test document with fresh context-less instancein 42 of 1637, across 3 files
  • ask interview questions one at a timein 42 of 1637, across 26 files
  • include exact file paths in every taskin 42 of 1637, across 15 files
  • Apply surgical edits during refinementin 41 of 1637, across 2 files
  • Offer structured workflow or freeformin 40 of 1637, across 1 file
  • Ask for document meta-contextin 40 of 1637, across 1 file

Said here and by no other author read

  • extract the single transferable idea and proof
  • ask for target channels if none are named
  • rebuild content natively for each target channel
  • hold voice while shifting register per channel
  • label each version with its target channel
  • keep the core idea intact across every version

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.