agentleFS
JakeschincariolJakeschincariol/x-agent-skill/skills/x-repurpose/SKILL.md

x-repurpose

Skill4 starsChanged 45 days agoMITView on GitHub

Turn one long asset - a YouTube video, podcast, newsletter, blog post, transcript, LinkedIn post or client call - into a week of X posts and one thread. Use when the user says "repurpose this", "turn this into tweets", "I have a video/newsletter/transcript", or pastes a long piece of content and wants it on X.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 1

    1. swayamdhawan/x-agent★ 0100% same

    Edited · 0

    None found.

    Wrote their own version · 1

    1. belzoralolbtw/x-agent-skill★ 0same name

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository10 other files it gives its agents.

The file

Files
SKILL.md

x-repurpose

One good long asset holds five to eight X posts and a thread. Most people post one link to it and throw the rest away.

Input

A transcript, article, newsletter, script, or call summary. If the user gives a YouTube URL and the session has a transcript tool, use it; otherwise ask them to paste the text. Read the whole thing before extracting anything.

Extract, do not summarise

A summary is not a post. Nobody on X wants the summary. Pull out the things that stand alone:

pullwhat it isbecomes
Claimsevery sentence that would start an argumenta #1 Contrarian or #21 One-Liner
Numbersevery figure, cost, duration, percentagea #13 Statistic or #9 Time Anchor
Storiesa person, a scene, a costa #3 Cost Confession or a short thread
Mechanisms"the way this works is..."a thread, one step per post
Mistakesanything that went wronga #17 The Regret
Linesa sentence already quotable as-isa post on its own, nearly verbatim

List what you found, with counts, before writing anything. If the asset yields fewer than four items, it is thin, and posts squeezed from it will be thin too. Say so.

Then build the week

Each extract becomes one post, and each one has to stand completely alone. The reader has not seen the video and never will. Never write "as I said in my latest video". The post is the thing.

  • Assign a hook formula from ../x-post/hooks.json to each, and vary them. Six posts from one source in the same shape reads as a content mill.
  • The strongest claim goes first in the week. The mechanism becomes the thread, midweek. The link to the original goes in a reply under the thread's last post, if anywhere.
  • From a LinkedIn post: cut it to the one line that carries it. LinkedIn rewards the long version; X rewards the sentence that survives alone.

Output

SOURCE: "Why we killed discovery calls" (18 min, 3,400 words)

FOUND  4 claims, 6 numbers, 2 stories, 3 mechanisms, 1 mistake, 5 lines

WEEK
MON  #1  Contrarian    Discovery calls are a tax you pay for a bad website.
TUE  #9  Time Anchor   We got 6 hours a week back by deleting one calendar link.
WED  THREAD            The 4-question form that replaced the call, one question per post.
THU  #21 One-Liner     Nobody books a call to learn your price.
FRI  #3  Cost          $9,000 of pipeline, lost to a "quick call" that never happened.

Say "write Monday" and I will draft it.

Then draft on request, one at a time, each through /x-post (or /x-thread) and /x-human. Do not dump six finished posts at once: they will all sound the same, and the user will edit none of them.

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.