agentleFS
styfinitystyfinity/linkedin-engine/skills/linkedin-repurposer/SKILL.md

linkedin-repurposer

Skill9 starsChanged 4 months agoMITView on GitHub

Turn one source asset into a week of content - five post stubs, a carousel outline, and a DM nudge. Use when you have a transcript, a doc, a win, or a long post and want a week of content from it.

9 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

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Read the source. Pull the 5 strongest ideas: the ones that prove a competence the buyer pays for, not the ones that are merely interesting.

    line 16
  2. Distinctive:

    Every piece must prove a competence the buyer buys.

    line 31

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “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

LinkedIn Repurposer

One good asset is a week of content. This skill mines a single source for the five strongest ideas and shapes each into something the buyer reads.

Inputs

  • The source asset (a call transcript, a doc, a win, a long post): $ARGUMENTS
  • The brief (lanes, voice profile, offer, pains) loads automatically.

Do this

  1. Read the source. Pull the 5 strongest ideas: the ones that prove a competence the buyer pays for, not the ones that are merely interesting.
  2. Map each idea to a content lane from the brief and a hook formula (contrarian take, before/after, list, story open loop, hard number).
  3. Draft a post stub for each: lane, hook, one-line angle. Stub only, not the full post.
  4. Pull the single best idea into a carousel outline (title slide plus 5 to 7 slide lines).
  5. Pull one idea into a short DM nudge that opens a conversation off the back of the asset.
  6. Anonymise as you go: keep the real numbers and outcomes, drop every name (people, companies, clients). A number stays "a client" or "an operator".

Output

  • Five post stubs, each labelled with its lane, hook formula, and angle.
  • One carousel outline (title plus slide lines).
  • One DM nudge (two short lines). End with a one-line note: run /linkedin-humanizer on any stub before drafting it full, and hand the DM nudge to /linkedin-first-dm if it targets a specific prospect.

Rules

  • Anonymise everything. No real person, company, or client names. Keep the numbers, drop the source.
  • Every piece must prove a competence the buyer buys. Cut the interesting-but-unsellable.
  • Stubs and outlines only. Claude drafts, the operator approves and posts.
  • No em-dashes.

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.