agentleFS
styfinitystyfinity/claude-marketing-department/skills/repurpose/SKILL.md

repurpose

Skill6 starsChanged 4 months agoMITView on GitHub

Takes one strong asset and produces ten platform-native derivatives — text posts, emails, a carousel outline, a short-video script, and shorts hooks — each rebuilt from the idea up, not cut down. Use when good material sits in one format while other channels go hungry.

21 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use email, strategy and 2 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • OpenAISkill

    email

    Email sending integration guidance — Resend (native Vercel Marketplace) with React Email templates. Covers API setup, transactional emails, domain verification, and template patterns. Use when sending emails from a Vercel-deployed application.

    Also in 4 projects that use this

  • EpistatesSkill

    strategy

    Plan weekly or monthly X content strategy. Use when the user wants to plan their content calendar, set growth goals, build a content pipeline, or think strategically about their X presence.

    Also in 3 projects that use this

  • AnthropicSkill

    analyze

    Answer data questions -- from quick lookups to full analyses. Use when looking up a single metric, investigating what's driving a trend or drop, comparing segments over time, or preparing a formal data report for stakeholders.

    Also in 3 projects that use this

  • VercelSkill

    setup

    Set up Vercel CLI and project configuration. Use when the user says "set up Vercel", "configure Vercel", "link to Vercel", or "vercel init".

    Also in 3 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 18 edited versions we read keep these.

  • 1

    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:

    All ten derivatives ready to publish, labelled by platform and source idea, plus the drop schedule.

    line 29

“Common” is measured: kept by at least 6 in 10 of the 18 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

Repurpose — one asset, ten natives

Repurposing dies when it means shortening: a blog paragraph pasted onto social, an article read to camera. Every platform has its own physics — hook expectations, rhythm, length, CTA culture — and an idea only travels if it is rebuilt for the destination. Extract the ideas first, then write each derivative as if it were born there.

Inputs

  • The source asset, pasted or as a file path: $ARGUMENTS
  • From marketing-brief.md if present: channels & funnel (which platforms matter and in what order), the voice section, the language bank, and the banned-phrases list.

Do this

  1. Mine the idea inventory. List every distinct claim, story, number, method, and contrarian take in the asset. A strong asset carries five to ten; number them.
  2. Rank the ideas by standalone strength — does each work without the surrounding context? The best derivative usually comes from an idea buried in the middle, not from the asset's own headline.
  3. Map ideas to the set of ten, adapting platforms to the brief's channels:
    • 3 text posts — one story-led, one list-led, one contrarian; fresh hooks, feed rhythm, whitespace.
    • 2 emails — one pure value, one value-then-pitch; subject lines plus full body.
    • 1 carousel outline — slide-by-slide text, one idea per slide, payoff on the final slide.
    • 1 short-video script — spoken lines plus shot notes, 30–45 seconds.
    • 3 shorts hooks — first-three-seconds openers, banked for future videos.
  4. Rebuild each derivative from its idea up, in the brief's voice, phrased from the language bank. If a sentence appears in two formats, one of them is not finished. Run weak first lines through /marketing:hook-factory.
  5. Match each CTA to platform culture: comment or reply on social, click in email, follow on video. One CTA per derivative.
  6. Sequence the drop so channels reinforce rather than repeat — the same idea should not hit the same audience twice inside 48 hours.

Output

All ten derivatives ready to publish, labelled by platform and source idea, plus the drop schedule. Flag any idea strong enough to deserve its own full asset later.

Rules

  • Reshape, never shorten. A derivative that reads like an excerpt goes back in the shop.
  • One idea per derivative. Cramming the whole asset into a post is how repurposing earned its bad name.
  • Facts stay identical across every version — numbers do not drift between formats, and no derivative gains a claim the source cannot back.
  • Native register wins: what sounds right in an email sounds strange on social, and both are correct.

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.