Systems Lab

Agent skill

content-repurposer

Take a long-form asset (blog post, webinar, podcast, LinkedIn article) and generate 10+ derivative pieces ready to publish: LinkedIn posts, tweets/X threads, email snippets, short-form hooks, and pull-quotes.

dormantSelf-containedInstructions only781 words

Filed under Content and SEO.

From edupegoretti/fluidz-skills · 116 skills · 0 · pushed 2026-03-11

What it does when it runs

Take a long-form asset (blog post, webinar, podcast, LinkedIn article) and generate 10+ derivative pieces ready to publish: LinkedIn posts, tweets/X threads, email snippets, short-form hooks, and pull-quotes. Pure reasoning skill — no scripts, no scraping. Use when a founder or marketer has created one piece of content and needs to distribute it across multiple channels without writing each variant from scratch.

Read from the skill and the 1 file bundled beside it. A skill’s own description is written to be selected by an agent, so it describes the job and not the dependencies.

Keys and connectors you must supply
None found.
Hosts it reaches
No third-party host appears in the skill or its bundled files.
Tool permissions it declares
No allowed-tools in the frontmatter. It only issues instructions, so there is nothing to bound.
Actions present in the files
None. Instructions only.

Ask about content-repurposer

Opens your assistant with this page's verified links already in the prompt.

Is this safe to install?ClaudeChatGPT
Adapt it to my stackClaudeChatGPT
What else do I need for it to workClaudeChatGPT
Rather ask a human? Talk to Cheetah
git clone --depth 1 --filter=blob:none --sparse https://github.com/edupegoretti/fluidz-skills.git /tmp/fluidz-skills
git -C /tmp/fluidz-skills sparse-checkout set "skills/composites/content-repurposer"
mkdir -p ~/.claude/skills/content-repurposer
cp -R "/tmp/fluidz-skills/skills/composites/content-repurposer/." ~/.claude/skills/content-repurposer/

Picked up without a restart. A project skill of the same name is shadowed by your personal one. For one repository only, swap ~/.claude/skills for .claude/skills. Claude Code docs ↗

The folder is the same in every client that implements the format — 46 of them — so if yours is not above, only the destination changes.

Reproduced in full from edupegoretti/fluidz-skills/blob/a2cf697e2e8ec2ea517d85496e2d5c7f5dc44cd3/skills/composites/content-repurposer/SKILL.md, which is licensed MIT (repository). 781 words, 26 headings.

Content Repurposer

Pure reasoning skill. Takes one long-form asset and fans it out into 10+ channel-specific derivative pieces — all aligned to the author's brand voice.

When to Use

  • "Turn this blog post into LinkedIn content"
  • "Repurpose this webinar into tweets and an email"
  • "I have a podcast episode, help me get more mileage from it"
  • "Turn this into posts I can schedule for the next two weeks"

Phase 0: Intake

Ask all questions at once, organized clearly. Keep it fast — this skill should feel frictionless.

Source Content

  1. Paste the content OR share the URL (blog post, LinkedIn article, transcript, etc.)
  2. What is the core insight or argument of this piece? (Summarize in 1-2 sentences)

Author Context

  1. Who is the author? (Title, company, area of expertise)
  2. What is their tone? (Casual/direct, professional, storytelling, data-driven — or share a sample post)
  3. Who is the audience? (ICP title, industry, stage)

Output Preferences

  1. Which channels do you want output for? (LinkedIn, Twitter/X, email snippet, or all three — default: all)
  2. Any specific hooks, stats, or quotes from the piece that must be included?

Phase 1: Extract Source Intelligence

Before writing any variants, extract the following from the source content:

  • Core thesis — The single most important claim or insight
  • Top 3 supporting points — Evidence, examples, or sub-arguments
  • Best data/stats — Numbers, percentages, benchmarks
  • Best quotes — 2-3 pull-quote candidates
  • Contrarian angle — What conventional wisdom does this challenge?
  • Specific examples — Named companies, people, tools, events
  • Emotional hook — The frustration, aspiration, or fear this piece speaks to

Phase 2: Generate Derivative Pieces

LinkedIn Posts (generate 4-5 variants)

TypeStructureLength
Insight postHook → 3 supporting points → CTA150-300 words
ListicleHook → numbered list (5-10 items) → close200-350 words
Contrarian takeUnpopular opinion → why → evidence → implication100-200 words
Personal storySituation → problem → turning point → lesson150-250 words
Data postStat hook → context → implication → question80-150 words

LinkedIn formatting rules:

  • First line must hook without finishing the sentence (forces "see more")
  • Use line breaks liberally — one idea per line for scanability
  • No bullet points in first 3 lines
  • End with a question or call to reflect — not a CTA to buy
  • Emojis optional — match the author's existing style

Twitter/X Thread (generate 1-2 threads)

  • Thread length: 5-8 tweets
  • Tweet 1: The payoff, not the setup. State the insight directly.
  • Tweets 2-6: One supporting point per tweet. Short, punchy.
  • Tweet 7: Callback to tweet 1 with reframed conclusion
  • Tweet 8 (optional): Soft CTA — "I wrote about this in depth: [link]"

Each tweet: max 240 chars. No jargon. End threads with the strongest line.

Email Snippet (generate 1-2 variants)

Format for use in newsletters, nurture sequences, or cold outreach PS lines.

TypeLengthUse Case
Newsletter blurb80-120 wordsWeekly digest, newsletter intro
PS line20-40 wordsCold email personalization layer

Short-Form Hooks (generate 5-8 standalone hooks)

One-liner openings that work across contexts. Can be used to A/B test posts or as standalone comments.

Examples of good hooks:

  • "Most [role]s get [topic] completely backwards."
  • "The [thing everyone does] is why [bad outcome]."
  • "[Number] years ago, [company/person] did [thing]. Here's what happened."
  • "Unpopular opinion: [claim]."
  • "The real reason [common problem] happens isn't [assumed cause]."

Pull-Quotes (generate 3-5)

Shareable quotes formatted for screenshots or image posts. Should stand alone without needing context.

Phase 3: Review & Deliver

Present outputs organized by channel:

## Source Summary
Core thesis: [1 sentence]
Top 3 points: [bullets]

## LinkedIn Posts
### Post 1 — [Type]
[Full post text]

### Post 2 — [Type]
[Full post text]

...

## Twitter/X Thread
Tweet 1: [text]
Tweet 2: [text]
...

## Email Snippets
### Newsletter Blurb
[text]

### PS Line Options
- [option 1]
- [option 2]

## Short-Form Hooks
1. [hook]
2. [hook]
...

## Pull-Quotes
> "[quote]"
> "[quote]"

Iteration Rules

  • User picks their 2-3 favorite variants → refine only those
  • Max 2 rounds of revision per channel
  • If the author has existing posts to match, ask them to paste 1-2 examples before generating

Tools Required

None. Pure reasoning. Works with any LLM agent.

Files bundled with it

These load only when the skill asks for them, so they cost nothing until it runs.

Other skills for the same job

Different authors, same problem. Matched on the words in the skill name, across every library in the catalogue except this one.

Need help setting it up?

This page tells you what content-repurposer does and what it needs. Cheetah builds the agent setup it runs inside: data, CRM, sequencing and the guardrails.

Book a call →

The directory stays free. There is nothing gated behind this.