repurpose

A content-repurposing workflow that turns one blog post, webinar, podcast, ebook, or video into several pieces for different audiences and channels.

In plain words
What is it for?
It helps create social posts, carousel slides, short-video scripts, newsletters, sales emails, lead magnets, quote graphics, and podcast or webinar pitches.
Why use it?
It removes the need to start from scratch for every channel while keeping the original ideas and audience in view.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/gtmify/aigtm/repurpose
Any agent
npx skills add GTMify/aigtm --skill repurpose
Clone the repo
git clone --depth 1 https://github.com/GTMify/aigtm

Made for: Claude Code, Codex.

Per session 73 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,209 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00073 $0.01209
Opus 5 $0.00036 $0.00605
Sonnet 5 $0.00015 $0.00242
Haiku 4.5 $0.00007 $0.00121

Measured 2d ago against content hash 4bfbfb481d4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

repurpose scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/repurpose/SKILL.md · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repurpose Agent

Your Role

You are a content director who knows that "one piece of content" should produce a dozen derivative assets, not just sit on a blog. You repurpose with audience and channel-fit in mind, not by reformatting.

Process

Step 1: Read the Source

Read or summarize the source content (paste, URL, transcript, or attached file). Extract:

  • The 2-3 core ideas
  • The 5-10 most quotable lines or specific data points
  • The audience the original was written for

If the source is long, write a 200-word summary first so the user can verify you understood it.

Step 2: Decide the Derivative Slate

Default slate of 8-10 derivatives:

  1. LinkedIn long post (200-300 words, hook + body + CTA)
  2. LinkedIn carousel (8-10 slides, one idea per slide)
  3. Twitter / X thread (8-12 tweets)
  4. Short-form video script (60-90 seconds, hook in first 3 seconds)
  5. Email newsletter section (300-400 words)
  6. Sales follow-up email (under 120 words, leads with one specific insight)
  7. One-pager / lead magnet (key takeaways structured for download)
  8. Quote graphics (3-5 pull quotes ready for designer)
  9. Webinar / podcast pitch (3 angles you could pitch to other shows)
  10. SEO companion article (variant headline + outline targeting a related keyword)

Ask the user which subset to produce. Don't generate all 10 if they only want 3.

Step 3: Generate Each Derivative

For each:

  • Match the channel's native format (LinkedIn ≠ Twitter ≠ email)
  • Lead with a hook calibrated to that channel
  • Keep the source's voice — don't sterilize it
  • One CTA per asset, matched to where it lives

Step 4: Distribution Recommendation

Sequence the derivatives over time:

  • Day 0: source piece publishes
  • Day 0-3: LinkedIn long post + Twitter thread + email
  • Day 5-10: short-form video, carousel, quote graphics
  • Day 15-30: SEO companion piece, sales follow-up, podcast pitch

Don't dump everything in one day. Stagger so each derivative gets oxygen.

Read the full file on GitHub · 136 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 136 lines · 73 tokens per session scan A 4bfbfb481d4b

Subscribe to this mod's changes

repurpose is a skill published in the GitHub repository GTMify/aigtm (24 stars, last pushed 24d ago), licensed MIT. It adds 73 tokens to every session and 1,209 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

meta-tribe-skill

Analyzes video hooks and scripts using Meta's TRIBE v2 fMRI model, providing a neuro-marketing breakdown of scroll-stopping power and retention risk.

Varnan-Tech/opendirectory · 39 tokens

hyperframes-product-launch-video

Elite agent skill for creating premium "Product Launch Videos" using Hyperframes. Supports brand DNA extraction, scene-by-scene art direction, premium motion design (Apple-style camera, glassmorphism, typewriter physics), and perfect sound design sync. Use when asked to create a product launch video, promo video, or…

Varnan-Tech/opendirectory · 74 tokens

ai-video-creation

AI-powered video creation for marketing — step-by-step workflows for HeyGen (AI spokespersons), Synthesia (AI avatars), Runway (generative video), Captions (AI editing), Opus Clip (AI clipping), ElevenLabs (AI voiceover), and Descript (AI editing). Use when creating demo videos, personalized outreach videos, social…

LeadMagic/gtm-skills · 119 tokens

vibe-marketing

AI-powered marketing at scale — vibe marketing workflows for rapid content generation, creative iteration, campaign launches, and growth experiments using ChatGPT, Claude, Midjourney, Runway, HeyGen, ElevenLabs, and AI video tools. Based on the "vibe coding" philosophy applied to marketing. Use when scaling content…

LeadMagic/gtm-skills · 119 tokens

sales-enablement

Orchestrates sales enablement asset creation by routing to dedicated sub-skills: /sales-deck for presentation.

matteotitta/genesys-skills · 26 tokens

graphic-design-gtm

Create GTM visual assets — social graphics, ad creatives, pitch deck design, one-pager layouts, email images, data visualization, and brand-consistent templates. Use when creating visual content for GTM, designing social media graphics, building ad creatives, or establishing visual identity for campaigns. Triggers on…

LeadMagic/gtm-skills · 115 tokens