repurpose-master

A workflow for turning one long podcast, livestream, video, or article into many short-form content ideas. It finds self-contained moments and describes how to adapt each one for different platforms.

In plain words
What is it for?
Finding quotes, lessons, opinions, stories, questions, and demonstrations, then mapping each to a platform, opening hook, format, and source timestamp or idea.
Why use it?
It helps avoid publishing a long piece once and leaving most of its useful ideas unused. It also filters out clips that need too much surrounding context.

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/moses607/socialforge/repurpose-master
Any agent
npx skills add moses607/socialforge --skill repurpose-master
Clone the repo
git clone --depth 1 https://github.com/moses607/socialforge

Made for: Claude Code, Codex.

Per session 107 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,200 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 $0.00107 $0.01200
Opus 5 $0.00053 $0.00600
Sonnet 5 $0.00021 $0.00240
Haiku 4.5 $0.00011 $0.00120

Measured yesterday against content hash 49e659a961b7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

repurpose-master 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 yesterday.

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-master/SKILL.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repurpose Master

One deliberate long asset contains 30-50 pieces of short-form content — most creators publish it once and waste 95% of the value. The unlock is atomization: every quotable line, mini-lesson, hot take, story, and Q&A is a standalone clip with its own hook. You are not slicing the video into equal chunks; you are hunting the moments that already spike, then rebuilding each as a self-contained piece with a hook that assumes zero context. One idea per clip is non-negotiable — a clip that tries to say two things gets swiped on both.

1. Mine the asset for atomic moments

  1. Pass through the full asset and timestamp every candidate: a quotable line, a counterintuitive claim, a mini-framework, a personal story, a sharp Q&A exchange, a strong reaction or laugh.
  2. Tag each by type — QUOTE, LESSON, HOT-TAKE, STORY, Q&A, DEMO — because type dictates format and platform.
  3. Score for standalone strength: does it make sense with no setup? Does it provoke, teach, or surprise in under 3s? Kill anything that needs the surrounding 5 minutes.
  4. Target 30+ from a 45-60 min asset. Dense assets yield more; don't force weak cuts to hit a number.

2. Spec each cut

  1. Assign platform by fit: hot takes and quotes → TikTok/Reels/Shorts; frameworks and lessons → carousel + LinkedIn text; stories → Reels + Shorts; Q&A → Shorts + tweet.
  2. Write a fresh hook per clip — the source's opening line is almost never the hook. The strongest sentence usually sits 10-20s into the moment; open there.
  3. Set length, aspect ratio (9:16 vertical, 1:1 square, 16:9 native), and on-screen text keyword.
  4. One asset feeds many formats: the same 40s moment becomes a vertical clip, a quote-card image, a carousel slide, and a text post — four pieces, one source.

3. Batch workflow

  1. Mine once, spec all 30+ before editing anything — context-switching between watching and editing is the time sink.
  2. Group by format and cut in batches (all vertical clips, then all quote cards, then all carousels).
  3. Stagger the calendar: never publish two derivatives of the same moment on the same platform same day.
  4. Track which derivatives outperform, then commission more long assets around those angles.

Read the full file on GitHub · 65 lines

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. yesterday First seen · 65 lines · 107 tokens per session scan A 49e659a961b7

Subscribe to this mod's changes

repurpose-master is a skill published in the GitHub repository moses607/socialforge (2 stars, last pushed 1mo ago), licensed MIT. It adds 107 tokens to every session and 1,200 once invoked, about $0.0005 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 2026-08-31.

Related

Other skills, from other repositories

educational-content-and-how-to

The teach-to-grow content type -- pick a genuinely useful topic, teach ONE thing completely, structure it as a clear lesson, keep it accurate, and route it to the right format. Use when someone wants to teach their audience, make a how-to / tutorial / step-by-step / explainer / myth-buster, build authority content, or…

social-media-skills/skills · 232 tokens

interactive-content

The participation content format — polls, quizzes, Q&A / scoped AMAs, this-or-that, emoji sliders, question boxes, caption-this, Add-Yours, and challenges. Use when someone wants interactive posts, Story stickers, a poll/quiz/AMA, a challenge or contest, or to turn passive scrollers into participants. Low-friction…

social-media-skills/skills · 206 tokens

carousel-writer

Use to write a carousel — a swipeable multi-slide post (Instagram carousel, LinkedIn document/PDF carousel, or TikTok photo carousel) — one of the highest-save, highest-dwell formats. Run when the user says "write a carousel," "carousel post," "slides for X," "LinkedIn document/PDF post," "swipe post," "turn this into…

social-media-skills/skills · 172 tokens

creator-monetization

Creator monetization — build a diversified revenue portfolio from an audience: memberships, products, brand deals, platform payouts. Use when someone wants to "make money as a creator," "monetize my audience," "start a membership/community," "sell a course/digital product," "get brand deals / set my rates," or build…

social-media-skills/skills · 211 tokens

lead-magnets-and-funnels

Lead magnets and funnels — design offers that turn social traffic into subscribers, leads, and customers. Use when someone wants to "create a lead magnet," "build a funnel," "design a freebie/opt-in," "make a quiz/calculator/template to grow my list," or turn social traffic into qualified leads and customers. Designs…

social-media-skills/skills · 200 tokens

x-thread-builder

Build a long-form X (Twitter) thread (tweetstorm) using a 2026 thread formula (listicle-thread, story thread, curiosity-gap opener, how-I teardown), picked by goal (bookmarks, likes, reposts, replies). Structures tweet 1 as a promise plus open loop, paces one beat per tweet, and closes for the repost. Publishes via…

sergebulaev/x-skills · 123 tokens