repurpose-longform

repurpose-longform is a skill for Claude Code from JackVitick/socialync-mcp. It costs 58 tokens per session (651 once invoked), scanned A, original, MIT.

A tool for turning a transcript, article, or long video into draft posts suited to Instagram, TikTok, YouTube, X, LinkedIn, Threads, or Bluesky in Socialync. It creates drafts and queues them, but does not post directly to social platforms.

In plain words
What is it for?
Use it to extract one to five distinct ideas from long-form content, write platform-specific captions, and prepare posts for scheduling. Video platforms also require a media ID or public video URL.
Why use it?
It removes the need to rewrite the same source separately for each platform while keeping each draft within that platform’s format and length limits.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the socialync plugin — 3 skills, 1 MCP server shipped together

Good fit Use it to extract one to five distinct ideas from long-form content, write platform-specific captions, and prepare posts for scheduling. Video platforms also require a media ID or public video URL.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jackvitick/socialync-mcp/repurpose-longform
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.

Any agent
npx skills add JackVitick/socialync-mcp --skill repurpose-longform
Clone the repo
git clone --depth 1 https://github.com/JackVitick/socialync-mcp

Made for: Claude Code.

Or install socialync, the plugin that ships this one along with the rest of its 3 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for repurpose-longform

README.md
[![agentmods](https://agentmods.dev/badge/skills/jackvitick/socialync-mcp/repurpose-longform.svg)](https://agentmods.dev/skills/jackvitick/socialync-mcp/repurpose-longform)
Your own site
<a href="https://agentmods.dev/skills/jackvitick/socialync-mcp/repurpose-longform"><img src="https://agentmods.dev/badge/skills/jackvitick/socialync-mcp/repurpose-longform.svg" alt="Measured on agentmods" height="20"></a>
Per session 58 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 651 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00058 $0.00651
Opus 5 $0.00029 $0.00326
Sonnet 5 $0.00012 $0.00130
Haiku 4.5 $0.00006 $0.00065

Measured 6d ago against content hash 52e3e5c1cdc8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

repurpose-longform 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 6d 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-longform/SKILL.md · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repurpose long-form into Socialync drafts

Use Socialync MCP tools. Do not post directly to social platforms.

Setup

  1. list_profiles for profileId.
  2. list_connections so you only target connected platforms.
  3. check_quota before generating a batch. Free accounts have 5 posts/month (one cross-post = one post) and no AI generation. Paid plans allow 10 AI-created posts per day per brand.

How to split the work

Read the source (transcript, article, notes). Extract 1 to 5 distinct posts, not 8 clones of the same line.

For each post, write a native caption:

  • X / Bluesky: one idea, under the hard character cap.
  • Threads: conversational, max 5 links, under 500.
  • LinkedIn: the point in the first 210 characters, then the rest.
  • Instagram: first 125 characters do the work; hashtags only if the user wants them.
  • TikTok / YouTube: video only, so these need a mediaId from list_media or a public video URL. Hook in the first line. YouTube needs a title under 60 characters plus a description.
  • Facebook: short; long captions underperform.

If generate_content is available on the plan, use it for a first pass, then edit to match the user's voice from the source. On the free plan it returns a plan error: write the captions yourself.

Queue, do not publish

  1. Upload or pick media (create_media_upload / finalize_media_upload / list_media) when the user provided files or a public video URL. You cannot receive a video file in chat; the user uploads it in Socialync.
  2. validate_post per post.
  3. create_post_draft (text or images, immediate) or schedule_post_draft (future time, may carry one video) per post, or per cross-post group if they asked to publish the same asset everywhere.
  4. Show a table: platform, caption, proposed time, quota spend.
  5. Stop. The user approves drafts in their Socialync draft inbox, or confirms in chat and you call approve_draft.

Only use publish_now or publish_scheduled when the user explicitly asked to go live now and confirmed the exact content. Default is the draft flow, and default timing is scheduled, not publish-now.

Read the full file on GitHub · 46 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. 6d ago First seen · 46 lines · 58 tokens per session scan A 52e3e5c1cdc8

Subscribe to this mod's changes

repurpose-longform is a skill published in the GitHub repository JackVitick/socialync-mcp (0 stars, last pushed 10d ago), licensed MIT. It adds 58 tokens to every session and 651 once invoked, about $0.0003 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens