Communitygithub.com

jsath/claude-skills

Turns one published long-form video or podcast transcript into up to thirty pieces: 10 clips with new hooks and exact timestamps, 8 X posts, 4 LinkedIn posts, 3 carousels, 2 threads, a newsletter, a community post and a blog post, laid out on a two-week plan, all built only from what was said. In Claude Code it also cuts, reframes and captions the clips with ffmpeg. Use when someone wants to repurpose a long video, find clips, or write social posts from a transcript. Never posts or schedules.

Qu'est-ce que claude-skills ?

claude-skills is a Claude Code agent skill that turns one published long-form video or podcast transcript into up to thirty pieces: 10 clips with new hooks and exact timestamps, 8 X posts, 4 LinkedIn posts, 3 carousels, 2 threads, a newsletter, a community post and a blog post, laid out on a two-week plan, all built only from what was said. In Claude Code it also cuts, reframes and captions the clips with ffmpeg. Use when someone wants to repurpose a long video, find clips, or write social posts from a transcript. Never posts or schedules.

Compatible avec✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/jsath/claude-skills/tree/HEAD/skills/video/content-multiplier

Demander à votre IA préférée

Ouvre une nouvelle conversation avec cette compétence d'agent déjà préchargée.

Documentation

Content Multiplier

Five agents pull every usable moment out of a video the creator already made. Everything comes from what was said. The creator reviews and posts.

Where it runs

  • Claude.ai: paste the transcript (timestamped; word level if possible). All five agents run; the Clip Cutter outputs in/out points and one SRT per clip instead of video files.
  • Claude Code: same, plus the Clip Cutter cuts vertical captioned clips from the final video file with ffmpeg, whisper.cpp and OpenCV (see agents/03-clip-cutter.md for the tool check).
  • No social connectors. It never posts, schedules or logs in anywhere. The plan is a table (and CSV) the creator loads into their own scheduler.
  • Getting a transcript: YouTube Studio > Subtitles > download .srt or .vtt for your own video; podcast hosts usually export one; or in Claude Code run whisper.cpp on the file. It must be the transcript of the PUBLISHED edit, or clip timestamps will be wrong.

Setup (start, two rounds, "skip" allowed)

  1. What is the video about, and who is it for?
  2. Which platforms do you post on, and how many posts per week on each?
  3. One CTA per platform (comment a keyword, join the newsletter, book a call).
  4. Start date and time zone for the plan.
  5. 5 to 10 of your own posts that sound like you; words you never use.
  6. Names, products and terms that must be spelled exactly (SPELLING).
  7. Anything that must NOT be used (private details, a client, a misspoken line).

Commands

CommandRunsResult
startsetupPROFILE, SPELLING
multiply + transcript (and video path in Claude Code)1 to 5 in order30 pieces + plan
moments1MOMENTS
clips2 (needs MOMENTS)CLIPS
cut3clips or cut list + SRTs
write4POSTS
plan5PLAN

The fixed mix of 30

10 clips, 8 X posts, 4 LinkedIn posts, 3 carousels, 2 threads, 1 newsletter, 1 community post, 1 blog post. If the material is not there for a piece, leave it out and say so. Never pad to reach 30.

Agents

Read the agent file before running that step; its rules live only there.

  1. agents/01-moment-finder.md: splits the transcript into one-idea moments with exact times; ranks how well each stands alone.
  2. agents/02-clip-picker.md: picks up to 10 standalone clips, tightens in/out, writes a hook for the first 2 seconds.
  3. agents/03-clip-cutter.md: cuts, reframes to 1080x1920 and captions each clip (Claude Code), or cut list + SRT (Claude.ai).
  4. agents/04-text-writer.md: the 20 written pieces in the creator's voice.
  5. agents/05-planner.md: 14-day calendar, one CTA per piece, overflow listed.

Shared files (project notes in Claude.ai, work/ in Claude Code)

  • PROFILE, SPELLING
  • MOMENTS (M1...), CLIPS (CL1 to CL10), POSTS (X1-X8, L1-L4, C1-C3, T1-T2, N1, CP1, B1), PLAN
  • Claude Code only: input/final.mp4, out/clip-NN-*.mp4, out/clip-NN.srt, out/CHECKS.md

Safety rules (every agent)

  • Only what was said. Quotes word for word. A missing fact becomes [ADD SOURCE: what is needed].
  • Nothing from the do-not-use list, ever, even at a clip boundary.
  • Timestamps in HH:MM:SS.mmm, snapped to word boundaries. Never cut mid-word.
  • SPELLING applied to every caption and post. No em dashes; no emoji or hashtags unless the creator's samples use them.
  • Never post, schedule or connect to a social account. Never upload a clip.

End-of-run output

MULTIPLIED: "How I plan a week" (42 min)
Moments  31 found, 14 stand alone, 3 AVOID (private)
Clips    10 picked (24 to 58 s), 8 hook KEEP, 2 hook CARD
Cutter   10 clips in out/, 9 FACE crop, 1 CENTRE-CROP (screen share), all checks PASS
Posts    8 X, 4 LinkedIn, 3 carousels, 2 threads, N1, CP1, B1 written; 2 [ADD SOURCE] gaps
Left out none
Plan     Day 1 Mon: CL3 Reels/Shorts/TikTok + X2; N1 on Day 6; 2 pieces overflow to week 3
Nothing has been posted or scheduled. Review every clip and post before it goes out.

Individual skills in this repo

This repo contains 11 individual skills — each has its own dedicated page.

jsath/claude-skills

Writes captions for a finished video from its transcript: pulls the line worth repeating, writes first-line options, writes per-platform versions (Instagram, TikTok, YouTube title and description, others on request), keeps the creator's voice using their best past captions, and checks the call to action matches what the video actually says. Use when a creator asks for captions, a caption hook, a YouTube title and description, or a CTA check. Drafts only; never posts or schedules.

jsath/claude-skills

Write CAPTIONS-PLATFORMS.md for one finished short video: a per-platform post caption for Instagram, TikTok, YouTube Shorts (title + description), Facebook, Threads, Bluesky and X, each within that platform's limits, with your comment-keyword CTA on the platforms where it belongs and never on X. Keyword, CTA, platforms, hashtags and limits come from a config file; a checker script fails the file on any miss. Use after an edit is finished, when asked to 'write the captions', 'caption this reel for every platform', or before scheduling.

jsath/claude-skills

Transcribe audio or video on your own machine with Whisper (mlx-whisper, faster-whisper or whisper.cpp) and get word-level timestamps as words.json, a plain .txt and an .srt. No API key, nothing uploaded. This is the transcription step the editing skills (edit-style, longform-edit, reel-captions) depend on. Use when asked to transcribe a take, get word timings, make an SRT, re-transcribe a final render for a caption sync check, or 'run whisper locally'.

jsath/claude-skills

Turn a raw talking-head take into a dynamically edited 1080x1920 reel: full-face, full-graphic and split layouts that switch every 2 to 5 seconds, real UI and official-logo panels, captions on every word timed by Whisper, voice plus synthesised SFX (no music bed) mastered to -14 LUFS, and hard QA gates (caption sync on the final render, A/V length, loudness, colour, framing, contact sheet, claims). Also covers writing the script so it does not read as AI. Use when asked to 'edit this reel', 'make it look edited', 'add captions / dynamic layout / graphics', or 'write a reel script'.

jsath/claude-skills

Edits a raw long-form YouTube recording (screen recording export, camera file, or either plus a separate mic) into a publish-ready video automatically, like Descript on autopilot: transcribes with word timestamps, removes retakes and keeps the last take, tightens dead space while keeping silent on-screen action (speeding up long waits), masters the voice to -14 LUFS / -1.5 dBTP with no music bed, re-transcribes the FINAL render for an every-word SRT (optional burned-in captions), drafts chapters, titles and a description, and fails loudly on QA gates (words, A/V sync, caption sync per chapter, caption coverage, loudness) plus contact sheets you look at. Use when someone says edit this long-form, clean up my recording, cut the retakes and dead space, process the long-form inbox, or descript this. Needs Claude Code with ffmpeg, whisper.cpp and Python 3.

jsath/claude-skills

Turns one podcast episode transcript into a week of written content: an Episode Prep agent that checks the transcript and speaker names, a Clip Spotter that picks the best short-clip moments with exact timestamps and hooks for an editor to cut, a Show Notes Writer that writes show notes and chapter markers, a Repurpose Writer that turns the big ideas into a newsletter, a LinkedIn post and Instagram captions, and an Episode Planner that spreads it all over the week. Works from a transcript the user supplies or exports from their transcription tool. It does not edit audio or video and does not cut clips. Use when a podcaster asks for show notes, chapters, clip timestamps, or posts from an episode, or says \"repurpose this episode\". Drafts only; never posts.

jsath/claude-skills

Turns one raw talking-head take into a finished 1080x1920 vertical reel in Claude Code with free local tools (ffmpeg, whisper.cpp, headless Playwright): transcribes, keeps the last take of repeated lines, cuts pauses, captions every word, adds real screenshots and official logos, and runs measured QA gates. Use when someone wants a raw phone take edited into a Reel, TikTok or Short, retakes and silences cut, word-by-word captions, or a finished video checked. In Claude.ai it only produces a cut list, shot plan and .srt from a pasted transcript.

jsath/claude-skills

Turns notes, voice-note transcripts and half ideas into Reel, TikTok and YouTube scripts in the creator's own voice: ranks an idea bank, writes ten hooks per idea, writes the script at the right length, rewrites anything that sounds like AI using transcripts of the creator's past videos, and fact-checks every claim with a source and date. Use when someone wants a video script, hooks, a ranked list of what to film, a voice pass, a claims check, or a record sheet to read from while filming.

jsath/claude-skills

Reviews and rewrites a video script (YouTube long-form, a short, or a talking-head reel) so it sounds like one person talking to one friend and holds attention: kills forced analogies and presenter phrases, fixes framing, checks hooks, open loops and re-engagement beats, and suggests titles. Use when someone says fix this script, polish my script, make it sound like me, tighten this before I film, or asks for a hook or title for a video. Returns the rewritten script plus a short change log.

jsath/claude-skills

Make a 1280x720 YouTube thumbnail (or a banner/cover) that reads at phone size: a text-free background plate (generated or from a real frame), a real cutout of the person, 1 to 3 words in tight colour blocks, an official logo, composed by a script that checks overlaps and frame edges and renders the 320px and 168px views you must look at. Use when asked for a thumbnail, cover, banner, 'make this clickable', or to fix a thumbnail that looks cluttered or small.

jsath/claude-skills

Runs five agents that keep a YouTube channel's titles and descriptions matched to what people search for now: a Channel Reader that pulls the user's own video list and stats with their YouTube Data API key, YouTube Analytics OAuth or a pasted YouTube Studio export, a Niche Watcher that finds what is working right now for similar-size channels from public search results the API returns or the user provides, a Title Writer that drafts titles, descriptions and chapters for new videos, a Back Catalogue agent that picks old videos worth a refresh and drafts new versions, and a Change Tracker that records every change the user makes and compares before and after on matched windows. Use when a creator asks for YouTube SEO, better titles or descriptions, what is working in their niche, a back catalogue refresh, or says \"seo run\". Never invents search volumes or stats and never changes a video; drafts only.

Skills associés