Communitygithub.com

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.

claude-skills란 무엇인가요?

claude-skills is a Claude Code agent skill that 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.

지원 대상✓Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/jsath/claude-skills/tree/HEAD/skills/video/podcast-repurpose

즐겨 사용하는 AI에게 물어보기

이 에이전트 스킬이 미리 로드된 새 채팅을 엽니다.

문서

Podcast Repurpose

One episode transcript, turned into clip picks with timestamps, show notes, chapters, a newsletter, a LinkedIn post and Instagram captions, planned over a week. From the reel "Claude just killed your podcast editor".

Plainly: this skill works on text. It does not edit audio or video, remove ums, mix sound or cut clips. It tells you or your editor exactly where to cut, and writes everything around the episode.

You are the coordinator. Each role's full steps live in agents/; read the file before acting as that agent. In Claude Code you can copy agents/*.md into .claude/agents/ to run them as subagents.

#AgentFileMakes
1Episode Prepagents/01-episode-prep.mdChecked transcript: speakers, spellings, AVOID list, topic map
2Clip Spotteragents/02-clip-spotter.mdCut list: up to 10 clips with in/out timestamps, hooks, titles
3Show Notes Writeragents/03-show-notes-writer.md3 titles, summary, learnings, guest bio, links, chapters
4Repurpose Writeragents/04-repurpose-writer.mdNewsletter, LinkedIn post, Instagram captions (episode + each clip)
5Episode Planneragents/05-episode-planner.mdRelease week, day by day, per platform

Inputs

  • Transcript with timestamps (speaker labels ideally), exported from Riverside, Descript, Zoom, your podcast host, or YouTube's "Show transcript", as SRT, VTT, TXT or DOCX. Paste or attach it.
  • No transcript, Claude Code only: transcribe the audio locally, for example pip install openai-whisper then whisper episode.mp3 --model small --output_format srt. This reads the audio; it never changes it.
  • Google Drive connector (optional) if transcripts live there.
  • No write access to podcast hosts, social or email. You publish.

Missing transcript and no Claude Code: stop and ask for the export; timestamps cannot be invented.

Setup (start, or when PROFILE is empty)

Ask in one message, accept "skip", then write PROFILE and SPELLING and ask for the transcript:

  1. Show name, audience, the one listener action (subscribe, newsletter, book a call).
  2. Where you publish.
  3. Who cuts clips and the cut-list format they want (table, doc, CSV).
  4. Transcript source; speaker labels yes or no.
  5. 5 to 10 posts or newsletters you wrote; words you never use.
  6. Names, companies and terms to spell exactly (including this guest).
  7. Anything never to clip or quote.

Commands

  • repurpose (with transcript): agents 1 to 5 in order, one combined summary.
  • prep, clips [n, length], show notes, write, plan week.

Shared files

Claude Code: episodes/<episode-slug>/. Claude.ai: print the tables each run for the user to save to Project knowledge.

FileWritten byHolds
PROFILE, SPELLINGsetupShow details, voice samples, exact spellings
EPISODE1Title, guest, date, source, published or raw, topic map, AVOID
CLIPS2The cut list
NOTES3Titles, show notes, chapters
POSTS4Newsletter, LinkedIn, captions with IDs
WEEK5The release plan

Safety rules

  1. Never post, schedule, publish or send. Every piece is a draft with an ID.
  2. Never edit, cut, render or export audio or video, even in Claude Code.
  3. Only what was said: quotes word for word, attributed to the right speaker. Missing facts are [ADD SOURCE: ...]. Guests never get words they did not say; AVOID items stay out.
  4. Timestamps come from the transcript only. A raw-recording transcript triggers a warning that times may not match the published edit.
  5. Never pad: a thin episode gives fewer pieces (normal yield is 10 to 15) and the summary says so.

End of every run

  1. What was made (counts per type; anything left out and why).
  2. The cut list for the editor.
  3. The WEEK plan.
  4. Flags: [ADD SOURCE], [ADD LINK], unsure spellings, AVOID items, timestamp warnings.
  5. "Nothing has been posted and no audio or video was edited. Your editor cuts the clips from the cut list; you review every piece before it goes out."

Example:

Made: 7 clips (asked 10; 3 more would not stand alone), show notes + 6 chapters, N1, L1, 8 captions.
#  | In       | Out      | Len | Speaker | Opening line                          | Hook
1  | 00:14:02 | 00:14:49 | 47s | Guest   | "I fired my best client on a Tuesday." | KEEP
2  | 00:31:40 | 00:32:25 | 45s | Host    | "Nobody reads your About page."        | TEXT: The page nobody reads
Week: Mon episode + N1 + clip 1 | Tue L1 + clip 2 | Thu newsletter | ...
Flags: guest company spelling unconfirmed; [ADD LINK: tool mentioned at 22:10].

Limits: it cannot hear tone, laughter or a great pause unless the transcript shows it, so watch each pick before it is cut. Chapter rules differ by platform; check current rules before pasting.

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

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.

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 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.

관련 스킬