Communitygithub.com

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.

claude-skills 是什么？

claude-skills is a Claude Code agent skill that 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.

兼容平台✓Claude Code~Codex CLI~Cursor
npx skills add https://github.com/jsath/claude-skills/tree/HEAD/skills/video/ready-to-film
查看原文→浏览所有技能

在你喜欢的 AI 中提问

打开一个已预加载此 Agent Skill 的新对话。

OpenAIChatGPTClaudeClaudeGeminiGeminiGrokGrokPerplexityPerplexityDeepSeekDeepSeek

文档

Ready to Film

Five agents turn messy notes into scripts the creator reads straight off the screen, in their voice, with every claim checked before it is said on camera.

Where it runs and what it connects to

SourceWorks inWhat it really does
Pasted textClaude.ai and Claude Codenotes, voice-note transcripts, past video transcripts
ScreenshotsbothClaude reads the text in them
Google Drive connector (optional)Claude.aisearches and reads Docs in a folder the user names
Web search (optional)boththe Fact Checker's public sources
Local files / whisper-cliClaude Coderead a notes folder; transcribe audio voice notes locally if whisper.cpp is installed

Claude.ai cannot transcribe audio files. Ask for the phone's own transcript of a voice note, or run it through Claude Code.

Getting transcripts of your last 10 videos

  • YouTube: Studio > Subtitles > download the .srt, or in Claude Code yt-dlp --skip-download --write-auto-subs --sub-langs en <url>.
  • Instagram / TikTok: copy the auto-captions, or paste the script you read from.
  • Anything else: re-transcribe the video file with whisper.cpp in Claude Code.

Setup (start)

Ask in two short rounds, accept "skip", save as PROFILE:

  1. Who are your videos for, in one line?
  2. Platforms, and your usual length on each.
  3. Your 3 best videos and how they did against your usual numbers (paste numbers if you have them).
  4. Anything you never say or do on camera?
  5. Transcripts of 10 past videos, as spoken.
  6. Your current notes or idea list, or the Drive folder name.
  7. Teleprompter, phone, or memory? (sets the max line length: 12 words for phone, 18 for teleprompter)
  8. Your end-of-video CTA, word for word.

Then run agent 4 once to build VOICE, agent 1 on the notes, and suggest script <top idea> as a reel.

Commands

CommandRuns
startsetup above
new idea: <text> or pasted notesagent 1
hooks <idea #>agent 2
script <idea #> as a reel / tiktok / youtube2, pause for the hook pick (or auto = top hook), then 3, 4, 5
voice <pasted script>agent 4
check <pasted script>agent 5
record sheetagent 3's record-sheet mode on all scripts marked checked

Agents

Read the agent file before running that step; it is the only home for that role's rules.

  1. agents/01-idea-bank.md: splits notes into single ideas, ranks what to film first.
  2. agents/02-hook-writer.md: ten openers, first three words checked, top three marked.
  3. agents/03-script-writer.md: script at the platform's length, beat table, record sheet.
  4. agents/04-voice-editor.md: builds VOICE, rewrites lines that read as AI.
  5. agents/05-fact-checker.md: claims table, every claim verified with source and date or flagged.

Shared files

Claude Code: files in scripts/. Claude.ai: print the updated tables at the end of each run for the user to save to Project knowledge.

PROFILE.md  setup answers
VOICE.md    agent 4's voice notes
IDEAS.md    ranked idea bank
SCRIPTS.md  each script, status: draft / voiced / checked / filmed
CLAIMS.md   every claim, source, date checked, status

Safety rules (every agent)

  • Never invent a number, study, quote, result or personal story. Gaps become [NEED: what, and where it would come from].
  • No script is marked checked while any claim is NEEDS SOURCE or CUT.
  • Build only from the creator's own words and opinions.
  • Spoken style: numbers as digits, no em or en dashes, no rhetorical-question openers.

End-of-run output

READY TO FILM: idea #4 as a reel
Hooks     10 written, picked #3 "Your inbox runs your day."
Script    148 words, about 38 s at 3.9 words/s
Voice     6 lines rewritten (2 antithesis, 3 filler, 1 trailing clause)
Claims    5: 3 VERIFIED, 1 FIX applied, 1 NEEDS SOURCE ("saves 6 hours a week")
Status    not ready, 1 line flagged. Send the source or cut the line.
Next      "record sheet" once it is checked

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 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

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.

相关技能

steipete/video-frames

Extract frames or short clips from videos using ffmpeg.

community

steipete/summarize

Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.

community

openclaw/openclaw

Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.

community

obra/superpowers

Obra superpowers agent skills.

community

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

community

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

community