raw-to-reel
Skill14 starsChanged 35 days agoMITView on GitHub
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.
- Installs packages
In this repository63 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- board-advisorSkill
- bottleneck-removalSkill
- business-auditSkill
- business-starterSkill
- competitor-researchSkill
- founder-independenceSkill
- hand-it-offSkill
- happy-customerSkill
- hiring-replacementSkill
- meeting-follow-upSkill
- monday-numbersSkill
- new-hireSkill
- no-meeting-mondaySkill
- obsidian-brainSkill
- ops-deskSkill
- safe-resaleSkill
- spreadsheet-dashboardSkill
- warm-leadSkill
- downloadable-asset-engineeringSkill
- html-to-pdfSkill
- linux-server-opsSkill
- precision-pdf-editingSkill
- repo-radarSkill
- secure-credentialsSkill
- security-auditorSkill
- best-timeSkill
- brand-deal-filterSkill
- comment-replySkill
- content-monthSkill
- daily-socialSkill
- dm-closerSkill
- idea-bankSkill
- marketing-teamSkill
- reel-ideationSkill
- reel-scorecardSkill
- trial-postSkill
- viral-breakdownSkill
- youtube-seoSkill
- caption-engineSkill
- content-multiplierSkill
- edit-styleSkill
- footage-ingestSkill
- longform-editSkill
- podcast-repurposeSkill
- ready-to-filmSkill
- reel-captionsSkill
- script-polishSkill
- thumbnail-generatorSkill
- use-local-whisperSkill
- conversion-funnel-auditingSkill
- llms-txtSkill
- seo-agentSkill
- website-designerSkill
- website-devSkill
- be-conciseSkill
- humanizerSkill
- launch-weekSkill
- linkedin-writerSkill
- newsletterSkill
- The first 60 shown.
The file
We split this skill into the rules it gives an agent
7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈5
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 45
Use ggml-small.en (about 466 MB) as the default.
- Very specific: line 49
Read the agent file before running that step.
- Distinctive: line 57
If an agent fails, fix and rerun that agent only, then everything after it.
- Distinctive: line 75
Never modify or overwrite the raw file.
- Distinctive: line 76
Never post or upload anything.
- Distinctive: line 79
No private data on screen (inboxes, bank pages, client names, logged-in dashboards) unless the user supplied the image and confirmed it is …
- Distinctive: line 80
No number or claim as on-screen text without a source from the user.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Raw to Reel
Five agents, run in order, turn raw/<take>.mov into out/<take>/final.mp4. This is the simple version. For the full engine (per-line layouts, synthesised SFX, more QA gates), use ../edit-style. For setting up whisper.cpp in depth, see ../use-local-whisper.
Where it runs
- Claude Code on macOS or Linux: full pipeline. Needs ffmpeg, whisper.cpp (
whisper-cli) with a model, Python 3 with Pillow and OpenCV, and Playwright with headless Chromium. - Claude.ai: cannot open or export video.
planmode only: paste a transcript, get a tightened script, a shot plan and an .srt.
Commands
| Command | Runs | Output |
setup | tool check below | missing tools + install commands; installs only after the user says yes |
edit raw/<file> | agents 1, 2, 4, 3, 5 | out/<name>/ files below |
plan raw/<file> or plan + pasted transcript | agent 1 (transcript, retakes), 2 (cut list only), 4 (shot plan only) | tables, no render |
check <file> | agent 5 | QA.md |
Captions (agent 3) run after the visual build (agent 4) because layouts change caption position, and captions are always the top layer.
setup check
ffmpeg -version | head -1; ffprobe -version | head -1
whisper-cli --help >/dev/null 2>&1 && echo WHISPER_OK || echo WHISPER_MISSING
ls ~/whisper-models/ggml-*.bin 2>/dev/null || echo NO_MODEL
python3 -c "import PIL, cv2; print('PY_OK')"
python3 -c "import playwright; print('PW_OK')"Install commands to offer (macOS shown; on Linux use the distro package for ffmpeg and build whisper.cpp from source):
brew install ffmpeg whisper-cpp
mkdir -p ~/whisper-models && curl -L -o ~/whisper-models/ggml-small.en.bin \
https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.en.bin
python3 -m pip install pillow opencv-python playwright && python3 -m playwright install chromiumUse ggml-small.en (about 466 MB) as the default; ggml-base.en if the machine is slow, multilingual ggml-small for non-English takes.
Agents
Read the agent file before running that step. Each file is the only place its detailed rules live. In Claude Code you can copy them into .claude/agents/ to run as real subagents.
agents/01-footage-prep.md: probe, colour fix, word-level transcript, retake table.agents/02-cutter.md: removes earlier takes, dead air and pauses without clipping words.agents/03-captions.md: every word captioned, timed from a transcript of the cut audio.agents/04-visual-planner.md: face / graphic / split shot plan, real screenshots and logos, layered render.agents/05-qa-checker.md: measured gates, contact sheet, claims list, READY or NOT READY.
If an agent fails, fix and rerun that agent only, then everything after it.
Shared files
raw/<name>.mov never modified
work/<name>/LOG.md one line per finished step, so a stopped run can resume
work/<name>/words.json agent 1 transcript (word, start, end)
work/<name>/cuts.csv agent 2
work/<name>/shotplan.md agent 4, with assets/SOURCES.md
out/<name>/final.mp4 1080x1920, H.264 + AAC, BT.709 limited range
out/<name>/captions.srt
out/<name>/contact.png 12 frames
out/<name>/QA.mdSafety rules (every agent)
- Never modify or overwrite the raw file. One work folder per video.
- Never post or upload anything.
- Re-time the picture, never the voice: no speed changes on the audio to make something fit.
- Real things only on screen: real websites, real app screens, official logos. No generated UI, no fake dashboards, no pill badges, stickers or emoji.
- No private data on screen (inboxes, bank pages, client names, logged-in dashboards) unless the user supplied the image and confirmed it is safe.
- No number or claim as on-screen text without a source from the user.
- Browsers run headless only. Run renders with
nice -n 10. If the user says they are recording, stop rendering.
End-of-run output
RAW TO REEL: take1
1 Prep 4K HDR -> SDR BT.709, 212 words, 3 retakes found, kept last take of each
2 Cutter 58.4 s -> 41.2 s, 19 pause cuts, 3 retake cuts, 1 cut flagged at 00:17.3
4 Visuals 11 shots (4 FULL, 3 GFX, 4 SPLIT), 3 screenshots, 2 official logos
3 Captions 96 cues, 2 words unaligned (listed in QA.md)
5 QA READY (8/8 gates PASS) -> out/take1/QA.md
Decide: "doubles your output" is said on camera with no source (CLAIMS list)
Nothing has been posted. Watch final.mp4 once before you upload it.Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

