Skip to content
Back to search

vodcut

MarketplaceWorks with Claude CodeGitHub

/vodcut, an open-source Claude Code skill: watches an entire stream VOD on your machine (whisper.cpp + loudness + reaction cues), verifies the best moments on frame sheets, cuts them 1080x1920 and opens each one as an AI Producer project for captions and export. The README's one-paste prompt runs it end to end.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/steven-van-opus--vodcut/badge.svg)](/listings/steven-van-opus--vodcut)

HTML

<a href="/listings/steven-van-opus--vodcut"><img src="/api/listings/steven-van-opus--vodcut/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**1. AI Producer's official plugin** (the clips open there):

claude plugin marketplace add https://github.com/opus-pro/ai-producer-plugin.git#main
claude plugin install aip@ai-producer-plugins --scope user

Start a new session and sign in with `/mcp` -> `plugin:aip:ai-producer` (your OpusClip account, in the browser). AI Producer in coding agents is rolling out and open to a limited set of accounts.

**2a. /vodcut as a plugin**

/plugin marketplace add steven-van-opus/vodcut
/plugin install vodcut@vodcut

Run it as `/vodcut:vodcut`. The plugin declares `aip@ai-producer-plugins` as a dependency: with step 1 done, Claude Code keeps it enabled; without it, /vodcut installs but does not load.

**2b. /vodcut as a plain skill**

git clone https://github.com/steven-van-opus/vodcut.git
mkdir -p ~/.claude/skills && cp -R vodcut/skills/vodcut ~/.claude/skills/vodcut

Run it as `/vodcut`. The scripts travel inside the skill folder.

gtavi-aiproducer already includes the /vodcut scan; install one or the other. Both ship a skill named `vodcut`, so with both installed a bare `/vodcut` goes to whichever loaded first.

**3. Local tools**

brew install ffmpeg yt-dlp whisper-cpp
mkdir -p ~/.cache/whisper && curl -L -o ~/.cache/whisper/ggml-large-v3-turbo-q5_0.bin \
  https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-turbo-q5_0.bin

Python 3.9+ (standard library only).

One-paste prompt

With steps 1-3 done, paste this into Claude Code. Edit the [brackets] or keep the defaults:

Run /vodcut (/vodcut:vodcut if you installed the plugin) end to end with:
VOD: [a link or local file; default qSyo5d-dVzA, IShowSpeed's first GTA 6 stream]
Clips: [5]
Moments fans already clipped: [none, or phrases like "is that hulk"]
Style: [AI Producer's plain captions, no reference style]

1. Scan the whole VOD in the background and tell me when the moments are ranked.
2. Add those moments, check the best on frame sheets, then show me your picks and why.
   Wait for my OK.
3. Cut each pick 1080x1920, facecam on top and gameplay below, and credit the streamer.
4. Open every clip as an AI Producer project with captions in that style.
5. Report the numbers and each project link.
Before anything that costs credits, tell me the price and wait for my yes.
Don't export until I ask, and never post anything.

It runs the whole flow, VOD to editable AI Producer projects, and waits for your OK on the picks and before anything that costs credits. No export unless you ask, and no posting.

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 35 lines
  1. {
  2. "$schema": "https://anthropic.com/claude-code/marketplace.schema.json",
  3. "name": "vodcut",
  4. "owner": {
  5. "name": "steven-van-opus"
  6. },
  7. "metadata": {
  8. "description": "Single-plugin marketplace for /vodcut: scan a whole stream VOD locally and open the best moments in AI Producer.",
  9. "version": "1.1.0"
  10. },
  11. "allowCrossMarketplaceDependenciesOn": [
  12. "ai-producer-plugins"
  13. ],
  14. "plugins": [
  15. {
  16. "name": "vodcut",
  17. "source": "./",
  18. "description": "One skill: /vodcut scans an entire stream VOD on your machine, finds and verifies the best moments, cuts them 1080x1920 and opens each one as an AI Producer project.",
  19. "version": "1.1.0",
  20. "author": {
  21. "name": "steven-van-opus"
  22. },
  23. "homepage": "https://github.com/steven-van-opus/vodcut",
  24. "repository": "https://github.com/steven-van-opus/vodcut",
  25. "license": "MIT",
  26. "category": "productivity",
  27. "keywords": [
  28. "vod",
  29. "stream-clips",
  30. "ai-producer",
  31. "vertical-video"
  32. ]
  33. }
  34. ]
  35. }
README.md · README · 185 lines
  1. <div align="center">
  2. <img src="docs/hero.png" alt="/vodcut: a terminal command over a loudness strip of a whole stream with three peaks marked #3, #2 and #1, three vertical clips, and the line opened in AI Producer" width="720">
  3. # /vodcut
  4. **Your agent watches the whole stream. You post the 40 seconds that matter.**
  5. My agent watched **23.76 hours** of IShowSpeed's GTA 6 stream and ranked **2,852 thirty-second windows** into
  6. the top **20 moments** in **1:03:27**, for **$0** in API calls.
  7. </div>
  8. - Hand it any VOD (YouTube, Twitch, Kick or a local file), get back the moments worth posting
  9. - Transcribes every hour on your machine with whisper.cpp and ranks 30-second windows by loudness + reaction cues
  10. - Finds the moments fans already clipped by phrase, and checks every winner on a frame sheet before cutting
  11. - Cuts and frames each one 1080x1920: facecam on top, gameplay below, 30 fps
  12. - Opens each clip in AI Producer, where captions and export happen: you get an editable project link
  13. - Fully open source (MIT). One skill, works as a plugin or as a plain `~/.claude/skills` folder
  14. [Install](#install) · [Use](#use) · [How it works](#how-it-works) · [The numbers](#the-numbers) · [FAQ](#faq)
  15. ---
  16. ## Install
  17. **1. AI Producer's official plugin** (the clips open there):
  18. ```bash
  19. claude plugin marketplace add https://github.com/opus-pro/ai-producer-plugin.git#main
  20. claude plugin install aip@ai-producer-plugins --scope user
  21. ```
  22. Start a new session and sign in with `/mcp` -> `plugin:aip:ai-producer` (your OpusClip account, in the browser).
  23. AI Producer in coding agents is rolling out and open to a limited set of accounts.
  24. **2a. /vodcut as a plugin**
  25. ```text
  26. /plugin marketplace add steven-van-opus/vodcut
  27. /plugin install vodcut@vodcut
  28. ```
  29. Run it as `/vodcut:vodcut`. The plugin declares `aip@ai-producer-plugins` as a dependency: with step 1 done, Claude
  30. Code keeps it enabled; without it, /vodcut installs but does not load.
  31. **2b. /vodcut as a plain skill**
  32. ```bash
  33. git clone https://github.com/steven-van-opus/vodcut.git
  34. mkdir -p ~/.claude/skills && cp -R vodcut/skills/vodcut ~/.claude/skills/vodcut
  35. ```
  36. Run it as `/vodcut`. The scripts travel inside the skill folder.
  37. gtavi-aiproducer already includes the /vodcut scan; install one or the other. Both ship a skill named `vodcut`, so
  38. with both installed a bare `/vodcut` goes to whichever loaded first.
  39. **3. Local tools**
  40. ```bash
  41. brew install ffmpeg yt-dlp whisper-cpp
  42. mkdir -p ~/.cache/whisper && curl -L -o ~/.cache/whisper/ggml-large-v3-turbo-q5_0.bin \
  43. https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-large-v3-turbo-q5_0.bin
  44. ```
  45. Python 3.9+ (standard library only).
  46. ### One-paste prompt
  47. With steps 1-3 done, paste this into Claude Code. Edit the [brackets] or keep the defaults:
  48. ```text
  49. Run /vodcut (/vodcut:vodcut if you installed the plugin) end to end with:
  50. VOD: [a link or local file; default qSyo5d-dVzA, IShowSpeed's first GTA 6 stream]
  51. Clips: [5]
  52. Moments fans already clipped: [none, or phrases like "is that hulk"]
  53. Style: [AI Producer's plain captions, no reference style]
  54. 1. Scan the whole VOD in the background and tell me when the moments are ranked.
  55. 2. Add those moments, check the best on frame sheets, then show me your picks and why.
  56. Wait for my OK.
  57. 3. Cut each pick 1080x1920, facecam on top and gameplay below, and credit the streamer.
  58. 4. Open every clip as an AI Producer project with captions in that style.
  59. 5. Report the numbers and each project link.
  60. Before anything that costs credits, tell me the price and wait for my yes.
  61. Don't export until I ask, and never post anything.
  62. ```
  63. It runs the whole flow, VOD to editable AI Producer projects, and waits for your OK on the picks and before anything
  64. that costs credits. No export unless you ask, and no posting.
  65. ## Use
  66. ```text
  67. /vodcut https://www.youtube.com/watch?v=<VOD_ID> 5
  68. ```
  69. 1. Scans the whole VOD in the background (resumable), then ranks the moments.
  70. 2. Adds the moments fans already clipped, if you name them ("is that hulk").
  71. 3. Shows you the top moments as frame sheets and picks the winners with you.
  72. 4. Measures the facecam once, then cuts and frames each winner 1080x1920.
  73. 5. Opens every clip in AI Producer and gives you each project link.
  74. 6. Captions, sound and the MP4 export happen in AI Producer, on request.
  75. ## How it works
  76. ```text
  77. VOD ──ytfrag.py / yt-dlp──> audio.m4a ──scan_vod.py──> transcript + loudness ──rank_windows.py──> moments
  78. ──vodcut.py find──> + known moments ──vodcut.py verify──> frame sheets (Claude looks at every one)
  79. ──vodcut.py cut──> 1080x1920 clips (frame.py) ──vodcut.py prep──> sign_upload args
  80. ──AI Producer──> project + transcript + captions + export + editable link
  81. ```
  82. - **YouTube VODs, both ways YouTube serves them.** Post-live VODs still served as 2-second fragments, where
  83. `yt-dlp --download-sections` fails, go through `ytfrag.py`: parallel, rotated signed URLs, resumes and retries.
  84. Processed VODs (YouTube processes them later; the launch-day VODs took about a day) go through yt-dlp.
  85. `vodcut.py` asks yt-dlp which one it is before every download, and `ytfrag.py` refuses a processed VOD rather
  86. than pull the whole file once per fragment.
  87. - **Score** = loudness z-score of a window's 5 loudest seconds + 0.35 x reaction cues + 0.01 x words. Whisper's
  88. repetition loops (it repeats a line over music) are cleaned first, so a hallucination cannot win.
  89. - **Review flags** on every moment: `profanity` (bleep it), `sexual`, `spoiler`, `loop`.
  90. - **AI Producer** is where the edit lives, and it is not asked to do what it does not do: its sources are capped at
  91. about 30 minutes and it keeps the source orientation, so /vodcut finds the moment and frames it vertical first.
  92. | Script (`skills/vodcut/scripts/`) | What it does |
  93. |---|---|
  94. | `vodcut.py` | The pipeline: `scan`, `find`, `verify`, `cut`, `prep`, `report` |
  95. | `ytfrag.py` | Exact windows or whole tracks of YouTube post-live VODs still served as 2-second fragments |
  96. | `scan_vod.py` | Loudness + chunked whisper.cpp transcription, resumable |
  97. | `scan_frags.py` | Transcribes while a fragment-served download is still running |
  98. | `rank_windows.py` | Ranked 30 s windows, loop cleaning, review flags, distinct moments |
  99. | `framesheet.py` | 12 frames of a moment in one image |
  100. | `frame.py` | Facecam grid, 9:16 still, 1080x1920 compose (stack, inset, full) |
  101. | `bleep.py` | Word timings and baked-in bleeps before upload |
  102. | `aip_prep.py` | AI Producer limit check, `sign_upload` arguments, provenance + credit |
  103. Every script answers `--help`. Tests: `python3 -I -m unittest discover -s tests -v`.
  104. ## The numbers
  105. The launch line comes from one fresh, uninterrupted run on 2026-11-20, saved as
  106. [`docs/launch-run.json`](docs/launch-run.json) (its `vodcut.py report --json`, without the transcript lines):
  107. ```bash
  108. python3 -I skills/vodcut/scripts/vodcut.py scan qSyo5d-dVzA vodcut/speed-1118
  109. ```
  110. | | |
  111. |---|---|
  112. | Stream | IShowSpeed's first GTA 6 stream on YouTube (`qSyo5d-dVzA`) |
  113. | Hours scanned | 23.76 |
  114. | 30-second windows ranked | 2,852 |
  115. | Moments kept | 20 (the `--moments` default), best first |
  116. | Wall time | 1:03:27 |
  117. | API cost | $0 (ffmpeg, yt-dlp and whisper.cpp run locally) |
  118. The wall time runs from the audio download to the ranked moments, on one M1 Ultra Mac that had other jobs
  119. running. `report` prints a wall time only for a folder whose first scan fetched the audio itself and ran start to
  120. finish; your machine and connection set yours.
  121. AI Producer's own steps are priced live by AI Producer (`get_pricing`) before anything runs.
  122. ## FAQ
  123. **Does AI Producer find the moments?** No, /vodcut does, on your machine. AI Producer edits the clips once they exist.
  124. **Does it make 16:9 streams vertical?** Yes, /vodcut does that with ffmpeg before the upload; AI Producer keeps a
  125. source's orientation.
  126. **Twitch and Kick?** Yes, through yt-dlp: the audio for the scan, a 360p preview per moment, and full quality only for
  127. the windows you pick.
  128. **What leaves my machine?** Only the clips you choose to open in AI Producer. The scan, the transcript and the
  129. previews stay local.
  130. **Credits?** Every clip gets a provenance file with the source link, times and a credit line
  131. (`🎥 @streamer (Platform)`). Credit is courtesy, not a license: keep clips short and transformed.
  132. ## Disclaimer
  133. Not affiliated with or endorsed by Rockstar Games, Take-Two Interactive, IShowSpeed or any streamer named here.
  134. Stream footage belongs to its owners: credit them, follow each game's video policy and every campaign's brief, and
  135. take a clip down when asked. AI Producer and OpusClip are products of OpusClip, used through the official `aip`
  136. plugin. MIT licensed, see [LICENSE](LICENSE).

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.