Skip to content
Back to search

skills

SkillWorks with Claude CodeGitHub

Claude Code skills — live-stream-clipper: auto-clip Twitch/YouTube streams on chat hype into captioned vertical Shorts

Safety scan

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

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/morphhyy--skills/badge.svg)](/listings/morphhyy--skills)

HTML

<a href="/listings/morphhyy--skills"><img src="/api/listings/morphhyy--skills/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

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

git clone https://github.com/morphhyy/skills.git
cp -r skills/live-stream-clipper ~/.claude/skills/                 # every project
# or
cp -r skills/live-stream-clipper <your-project>/.claude/skills/    # one project

Restart Claude Code. The skill loads on its own when you ask for something it covers, for example *"clip xQc's stream live and give me 3 shorts"*.

---

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.

README.md · README · 139 lines
  1. # skills
  2. Skills for [Claude Code](https://claude.com/claude-code). Each folder is one skill: a `SKILL.md` that tells Claude when and how to use it, plus any scripts it runs.
  3. | Skill | What it does |
  4. |---|---|
  5. | [live-stream-clipper](live-stream-clipper/SKILL.md) | Clips Twitch and YouTube streams **while they're live**. Watches chat for hype spikes, cuts the moment, burns in captions, renders a 1080×1920 Short, and can upload it to YouTube. |
  6. ## Install a skill
  7. ```bash
  8. git clone https://github.com/morphhyy/skills.git
  9. cp -r skills/live-stream-clipper ~/.claude/skills/ # every project
  10. # or
  11. cp -r skills/live-stream-clipper <your-project>/.claude/skills/ # one project
  12. ```
  13. Restart Claude Code. The skill loads on its own when you ask for something it covers, for example *"clip xQc's stream live and give me 3 shorts"*.
  14. ---
  15. ## live-stream-clipper
  16. ```
  17. streamlink / yt-dlp ──► ffmpeg 10s segment buffer
  18. Twitch IRC / YouTube live chat ──► spike detector ──► cut [spike-22s, spike+8s]
  19. ──► whisper.cpp captions ──► vertical Short ──► (optional) YouTube upload
  20. ```
  21. Everything is free. Chat is read anonymously. Only the YouTube upload needs a Google account.
  22. ### Requirements
  23. | Tool | Used for |
  24. |---|---|
  25. | Python 3.10+ | the clipper (standard library only) |
  26. | [ffmpeg](https://ffmpeg.org) with libass and freetype | recording, cutting, captions, covers |
  27. | [streamlink](https://streamlink.github.io) | Twitch recording |
  28. | [yt-dlp](https://github.com/yt-dlp/yt-dlp) | YouTube recording and live chat |
  29. | [whisper.cpp](https://github.com/ggml-org/whisper.cpp) (`whisper-cli`) + a model | captions (optional: use `--no-captions`) |
  30. | [uv](https://docs.astral.sh/uv/) | YouTube uploader (pulls its own Google API packages) |
  31. **macOS**
  32. ```bash
  33. brew install python ffmpeg streamlink yt-dlp whisper-cpp uv
  34. ```
  35. **Debian / Ubuntu**
  36. ```bash
  37. sudo apt install python3 ffmpeg
  38. curl -LsSf https://astral.sh/uv/install.sh | sh
  39. uv tool install streamlink && uv tool install yt-dlp
  40. # whisper-cli: build from source (https://github.com/ggml-org/whisper.cpp#quick-start)
  41. ```
  42. **Whisper model** (about 466 MB; use `base` for a smaller and faster model)
  43. ```bash
  44. mkdir -p ~/.cache/whisper
  45. curl -L -o ~/.cache/whisper/ggml-small.bin \
  46. https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.bin
  47. ```
  48. > Tested on macOS. Linux should work. Windows isn't supported yet: the recorder's process handling and the helper `.sh` scripts assume a POSIX system, so use WSL.
  49. ### Usage
  50. Run these from your project folder. Clips are saved there.
  51. ```bash
  52. S=~/.claude/skills/live-stream-clipper/scripts
  53. python3 $S/clipper.py xqc # Twitch channel
  54. python3 $S/clipper.py "https://www.youtube.com/watch?v=VIDEO_ID" # YouTube live
  55. python3 $S/clipper.py xqc --max-clips 3 --export output # stop after 3, copy to ./output
  56. python3 $S/clipper.py xqc --layout split --cam 0:0:480:270 # facecam on top, gameplay below
  57. python3 $S/clipper.py xqc --upload --privacy private # upload every Short
  58. ```
  59. It waits for the stream to go live, learns the normal chat speed for 90 seconds, then clips when chat spikes. It survives stream drops and keeps only the last 30 minutes of recording on disk.
  60. - **Watch progress:** `tail -f clips-xqc/events.log`
  61. - **Force a clip now:** `touch clips-xqc/CLIP_NOW`
  62. - **Stop:** Ctrl+C
  63. Output:
  64. ```
  65. clips-<channel>/
  66. events.log LIVE / SPIKE / CLIP READY / UPLOAD
  67. chat.jsonl every chat message with timestamps
  68. clips/<id>/ raw.mp4 short.mp4 captions.srt meta.json
  69. ```
  70. **Layouts:** `blur` (default; the full frame over a blurred background), `crop` (centre crop, good for IRL), `split` (facecam above gameplay; give the facecam box with `--cam x:y:w:h` in source pixels).
  71. ### Tuning
  72. | Problem | Try |
  73. |---|---|
  74. | Too many clips | `--mult 4 --floor 40 --cooldown 90` |
  75. | No clips (small chat) | `--mult 2.5 --floor 6` |
  76. | Clip starts too late | raise `--pre` (default 22s) |
  77. | Clip ends too early | raise `--post` (default 8s) |
  78. | Wrong caption language | `--lang en` |
  79. | Captions too slow | use the `base` model with `--model ~/.cache/whisper/ggml-base.bin` |
  80. Run `python3 $S/clipper.py --help` for every option.
  81. ### YouTube upload (optional, one time)
  82. 1. In [Google Cloud Console](https://console.cloud.google.com), create a project and enable **YouTube Data API v3**.
  83. 2. Set up the **OAuth consent screen** as External and add yourself as a test user.
  84. 3. Create an **OAuth client ID** of type **Desktop app** and save the JSON as `~/.config/live-clipper/client_secret.json`.
  85. 4. Log in once: `uv run $S/upload_short.py --auth`
  86. Upload a single clip by hand:
  87. ```bash
  88. uv run $S/upload_short.py --meta clips-xqc/clips/<id>/meta.json --title "your title" --privacy private
  89. ```
  90. **Limits:**
  91. - **Private only at first.** Google forces uploads from unaudited API projects to private. Make them public in YouTube Studio, or apply for the API audit.
  92. - **About 6 uploads a day.** Each upload costs about 1,600 of the default 10,000 daily quota units.
  93. ### Credentials stay local
  94. The OAuth client, login token and any cookies live in `~/.config/live-clipper/`, never in this repo. The token is written with `0600` permissions. If YouTube blocks the recorder as a bot, export cookies to `~/.config/live-clipper/yt-cookies.txt`. Each run copies them into its own folder, so don't commit or share your `clips-*` folders.
  95. ### Use responsibly
  96. These clips come from someone else's stream. Credit the streamer (the default description does), and get their permission or join their clipping program before you upload. Copyright claims and strikes land on **your** channel, and game footage can trigger Content ID.
  97. ## License
  98. [MIT](LICENSE)

Ratings and comments

Sign in to rate this skill.

Sign in

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