Skip to content
Back to search

ashtonvossai

MarketplaceWorks with Claude CodeGitHub

Free Claude Code skills from Ashton Voss AI.

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/abhishek047--codex-clipper-skill/badge.svg)](/listings/abhishek047--codex-clipper-skill)

HTML

<a href="/listings/abhishek047--codex-clipper-skill"><img src="/api/listings/abhishek047--codex-clipper-skill/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.

Option A: paste this into Claude Code (easiest)

Install the GTA 6 Clipper skills from https://github.com/vossashtonai/gta6-clipper.
Clone the repo to a temporary folder, then copy BOTH folders inside its skills/ folder
(gta6-clipper and gta6-live-clipper) into ~/.claude/skills/ so they sit side by side.
Then run: bash ~/.claude/skills/gta6-clipper/scripts/setup.sh
Tell me what it installed and whether it says READY. Then remind me to restart Claude Code.

Option B: as a Claude Code plugin

In Claude Code:

/plugin marketplace add vossashtonai/gta6-clipper
/plugin install gta6-clipper@ashtonvossai

Then say **set up the GTA 6 clipper**.

Option C: by hand

git clone https://github.com/vossashtonai/gta6-clipper.git /tmp/gta6-clipper
cp -R /tmp/gta6-clipper/skills/gta6-clipper /tmp/gta6-clipper/skills/gta6-live-clipper ~/.claude/skills/
bash ~/.claude/skills/gta6-clipper/scripts/setup.sh

Setup checks what your Mac needs and installs what's missing: Homebrew packages (FFmpeg, whisper-cpp, Deno), a Python environment (yt-dlp, OpenCV, Pillow) and the Whisper speech model (~465 MB). Re-run it any time downloads start failing; it updates yt-dlp.

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 · 15 lines
  1. {
  2. "name": "ashtonvossai",
  3. "owner": { "name": "Ashton Voss AI" },
  4. "description": "Free Claude Code skills from Ashton Voss AI.",
  5. "plugins": [
  6. {
  7. "name": "gta6-clipper",
  8. "source": "./",
  9. "description": "Clip GTA 6 streams into ready-to-post vertical clips, from a finished stream or live. Mac only.",
  10. "version": "1.0.0",
  11. "author": { "name": "Ashton Voss AI" },
  12. "category": "productivity"
  13. }
  14. ]
  15. }
README.md · README · 133 lines · 1 finding marked
  1. # GTA 6 Clipper
  2. Two macOS skills for Codex and Claude Code that turn GTA 6 streams into ready-to-post vertical clips.
  3. - **gta6-clipper** clips a stream that has finished. Give it a YouTube, Twitch or Kick link, or nothing and it finds today's biggest GTA 6 streams.
  4. - **gta6-live-clipper** clips a stream while it's still live. A clip is ready about 5 to 8 minutes after the moment happens.
  5. Every clip comes out 1080x1920: facecam on top, gameplay below, a hook title, word-by-word captions, and a post caption with hashtags.
  6. **Mac version.** On Windows? Use the Windows version: https://github.com/vossashtonai/gta6-clipper-windows
  7. or paste this in PowerShell: `irm https://raw.githubusercontent.com/vossashtonai/gta6-clipper-windows/main/install.ps1 | iex`
  8. ## Use in Codex
  9. Open this repository as your Codex workspace. The two links in `.agents/skills/`
  10. register the existing skill folders with Codex. Start a new Codex chat in this
  11. workspace if an existing chat does not show them.
  12. - `$gta6-clipper set up the GTA 6 clipper` installs the shared macOS dependencies. Wait for `READY`.
  13. - `$gta6-clipper clip this stream <VOD URL>` selects and renders up to three highlights.
  14. - `$gta6-live-clipper clip this stream live <live URL>` keeps the recorder and highlight selection running in the active chat.
  15. In Codex, outputs go under the repository's `runs/` folder by default.
  16. Each clip has an MP4 and a companion text file with a title, caption, and hashtags.
  17. ## Install in Claude Code
  18. ### Option A: paste this into Claude Code (easiest)
  19. ```text
  20. Install the GTA 6 Clipper skills from https://github.com/vossashtonai/gta6-clipper.
  21. Clone the repo to a temporary folder, then copy BOTH folders inside its skills/ folder
  22. (gta6-clipper and gta6-live-clipper) into ~/.claude/skills/ so they sit side by side.
  23. Then run: bash ~/.claude/skills/gta6-clipper/scripts/setup.sh
  24. Tell me what it installed and whether it says READY. Then remind me to restart Claude Code.
  25. ```
  26. ### Option B: as a Claude Code plugin
  27. In Claude Code:
  28. ```text
  29. /plugin marketplace add vossashtonai/gta6-clipper
  30. /plugin install gta6-clipper@ashtonvossai
  31. ```
  32. Then say **set up the GTA 6 clipper**.
  33. ### Option C: by hand
  34. ```bash
  35. git clone https://github.com/vossashtonai/gta6-clipper.git /tmp/gta6-clipper
  36. cp -R /tmp/gta6-clipper/skills/gta6-clipper /tmp/gta6-clipper/skills/gta6-live-clipper ~/.claude/skills/
  37. bash ~/.claude/skills/gta6-clipper/scripts/setup.sh
  38. ```
  39. Setup checks what your Mac needs and installs what's missing: Homebrew packages (FFmpeg, whisper-cpp, Deno), a Python environment (yt-dlp, OpenCV, Pillow) and the Whisper speech model (~465 MB). Re-run it any time downloads start failing; it updates yt-dlp.
  40. ## Use it
  41. Open Claude Code and say:
  42. - **clip this stream** `<link>`
  43. - **find me today's biggest GTA 6 streams and clip them**
  44. - **live clip** `<link>` (for a stream that's live right now)
  45. Clips land in `~/GTA6-Clips/`. Each one has an `.mp4` and a `.txt` with the title, caption and hashtags.
  46. ## Terminal commands
  47. Run `make help` from the repository root for all setup, VOD, live, thumbnail,
  48. and publishing commands. Make uses `runs/` for VODs and `runs/live/` for live
  49. recordings by default. Set `GTA6_CLIPS_DIR` or `GTA6_LIVE_DIR` to use other folders.
  50. ```sh
  51. make setup
  52. make discover ARGS='--limit 5'
  53. make prep URL='https://www.youtube.com/watch?v=VIDEO_ID'
  54. make status RUN='runs/example'
  55. make render RUN='runs/example' ARGS='--top 3'
  56. make setup-upload
  57. make upload-preview
  58. make upload
  59. ```
  60. Highlight selection is handled by the clipper skill or by editing pick files
  61. before running `make render` or `make live-clip`. Pass additional CLI flags
  62. and multiple positional inputs with `ARGS`. Quote paths individually inside it,
  63. for example `make thumbnail ARGS='"path/to/first clip.mp4" "path/to/second clip.mp4" --at 1'`.
  64. ## How it works
  65. | Step | Finished stream | Live stream | Tools |
  66. |---|---|---|---|
  67. | 1. Get the stream | Downloads the audio only (4 h ≈ 220 MB) | Records 1-minute pieces, keeps the last 15 min | yt-dlp, FFmpeg |
  68. | 2. Speech to text | Whole stream in one go | Each minute as it lands | FFmpeg, Whisper |
  69. | 3. Find the hype | Loud seconds + YouTube replay chat speed | Loud seconds + live Twitch chat speed | FFmpeg, chat |
  70. | 4. Pick the moments | Claude reads 12-min chunks, best 3 scoring 7+ | Claude reads each 5-min window, any 7.5+ | Claude Code |
  71. | 5. Make the clip | Downloads only those minutes | Cuts from the pieces already on your Mac | OpenCV, Whisper, Pillow, FFmpeg |
  72. Chat is counted, never read: 10-second buckets, a spike is 8+ messages at 2.5x the normal rate. Loud means 9 dB above the streamer's own normal. The facecam is found by looking for a face, and box edges, that stay still while the gameplay moves.
  73. ## Run it free
  74. Picking (step 4) is the only part that uses AI. Everything else runs on your Mac. To run without a Claude subscription:
  75. 1. Install [Ollama](https://ollama.com).
  76. 2. Check your memory (Apple menu → About This Mac → Memory). 16 GB: `ollama pull qwen3.5:9b`. 32 GB or more: `ollama pull qwen3.5:27b`.
  77. 3. In Terminal: `ollama launch claude` and pick the model.
  78. 4. Same prompts as above.
  79. The free model is slower and its picks are rougher than Claude's. Expect some back and forth.
  80. ## Good to know
  81. - Age-restricted YouTube streams and Kick need your browser login. Tell Claude to use `--cookies chrome`.
  82. - YouTube streams that are still live can be clipped by the finished-stream skill once the replay is up. Twitch past broadcasts work while the stream is still going.
  83. - Twitch in "find me streams" is optional: create a free app at [dev.twitch.tv/console](https://dev.twitch.tv/console) and put `TWITCH_CLIENT_ID` and `TWITCH_CLIENT_SECRET` in `skills/gta6-clipper/.env` (see `.env.example`).
  84. - Live clipping needs the Claude Code session to stay open, and run at most 2 streams at once on a 16 GB Mac.
  85. - Clip streamers who are fine with clipping, and watch every clip before you post it.
  86. - YouTube ad money needs the Partner Program, and YouTube can refuse it for reposted, mass-made content. Add something of your own.
  87. ## Made by
  88. [Ashton Voss AI](https://www.youtube.com/@ashtonvossai). More free AI systems in the AI Alliance Community.
  89. MIT licensed.
  90. ## Upload approved clips
  91. Run `python -m upload.tui` to review runs and publish approved clips to configured
  92. YouTube, Facebook Page, and Instagram destinations. See the [upload setup guide](upload/README.md).
skills/gta6-clipper/scripts/setup.sh · Bundled script · 80 lines · 1 finding marked
  1. #!/usr/bin/env bash
  2. # GTA 6 Clipper setup: checks what this Mac needs, installs what's missing, says when it's ready.
  3. # Safe to re-run any time.
  4. set -uo pipefail
  5. SKILL_DIR="$(cd "$(dirname "$0")/.." && pwd)"
  6. VENV="$SKILL_DIR/.venv"
  7. MODELS="$SKILL_DIR/models"
  8. mkdir -p "$MODELS"
  9. ok() { printf " [ok] %s\n" "$1"; }
  10. inst() { printf " [install] %s\n" "$1"; }
  11. fail() { printf " [MISSING] %s\n" "$1"; FAILED=1; }
  12. FAILED=0
  13. echo "GTA 6 Clipper setup"
  14. if [[ "$(uname)" != "Darwin" ]]; then
  15. echo "This is the Mac version. On Windows, install the Windows version instead:"
  16. echo " Open PowerShell (Start -> type PowerShell) and paste:"
  17. echo " irm https://raw.githubusercontent.com/vossashtonai/gta6-clipper-windows/main/install.ps1 | iex"
  18. echo " (or see https://github.com/vossashtonai/gta6-clipper-windows)"
  19. exit 1
  20. fi
  21. # 1. Homebrew
  22. if command -v brew >/dev/null 2>&1; then ok "Homebrew"; else
  23. fail "Homebrew (install from https://brew.sh then re-run setup)"; exit 1; fi
  24. # 2. Command-line tools: ffmpeg (cutting/encoding), whisper-cpp (local transcript), deno (YouTube downloads)
  25. for pair in "ffmpeg:ffmpeg" "whisper-cli:whisper-cpp" "deno:deno"; do
  26. bin="${pair%%:*}"; formula="${pair##*:}"
  27. if command -v "$bin" >/dev/null 2>&1; then ok "$formula"; else
  28. inst "$formula"; brew install "$formula" >/dev/null 2>&1 && ok "$formula" || fail "$formula (brew install $formula)"; fi
  29. done
  30. # 3. uv (fast Python + venv manager)
  31. if command -v uv >/dev/null 2>&1 || [[ -x "$HOME/.local/bin/uv" ]]; then ok "uv"; else
  32. inst "uv"; curl -LsSf https://astral.sh/uv/install.sh | sh >/dev/null 2>&1 && ok "uv" || fail "uv"; fi
  33. UV="$(command -v uv || echo "$HOME/.local/bin/uv")"
  34. # 4. Python environment: yt-dlp (always latest, sites change weekly), OpenCV (facecam finder), Pillow (captions)
  35. if [[ ! -x "$VENV/bin/python" ]]; then inst "Python 3.12 environment"; "$UV" venv --python 3.12 "$VENV" >/dev/null 2>&1; fi
  36. "$UV" pip install --python "$VENV/bin/python" -q -U "yt-dlp[default]" opencv-python-headless pillow numpy >/dev/null 2>&1 \
  37. && ok "Python packages (yt-dlp, opencv, pillow, numpy)" || fail "Python packages"
  38. # 5. Whisper model (speech -> text, runs on this Mac). Reuse an existing one if present.
  39. WHISPER_MODEL=""
  40. for m in "$MODELS/ggml-small.en.bin" "$MODELS/ggml-small.bin" "$HOME/.cache/whisper-cpp/ggml-small.en.bin" "$HOME/.cache/whisper-cpp/ggml-small.bin"; do
  41. [[ -f "$m" ]] && WHISPER_MODEL="$m" && break; done
  42. if [[ -z "$WHISPER_MODEL" ]]; then
  43. inst "Whisper small.en model (~465 MB)"
  44. curl -L -s -o "$MODELS/ggml-small.en.bin" https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-small.en.bin \
  45. && WHISPER_MODEL="$MODELS/ggml-small.en.bin" || fail "whisper model"
  46. fi
  47. [[ -n "$WHISPER_MODEL" ]] && ok "Whisper model: $WHISPER_MODEL"
  48. # 6. Face detector model (YuNet, ~230 KB) used to find the facecam box
  49. YUNET="$MODELS/face_detection_yunet_2023mar.onnx"
  50. if [[ ! -f "$YUNET" ]]; then
  51. inst "YuNet face detector"
  52. curl -L -s -o "$YUNET" https://github.com/opencv/opencv_zoo/raw/main/models/face_detection_yunet/face_detection_yunet_2023mar.onnx || fail "YuNet model"
  53. fi
  54. [[ -s "$YUNET" ]] && ok "Face detector" || fail "Face detector"
  55. # 7. Fonts (macOS ships these)
  56. [[ -f "/System/Library/Fonts/Supplemental/Arial Black.ttf" ]] && ok "Caption font (Arial Black)" || fail "Arial Black font"
  57. # 8. Free space check: audio-only download keeps this small, but warn early
  58. FREE_GB=$(df -g "$SKILL_DIR" | awk 'NR==2{print $4}')
  59. if (( FREE_GB < 3 )); then echo " [warn] Only ${FREE_GB} GB free. Each stream needs ~0.5-1 GB while it runs."; else ok "Disk space (${FREE_GB} GB free)"; fi
  60. cat > "$SKILL_DIR/config.json" <<EOF
  61. {"whisper_model": "$WHISPER_MODEL", "yunet_model": "$YUNET"}
  62. EOF
  63. if [[ $FAILED -eq 0 ]]; then
  64. date > "$SKILL_DIR/.ready"
  65. echo; echo "READY. Say: clip this stream <link> or find me today's biggest GTA 6 streams and clip them"
  66. else
  67. rm -f "$SKILL_DIR/.ready"; echo; echo "NOT READY: fix the [MISSING] items above and re-run setup."; exit 1
  68. fi

Ratings and comments

Sign in to rate this skill.

Sign in

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