From clip-maker
Create vertical clips from a video. Full pipeline: transcribe → find moments → crop → cut → subtitles → copy. Use when the user invokes /clip-maker.
How this skill is triggered — by the user, by Claude, or both
Slash command
/clip-maker:clip-makerThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
> Converted from Claude Code command `/clip-maker`.
Converted from Claude Code command
/clip-maker. Review and adapt: hooks and MCP tool IDs may need manual mapping for Codex.
Create vertical (9:16) clips from a horizontal video, optimized for Reels/Shorts/TikTok.
Parse $ARGUMENTS for:
<video_path_or_url> — required, path to source video OR YouTube/web URL--duration N — target clip duration in seconds (default: 60)--auto — skip manual moment selection, use all found moments--no-subtitles — don't burn subtitles into clips--api — use OpenAI Whisper API instead of local whisper--no-copy — skip social media copy generation--language LANG — transcription language (default: ru)--prompt "terms" — domain-specific terms for whisper (improves recognition of jargon, names, abbreviations)Execute steps sequentially. Report progress to the user after each step.
bash plugins/clip-maker/scripts/install-deps.sh [--api if user passed --api]
If it fails, stop and report what's missing.
If <video_path> looks like a URL (starts with http://, https://, or youtube.com, youtu.be):
VIDEO_PATH=$(bash plugins/clip-maker/scripts/download-video.sh "<url>" ~/Downloads)
The script outputs the downloaded file path. Use it as <video_path> for subsequent steps.
Create output directory next to the video: {video_dir}/{video_name}_clips/
bash plugins/clip-maker/scripts/transcribe.sh "<video_path>" "<output_dir>" [--api] [--language LANG] [--prompt "terms"]
This produces <output_dir>/transcript.json.
Launch the moment-finder agent:
Agent(subagent_type="clip-maker:moment-finder", model="opus", prompt="
Analyze the transcript and find the most engaging moments for vertical clips.
- Transcript path: <output_dir>/transcript.json
- Target clip duration: <duration> seconds
- Output path: <output_dir>/moments.json
Read the transcript, find the best moments, and write moments.json.
")
If --auto is NOT set:
moments.jsonmoments.json to only include selected momentsIf --auto IS set: proceed with all moments.
bash plugins/clip-maker/scripts/extract-frames.sh "<video_path>" "<output_dir>/moments.json" "<output_dir>"
Launch the crop-analyzer agent:
Agent(subagent_type="clip-maker:crop-analyzer", model="sonnet", prompt="
Analyze frames to determine optimal crop positions for vertical clips.
- Frames directory: <output_dir>/frames/
- Source video dimensions: [get from ffprobe]
- Output path: <output_dir>/crop_coords.json
Read each moment's frames, locate the speaker, and write crop_coords.json.
")
bash plugins/clip-maker/scripts/cut-clip.sh "<video_path>" "<output_dir>/moments.json" "<output_dir>/crop_coords.json" "<output_dir>"
bash plugins/clip-maker/scripts/burn-subtitles.sh "<output_dir>/moments.json" "<output_dir>/transcript.json" "<output_dir>"
Launch the copywriter agent:
Agent(subagent_type="clip-maker:copywriter", model="sonnet", prompt="
Generate social media descriptions for the clips.
- Moments: <output_dir>/moments.json
- Output: <output_dir>/copy.md
Read moments.json and write copy.md with platform-specific descriptions.
")
Create <output_dir>/manifest.json with metadata for all clips:
{
"source": "<video_path>",
"created": "<timestamp>",
"clips": [
{
"file": "clip_01.mp4",
"title": "...",
"start": 125.4,
"end": 183.2,
"duration": 57.8,
"has_subtitles": true
}
]
}
Report final summary:
Remove intermediate files:
<output_dir>/frames/ directory<output_dir>/transcript.json — keep (useful reference)<output_dir>/moments.json — keep (useful reference)<output_dir>/crop_coords.json — removeProvides UI/UX resources: 50+ styles, color palettes, font pairings, guidelines, charts for web/mobile across React, Next.js, Vue, Svelte, Tailwind, React Native, Flutter. Aids planning, building, reviewing interfaces.
Fetches up-to-date documentation from Context7 for libraries and frameworks like React, Next.js, Prisma. Use for setup questions, API references, and code examples.
npx claudepluginhub ivanlutsenko/awac-ai-agent-plugins --plugin clip-maker