Core A-roll rough cut pipeline. Uses faster-whisper (with openai-whisper as fallback) for word-level transcription, combined with the final script and storyboard to perform conservative rough cuts via FFmpeg, outputting EDL, rough cut previews, transcription cache, and rough cut handoff files. Trigger words: rough cut, transcribe, cut voice-over, cut video by script.
Huanyu-Hibiki/Huanyu-Skills is a specialized AI agent skill designed to automate the core A-roll rough cut pipeline in video production and editing workflows. It streamlines the process of turning a final script and storyboard into a rough video edit by first performing word-level transcription using faster-whisper (or openai-whisper as a fallback). Then, it intelligently aligns the transcription with the script to determine cut points and uses FFmpeg to produce conservative rough cuts, ensuring no essential content is lost. The skill outputs several key deliverables: an EDL (Edit Decision List) for importing into professional editing software, a rough cut preview video, a transcription cache for future reference, and a rough cut handoff file for seamless collaboration. It is primarily designed for AI agent platforms like Claude Code or Cursor, and its trigger phrases include "rough cut", "transcribe", "cut voice-over", and "cut video by script", making it easy to invoke via natural language commands.
npx skills add https://github.com/Huanyu-Hibiki/Huanyu-Skills/tree/main/video-production-workflow/skills/video-rough-cutCore A-roll rough cut pipeline. Uses faster-whisper (with openai-whisper as fallback) for word-level transcription, combined with the final script and storyboard to perform conservative rough cuts via FFmpeg, outputting EDL, rough cut previews, transcription cache, and rough cut handoff files. Trigger words: rough cut, transcribe, cut voice-over, cut video by script.
Extract frames or short clips from videos using ffmpeg.
Summarize or transcribe URLs, YouTube/videos, podcasts, articles, transcripts, PDFs, and local files.
Use when testing, fixing, or extending the OpenClaw Control UI GUI with Vitest + Playwright end-to-end checks, mocked Gateway WebSocket flows, mocked dashboard runs, screenshots/videos, or agent-verifiable browser proof.
Obra superpowers agent skills.
See, Understand, Act on video and audio. See- ingest from local files, URLs, RTSP/live feeds, or live record desktop; return realtime context and playable stream links. Understand- extract frames, build visual/semantic/temporal indexes, and search moments with timestamps and auto-clips. Act- transcode and normalize (codec, fps, resolution, aspect ratio), perform timeline edits (subtitles, text/image overlays, branding, audio overlays, dubbing, translation), generate media assets (image, audio...
End-to-end marketing campaign planning and execution. Covers audience research, positioning, campaign angle definition, landing page copy, email sequences, social posts, ad copy, short-form video scripts, and content calendars. Use as the orchestration layer for multi-channel product launches. Use when planning or executing a multi-channel product launch, or producing landing page, email, social, or ad copy.