Communitygithub.com

video-edit

Video and animation skill. Edit original footage (talking head, screen recording, interview, raw clips) into a tight video that keeps the speaker's real voice. Transcribes, removes retakes and dead air without changing meaning, adds relevant explanatory graphics that never cover faces or key screen content, captions, mixes and renders; supports frame-specific revision notes. Use when the user uploads footage or a finished video to improve.

What is video-edit?

video-edit is a Claude Code agent skill that video and animation skill. Edit original footage (talking head, screen recording, interview, raw clips) into a tight video that keeps the speaker's real voice. Transcribes, removes retakes and dead air without changing meaning, adds relevant explanatory graphics that never cover faces or key screen content, captions, mixes and renders; supports frame-specific revision notes. Use when the user uploads footage or a finished video to improve.

Works with~Claude Code~Codex CLI~Cursor
npx skills add https://github.com/Blaise-Muhune/video-studio-starter/tree/HEAD/claude-skills/video-edit

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

/video-edit

Inputs: $0 slug, footage file(s) copied into projects/<slug>/assets/footage/ (on the user's computer via the device bridge, or uploads). Optional: brief, notes with timestamps. Outputs: renders/<slug>_vN.mp4, EDIT.md (paper edit + EDL), captions (assets/captions.srt), review files.

Load only

  • docs/editing-and-compositing.md § Editing original footage, § Audio
  • styles/talking-head-editorial.md
  • docs/quality-assurance.md before reviewing

Procedure

  1. Ingest: python tools/ingest_reference.py $0 assets/footage/<file> --name raw --transcribe gives shots, keyframes, loudness and a word-timed transcript (needs pip install faster-whisper). Inspect refs/raw/contact.png.
  2. Paper edit (EDIT.md): list phrases with [in–out]. Mark retakes (keep the last clean one), false starts, filler and long pauses. Cut-safety rules: gaps ≥400 ms are clean cut points; 150–400 ms only after checking frames; never cut inside <150 ms; pad 30–200 ms; keep thought-pauses ≤0.35 s. Never reorder words in a way that changes a claim. Never speed up speech.
  3. The user's voice is the narration. Clean it: high-pass 80 Hz, compression 2.5:1, loudness to the master. Don't replace it with TTS unless asked.
  4. Graphics where they help: define a term, show a number (sourced), draw a mechanism, highlight a screen region. Place them in the opposite third from the face, or cut to full-screen graphics while the voice continues. Never cover faces or important screen content (check the face box in keyframes).
  5. Build engine/src/projects/<slug>/Scene.tsx with an EDL array [{src, in, out}] → <OffthreadVideo> sequences, plus graphic overlays anchored to transcript words (put the transcript segments in timeline.json narration, then cues as usual).
  6. Captions: word-timed, 1–2 lines, ≤ 32 characters per line, inside safe areas, never duplicating on-screen kinetic type.
  7. Mix (audio_mix.py with the cleaned dialogue as audio/narration.wav), render, /video-review, revise.
  8. Frame-specific feedback: when the user says "at 0:12 the graphic covers my hand", extract that frame, fix it, re-render, and show the before/after still.

Quality gates

  • Meaning preserved: diff the kept transcript vs the original; no altered claims
  • No jump-cut artefacts flagged as pops; no faces covered (check stills)
  • Footage, music and images used are owned or licensed (manifest)
  • Loudness −14 LUFS, dialogue intelligible (measure; ask the user to listen)

Individual skills in this repo

This repo contains 1 individual skill — each has its own dedicated page.

Related Skills