Video edit cli
Edit, inspect, transcribe, cut, master, or package video and audio media with the headless `video-edit-cli` CLI. Use when the user asks to edit a recording, cut a video, inspect unfamiliar media, extract audio, preview a range, synchronize cameras, make a vertical clip, or produce podcast/episode deliverables.From its SKILL.md
npx -y skills add computerlovetech/video-edit-cli --skill video-edit-cliAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
2 things to look at
- 28 days oldThe repository was created 28 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
3.9 KB, 815 tokens by cl100k_base, as published. Nobody here has run it
You are the editor; the video-edit-cli CLI is your workbench. It exposes atomic,
deterministic primitives that print one JSON result on stdout. You form the
editorial plan yourself — no command decides what to keep, remove, or highlight.
Run video-edit-cli --help (and --help on any subcommand) for the authoritative
command surface; inside this repository run it as uv run video-edit-cli ….
If video-edit-cli is not on PATH, install it first with
uv tool install video-edit-cli (Apple Silicon transcription:
uv tool install 'video-edit-cli[mlx]'); ffmpeg and ffprobe must already be
installed separately.
Invariants (hold for every task)
- Source media is immutable. Never overwrite, re-encode in place, or delete an
original. Every derived file is new and keeps its
*.provenance.jsonsidecar. - Evidence before edits: never act on a range you have not inspected through metadata, transcript, frames, waveform, or preview.
- Validate before rendering; preview before mastering when edits are material.
- Prefer the cheapest sufficient evidence:
probeand transcript first for dialogue; targeted visual/audio inspection only where a decision needs it.
Method
- Establish the outcome. Restate what deliverable is requested and what media exists. Done when you can name the requested outputs and every source file involved.
- Preflight the workflow. Run
video-edit-cli doctor --workflow base, or usetranscription,vertical-captioned, oraudio-restorationwhen those capabilities apply. Resolve failed dependency checks before expensive work. - Set up a workspace. Read references/workspace.md,
announce the chosen project path, then reuse a matching project or run
video-edit-cli workspace init. Default to<project-root>/video-edit-projects/YYYY-MM-DD-<source-id-or-slug>/edit/unless the user specifies another location. Done whenworkspace.jsonlists every source with its hash. - Inspect the media.
probeevery source; gather audio, proxies, frames, filmstrips, waveforms, or range previews as decisions require. For dialogue media read references/transcription.md and transcribe first. Done when you know each source's duration, streams, and content well enough to justify the plan you are about to form. - Plan and render. Read references/edit-plan.md before creating or modifying a plan; author the plan yourself, validate it, and render a preview. Done when the validated plan renders and its manifest exists.
- Review and revise. Read references/cut-review.md; inspect every boundary of any render you produced. Done when each cut passes or its defect is fixed or explicitly reported.
- Finish the deliverable. Done when every requested output passes technical
validation and the required visual/editorial review.
output validatedoes not inspect framing or editorial quality; report those reviews separately.
Branch references (read when the condition applies)
- Audio cleanup/mastering requested, or analysis finds degraded speech → references/audio-restoration.md
- Packaged deliverable (project profile, subtitles, assets, music, master render) → references/subtitles-and-assets.md
- Multiple synchronized visual/audio sources → references/multicamera.md
- Vertical or short-form deliverable → references/vertical-video.md
What ships with it: 9 files
17.6 KB alongside SKILL.md
agents/
- openai.yaml207 B
references/
- audio-restoration.md3.2 KB
- cut-review.md1.8 KB
- edit-plan.md1.7 KB
- multicamera.md1.5 KB
- subtitles-and-assets.md2.7 KB
- transcription.md1.5 KB
- vertical-video.md2.7 KB
- workspace.md2.3 KB