video-edit
Agent skill from skills-collective/skills.
What it does
- Preservation goals first: "Preserve [face / pose / motion / framing / lip movement]; [then state the change]".
- One edit direction per call. Compound edits drift on motion.
- referenceimage only when justified (packaging swap, costume swap with target visual). Don't pass refs for general restyle.
- audiosetting: "origin" for talking-head where you don't want soundtrack regenerated.
- Source video constraints: 2–10s, ≤100MB.
- Subject must be > 5% of frame in the image reference for clean identity hold.
- Spatial constraints help: "character on left side, background motion right".
Requirements & configuration
- 3. CI / containers — set RUNCOMFYTOKEN=<token>.
- | 77 | not signed in or token rejected |
- Token storage: runcomfy login writes the API token to ~/.config/runcomfy/token.json with mode 0600 (owner-only read/write). Set RUNCOMFYTOKEN env var to bypass the file entirely in CI / containers.
Configuration: RUNCOMFY_TOKEN
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
Source
Repository: https://github.com/skills-collective/skills
video-edit FAQ
What does the video-edit skill do?
> Edit existing video on RunComfy — this skill is a smart router that matches the user's intent to the right edit model in the RunComfy catalog. Picks Wan 2.7 Edit-Video (general restyle / background swap / packaging swap, identity + motion preservation), Kling 2.6 Pro Motion Control (transfer precise motion from a reference video to a target character), or Lucy Edit Restyle (lightweight identity-stable restyle / outfit swap). Bundles each model's documented prompting patterns so the skill gets sharper edits without burning iterations on the wrong model. Calls `runcomfy run <vendor>/<model>/<endpoint>` through the local RunComfy CLI. Triggers on "video edit", "edit video", "restyle video", "swap video background", "motion control", "outfit swap video", or any explicit ask to transform a video. Preservation goals first: "Preserve [face / pose / motion / framing / lip movement]; [then state the change]". One edit direction per call. Compound edits drift on motion.
What does video-edit require?
3. CI / containers — set RUNCOMFYTOKEN=<token>. | 77 | not signed in or token rejected | Token storage: runcomfy login writes the API token to ~/.config/runcomfy/token.json with mode 0600 (owner-only read/write). Set RUNCOMFYTOKEN env var to bypass the file entirely in CI / containers. Configuration keys: RUNCOMFY_TOKEN.
How do I install video-edit?
Run: npx -y skills add https://github.com/skills-collective/skills --skill video-edit --agent claude-code — the source lives at github.com/skills-collective/skills.
Maintain video-edit?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/skills/skills-collective-skills-video-edit?ref=badge) npx agentictools info skills/skills-collective-skills-video-edit The second line is the CLI lookup for this page — handy in READMEs and docs.
