video-edit

Skill

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…

Made forVisuals & motion

What you needNode.js and an AI client that supports agent skills

Sources checked2026-11-02

Project links

skills.sh GitHub

How to use it

Run the install command in your project folder.
Restart your AI client so it picks up the skill.
Ask for a task that matches the description to try it.

Copy setup details

Use these instructions in your own environment. Copying text here does not run it.

Install command

Run on your own machine to install this skill.

npx skills add https://github.com/genmedia-labs/skills --skill video-edit

Security checks

Automated checks, last run Nov 2, 2026. They can miss problems and do not guarantee a listing is safe. Read the source and what you are asked to run before you use it.

NoteSnyk auditLayer 2
Snyk reported a warning with 2 issues.
Evidence (4)
Risk level
MEDIUM
Audited
Aug 13, 2026
W011 (medium)
Third-party content exposure detected (indirect prompt injection risk).
W012 (medium)
Unverifiable external dependency detected (runtime URL that controls agent).
Source: Snyk, as shown on skills.sh
PassedSetup commands and descriptionLayer 1
The install commands and description match none of the risky patterns we look for.
Source: AIWantsThis screening rules
PassedSkill instructions (SKILL.md)Layer 1
The skill file shows no hidden text, no instruction-override phrases and no risky commands.
Source: AIWantsThis screening rules
PassedGen Agent Trust Hub auditLayer 2
Gen Agent Trust Hub reported a pass for this skill.
Evidence (1)
Risk level
SAFE
Source: Gen Agent Trust Hub, as shown on skills.sh
PassedSocket auditLayer 2
Socket reported a pass for this skill.
Evidence (1)
Audited
Aug 13, 2026
Source: Socket, as shown on skills.sh
PassedSource repositoryLayer 2
The repository is public, not archived and has recent activity.
Evidence (3)
Last push
2026-09-07
Archived
no
License
MIT
Source: GitHub