Video Edit
Route natural-language video edit requests to the right RunComfy edit model and run jobs through the local RunComfy CLI without guessing which endpoint fits each transform.
Overview
Video Edit is an agent skill most often used in Build integrations (also Grow content, Launch distribution) that routes video transformation requests to the appropriate RunComfy edit model and runs them via the RunComfy
Install
npx skills add https://github.com/agentspace-so/runcomfy-agent-skills --skill video-editWhat is this skill?
- Intent router picks Wan 2.7 Edit-Video, Kling 2.6 Motion Control Pro, or Lucy Edit Restyle from the user’s ask
- Bundles model-specific prompting patterns to reduce wrong-model iteration
- Triggered by phrases like restyle video, background swap, motion control, and outfit swap
Adoption & trust: 211k installs on skills.sh; 15 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You know what change you want in an existing clip but not which RunComfy edit model or prompt pattern will preserve identity and motion without wasted runs.
Who is it for?
Solo builders who already use RunComfy, have reference or source videos, and want an agent to pick the edit endpoint and phrasing instead of trial-and-error across the catalog.
Skip if: Teams that need offline-only editing, full NLE timelines in DaVinci or Premiere, or guaranteed results without RunComfy account setup and CLI configuration.
When should I use this skill?
User mentions video edit, edit video, restyle video, swap video background, motion control, outfit swap video, or any explicit ask to transform existing video via RunComfy.
What do I get? / Deliverables
You get a CLI-driven edit job aimed at the matched Wan, Kling, or Lucy endpoint with guidance aligned to that model’s documented prompting approach.
- RunComfy CLI invocation targeting the selected edit model endpoint
- Edited video output from the completed RunComfy job
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
The skill’s core value is wiring an agent to RunComfy’s edit catalog via CLI—primary shelf is Build integrations, where solo builders connect creative pipelines to external generative services. Integrations is the correct subphase because execution is `runcomfy run <vendor>/<model>/<endpoint>` against hosted models, not in-repo frontend or backend code.
Where it fits
Wire your agent to restyle a product walkthrough clip through RunComfy without manually comparing Wan versus Lucy endpoints.
Batch outfit or packaging swaps on UGC-style videos for a content calendar while preserving face and motion.
Adapt one hero demo into platform-specific variants by swapping backgrounds or motion-matched character performances.
How it compares
Use as an agent skill package that routes to RunComfy edit APIs—not a desktop video editor and not an MCP server abstraction.
Common Questions / FAQ
Who is video-edit for?
It is for solo and indie builders using coding agents who edit marketing, demo, or social video through RunComfy and want automatic model selection plus CLI execution.
When should I use video-edit?
Use it in Build when hooking generative video into your agent workflow; in Grow when restyling or swapping outfits for content batches; and in Launch when adapting clips for distribution—whenever you say video edit, restyle, background swap, motion control, or outfit swap on exis
Is video-edit safe to install?
Review the Security Audits panel on this Prism page for this skill package before installing; it invokes shell and network access through the RunComfy CLI and sends media to third-party models.
SKILL.md
READMESKILL.md - Video Edit
# Video Edit — Pro Pack on RunComfy [runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-edit) · [Wan 2.7 Edit-Video](https://www.runcomfy.com/models/wan-ai/wan-2-7/edit-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-edit) · [Kling Motion-Control Pro](https://www.runcomfy.com/models/kling/kling-2-6/motion-control-pro?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-edit) · [Lucy Edit Restyle](https://www.runcomfy.com/models/decart/lucy-edit/restyle?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-edit) · [GitHub](https://github.com/agentspace-so/runcomfy-skills/tree/main/video-edit) **Video edit, intent-routed.** This skill doesn't lock you to one model — it picks the right video-edit model in the RunComfy catalog based on what the user actually wants: general restyle, motion transfer from a reference clip, or lightweight identity-stable outfit / background swap. ```bash npx skills add agentspace-so/runcomfy-skills --skill video-edit -g ``` ## Pick the right model for the user's intent | User intent | Model | Why | |---|---|---| | Restyle a talking-head video — preserve face / pose / lip movement | **Wan 2.7 Edit-Video** | Strong identity + motion preservation; supports up to 1080p | | Swap product background, keep camera motion | **Wan 2.7 Edit-Video** | Camera motion preserved; one-direction edit honored | | Replace packaging design using a reference image | **Wan 2.7 Edit-Video** + `reference_image` | Reference-conditioned design transfer | | Apply cinematic color grade / commercial polish | **Wan 2.7 Edit-Video** | Good at single-direction global look changes | | **Transfer precise motion** from a reference video to a target character | **Kling 2.6 Pro Motion Control** | Designed for motion mapping with identity hold | | Lip-sync motion of a target character to source video's lip movement | **Kling 2.6 Pro Motion Control** | Built for tight temporal coherence | | **Lightweight outfit / costume swap** with identity preservation | **Lucy Edit Restyle** | Core strength is localized identity-stable edits | | **Identity-stable restyle** ("astronaut in desert", "warm golden-hour lighting") | **Lucy Edit Restyle** | Specializes in temporal consistency for restyle | | Default if unspecified | **Wan 2.7 Edit-Video** | Most versatile, highest resolution | The agent reads this table, classifies the user's intent, and picks the matching subsection below. ## Prerequisites 1. **RunComfy CLI** — `npm i -g @runcomfy/cli` 2. **RunComfy account** — `runcomfy login`. 3. **CI / containers** — set `RUNCOMFY_TOKEN=<token>`. 4. **A source video URL** — formats and limits depend on the chosen route. --- ## Route 1: Wan 2.7 Edit-Video — default for restyle / background / packaging **Model**: `wan-ai/wan-2-7/edit-video` ### Schema | Field | Type | Required | Default | Notes | |---|---|---|---|---| | `prompt` | string | yes | — | Lead with preservation. One edit direction per call. | | `video` | string | yes | — |