Video Extend
Lengthen an existing Google Veo 3.1 clip or chain the next narrative beat via RunComfy’s extend-video CLI without hand-rolling video API jobs.
Overview
Video Extend is an agent skill for the Build phase that continues Google Veo 3.1 clips through RunComfy’s extend-video CLI using a source video plus a next-beat prompt.
Install
npx skills add https://github.com/runcomfy-com/skills --skill video-extendWhat is this skill?
- Routes to Google Veo 3-1 `extend-video` and `fast/extend-video` on RunComfy Model API
- Continues a seed clip with consistent motion, lighting, and subject identity using a forward-looking prompt
- Supports chained shot-by-shot narratives when each new segment extends the previous output
- Allowed tool surface: Bash(`runcomfy *`) with documented invoke patterns
- Triggers on extend, continue, longer clip, Veo extend, and video continuation wording
- Two extend routes documented: standard and fast/extend-video on Veo 3-1
Adoption & trust: 113k installs on skills.sh; 1 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have a strong short Veo clip but hit the per-call length limit and need more footage without losing motion, lighting, or character identity.
Who is it for?
Builders already generating with Veo 3.1 on RunComfy who want shot chains, longer demos, or narrative extensions from one seed video.
Skip if: Users who only need fresh text-to-video from scratch with no source clip, or workflows that cannot grant Bash access to `runcomfy`.
When should I use this skill?
User asks to extend video, continue video, make a clip longer, Veo extend, chain video shots, video continuation, or explicitly extend an existing video on RunComfy.
What do I get? / Deliverables
The agent invokes the documented Veo extend-video endpoint with your seed clip and continuation prompt, yielding a longer or chained clip ready for the next extend pass if needed.
- Extended video clip continuing the source with matched motion and identity
- Optional chained segment outputs for multi-shot narratives
Recommended Skills
Journey fit
Build is the primary phase because extending clips is production work on generative video assets while you iterate on demos, ads, or product storytelling. Integrations matches a Bash-gated `runcomfy run` bridge to Veo 3-1 `extend-video` and `fast/extend-video` endpoints.
How it compares
Continuation skill for an existing Veo asset—not a general multi-model text-to-video picker or desktop NLE timeline editor.
Common Questions / FAQ
Who is video-extend for?
Solo builders and creators using agent coding tools with RunComfy CLI who generate with Google Veo 3.1 and need longer or sequential clips from a starting video.
When should I use video-extend?
Use it in Build when you have a short Veo clip and want it longer, or when you are chaining narrative shots by extending the latest output with a prompt for what happens next.
Is video-extend safe to install?
It requires Bash to run `runcomfy` against remote APIs; check the Security Audits panel on this page and limit shell permissions in repos that should not call external generation services.
SKILL.md
READMESKILL.md - Video Extend
# Video Extend Continue an existing video clip past its per-call duration cap, or chain a narrative shot-by-shot from a single seed. This skill routes to Google Veo 3-1's `extend-video` endpoints and ships the documented prompting patterns + the exact `runcomfy run` invoke. [runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-extend) · [Veo 3-1 extend-video](https://www.runcomfy.com/models/google-deepmind/veo-3-1/extend-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-extend) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-extend) ## Powered by the RunComfy CLI ```bash # 1. Install (see runcomfy-cli skill for details) npm i -g @runcomfy/cli # or: npx -y @runcomfy/cli --version # 2. Sign in runcomfy login # or in CI: export RUNCOMFY_TOKEN=<token> # 3. Extend runcomfy run google-deepmind/veo-3-1/extend-video \ --input '{"video_url": "https://...", "prompt": "..."}' \ --output-dir ./out ``` CLI deep dive: [`runcomfy-cli`](https://www.skills.sh/agentspace-so/runcomfy-agent-skills/runcomfy-cli) skill. --- ## Pick the right endpoint Listed newest first. Both endpoints are Google Veo 3-1; pick by quality/latency trade-off. **Veo 3-1 Extend** — `google-deepmind/veo-3-1/extend-video` *(default)* > Continues an existing Veo clip with consistent motion, lighting, identity, and physics. > Pick for: hero-quality extends, final-delivery cuts, chained narrative shots that need to look like one continuous take. > Avoid for: cost-sensitive iteration — drop to **Veo 3-1 Fast Extend**. **Veo 3-1 Fast Extend** — [`google-deepmind/veo-3-1/fast/extend-video`](https://www.runcomfy.com/models/google-deepmind/veo-3-1/fast/extend-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-extend) > Faster Veo 3-1 extend at lower per-call cost. > Pick for: iteration on extend compositions, multi-shot drafts. > Avoid for: final delivery — use full **Veo 3-1 Extend**. The agent picks one and supplies the source video URL + a continuation prompt. --- ## Route: Veo 3-1 Extend **Model**: `google-deepmind/veo-3-1/extend-video` (or `/fast/extend-video`) **Catalog**: [Veo 3-1 extend](https://www.runcomfy.com/models/google-deepmind/veo-3-1/extend-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-extend) · [Veo 3-1 fast extend](https://www.runcomfy.com/models/google-deepmind/veo-3-1/fast/extend-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-extend) · [`veo-3` collection](https://www.runcomfy.com/models/collections/veo-3?utm_source=skills.sh&utm_medium=skill&utm_campaign=video-extend) ### Invoke ```bash runcomfy run google-deepmind/veo-3-1/extend-video \ --input '{ "video_url": "https://your-cdn.example/source-clip.mp4", "prompt": "The camera continues pushing in slowly. The character looks down at the object, then turns toward the window. Soft daylight, no other motion in the background." }' \ --output-dir ./out ``` ### Prompting tips - **The source video provides identity, lighting, fra