ai-video-gen — Claude Code skill: generate video from a prompt
This skill turns a text prompt into a video through several provider gateways. Useful when you need a clip without juggling a handful of vendor sites.
npx skills add calesthio/OpenMontage --skill ai-video-gen -a claude-codeWhat ai-video-gen does
The skill gives the agent one entry point for video generation: a prompt, an aspect ratio, and optionally a reference image for image-to-video plus a tail frame. Providers include VEO, Kling, Sora, Runway, Seedance, MiniMax and Gemini Omni. You do not pick between them by hand — video_selector checks availability, compares cost and falls back automatically.
Access runs through three gateways. HeyGen (HEYGEN_API_KEY) covers VEO 3.1, Kling Pro, Sora v2, Runway Gen-4 and Seedance; fal.ai (FAL_KEY) covers Seedance 2.0, Kling, MiniMax and VEO; the Gemini API (GEMINI_API_KEY or GOOGLE_API_KEY) covers Gemini Omni Flash. Without at least one of those keys the skill has nothing to call, so set one before the first run.
Editing an existing clip — adding or removing an object, restyling, changing lighting or on-screen text — is where Gemini Omni Flash is the only option: stateful multi-turn editing is unique to it in this set. Regenerating from scratch works on any provider.
What it helps with
- generate a video from a text description
- turn a reference image into a clip
- pick a provider that fits the budget and look
- edit a finished clip without regenerating it
- compare generation cost across providers
Example prompts for the agent
- Generate a video: a drone shot over a coastal city at sunset, 16:9
- Make a clip from
shot.pngand add camera movement - Remove an object from this clip and change the lighting to evening
How to install ai-video-gen
1Skills CLI (Vercel)
npx skills add calesthio/OpenMontage --skill ai-video-gen -a claude-code2Manually: put the files in place
~/.claude/skills/ai-video-gen/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/ai-video-gen/
1Skills CLI (Vercel)
npx skills add calesthio/OpenMontage --skill ai-video-gen -a codex2Manually: put the files in place
.agents/skills/ai-video-gen/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add calesthio/OpenMontage --skill ai-video-gen -a cursor2Manually: put the files in place
.cursor/skills/ai-video-gen/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install calesthio/OpenMontage ai-video-gen2Manually: put the files in place
.github/skills/ai-video-gen/SKILL.md1Skills CLI (Vercel)
npx skills add calesthio/OpenMontage --skill ai-video-gen -a gemini-cli2Platform CLI
gemini skills install https://github.com/calesthio/OpenMontage --path .claude/skills/ai-video-genManually: put the files in place
.devin/skills/ai-video-gen/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add calesthio/OpenMontage --skill ai-video-gen -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about ai-video-gen
How do I install ai-video-gen in Claude Code?
Run npx skills add calesthio/OpenMontage --skill ai-video-gen -a claude-code. The skill lands at ~/.claude/skills/ai-video-gen/SKILL.md.
What does ai-video-gen do?
It generates video from a text prompt through the HeyGen, fal.ai and Gemini API gateways. It also handles image-to-video from a reference image and edits of existing clips via Gemini Omni Flash.
What do I need for it to work?
One of HEYGEN_API_KEY, FAL_KEY, GEMINI_API_KEY or GOOGLE_API_KEY. Whichever gateway is configured is the one that gets used.
