ai-video-gen · sundial-org — Claude Code skill: what it does, how to install
ai-video-gen produces full AI videos from text prompts by orchestrating image generators, video synthesis engines, and FFmpeg.
no license 155 installs ★ 675 updated 2026-03-07
npx skills add sundial-org/awesome-openclaw-skills --skill ai-video-gen -a claude-codeWhat ai-video-gen does
This tool stitches together the whole pipeline from prompt to finished clip. Dedicated Python scripts handle specific stages: generate_video.py orchestrates the entire text-to-video workflow, images_to_video.py stitches still frames into a video track, add_voiceover.py adds narration, and multi_scene.py merges multiple prompts into one cut.
The underlying processes rely on third-party providers. Image creation hooks into DALL-E 3, Stable Diffusion, or Flux. Motion synthesis goes through Runway, LumaAI Dream Machine, or Replicate, while speech uses OpenAI TTS or ElevenLabs. Assembling final transitions and overlays relies on FFmpeg.
Running these scripts requires active API tokens configured in your .env file, alongside an existing FFmpeg installation on your machine.
What it helps with
- produce a complete narrated video directly from a text prompt
- compile a sequence of still frames into an MP4 file
- chain several distinct scenes into a continuous clip
- attach generated speech narration to an existing video
Example prompts for the agent
- Run generate_video.py with the prompt "Futuristic city at night" and save it to future.mp4
- Convert frame1.png, frame2.png, and frame3.png into a video at 24 fps using images_to_video.py
- Attach spoken narration to input.mp4 with add_voiceover.py
How to install ai-video-gen
1Skills CLI (Vercel)
npx skills add sundial-org/awesome-openclaw-skills --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 sundial-org/awesome-openclaw-skills --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 sundial-org/awesome-openclaw-skills --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 sundial-org/awesome-openclaw-skills skills/ai-video-gen2Manually: put the files in place
.github/skills/ai-video-gen/SKILL.md1Skills CLI (Vercel)
npx skills add sundial-org/awesome-openclaw-skills --skill ai-video-gen -a gemini-cli2Platform CLI
gemini skills install https://github.com/sundial-org/awesome-openclaw-skills --path 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 sundial-org/awesome-openclaw-skills --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 to install ai-video-gen in Claude Code?
Run npx skills add sundial-org/awesome-openclaw-skills --skill ai-video-gen -a claude-code in your terminal.
What does ai-video-gen do?
It orchestrates AI models for still images, video generation, and voice synthesis, then stitches everything via FFmpeg.
What dependencies are required to run the scripts?
Install the Python packages openai, requests, pillow, replicate, and python-dotenv, and ensure FFmpeg is available.
Similar skills
All skills for AI and ML →ai-video-gen by other authors comes first.