Video prompt lab
Local-first AI-video prompt generator, linter, and eval kit. One ShotSpec YAML -> Sora/Veo/Runway/Kling/Seedance prompts.
npx -y skills add YYH123123813/video-prompt-lab --skill video-prompt-labAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
What its author says it does
Copied from the file, not written here
Generate, lint, and evaluate model-specific AI-video prompts from a ShotSpec YAML brief.
SKILL.md
0.8 KB, 172 tokens by cl100k_base, as published. Nobody here has run it
Video Prompt Lab Skill
Use when a user wants prompts for Sora, Veo, Runway, Kling, Seedance, Jimeng, or a generic AI-video model.
Workflow:
- Convert the idea into a ShotSpec YAML with title, goal, duration, aspect ratio, subject, scene, camera, motion, lighting, audio/dialogue, overlays, and negative constraints.
- Run
python3 video_prompt_lab.py <spec.yaml> --models veo,sora,kling,seedance --out outputs/<name>. - Review
lint-report.mdbefore spending generation credits. - Give the user the model-specific prompt files.
- After generation, fill
scorecard.mdand iterate based on the weakest dimension.
Do not treat prompt generation as final output. Treat it as a measurable production loop.