Cinematic Video Prompt Skill
A skill with a 700-plus term film vocabulary for AI video prompts: angles, camera moves, lighting, composition and color.
- 185 ★ on the repository
- Last commit
- MIT
Minimal access
Why this level
- The skill works with prompt text only and calls no external services.
Install
- Works in
In your terminal, with SkillFoxx CLI
npx skillfoxx add skills/cinematic-video-prompt-skillDetects the agents on your machine, shows the access level and pins the version.
Other ways to install
Access and checks
How we reviewMinimal accessThe tool runs nothing and makes no network calls.
- The skill works with prompt text only and calls no external services.
This is third-party code. Review the repository files before installing.
What it does
Cinematic Video Prompt Skill teaches the model a professional cinematographer's vocabulary so prompts for video and image generation do not stay vague like a nice cinematic scene. The vocabulary is model-agnostic and fits Veo 3 and Google Flow, Kling, Sora, Runway Gen-4, Hailuo, Luma, Pika, Midjourney, Stable Diffusion, Flux and Nano Banana. `SKILL.md` holds the workflow, a prompt formula (shot size and angle, subject, action, setting and weather, lighting, camera movement, style and color, mood, technical parameters), condensed keyword tables, ready combinations per video type, a mood lookup, a pre-flight checklist and notes on what video models commonly get wrong. The `references/` files cover more than 70 angles and shot sizes, 60 camera movements, 80 lighting terms, 80 composition rules, lenses, film stocks, styles, color palettes and materials. Two bonus skills: a character reference sheet for consistent heroes across clips and Chinese-fantasy scenes.
Who it is for. Short-video directors, marketers and AI-video creators who need precise prompts for Veo, Kling or Sora instead of luck on the first try.
Good fit when
- A rainy scene is described with exact angle, lighting and camera movement.
- A ready combination for the video type is taken for Kling and Veo.
- A hero is kept consistent across clips through a character sheet.
- The prompt checklist is run before a paid generation.
Not a fit when
- The video generation itself is needed, while the skill only writes prompts.
- The model does not read English prompts.
- Strictly documentary footage with no stylization is required.
Example request
Write a Veo 3 prompt for a rainy night street, low angle, slow dolly in, neon light, 8 seconds.Limitations
The skill writes and improves prompts but does not create video or call video models. The vocabulary targets models that read English prompts, and Vietnamese explanations exist only in the human-facing references. Results depend on the specific video model: the formula cuts vagueness but does not guarantee repeatability. The skill's rules limit a clip to one camera move and one main action and about eight technical words. The last commit is from late September 2026.
How to disable. Delete the `~/.claude/skills/cinematic-video-prompt` folder and the copied `character-sheet-lite` and `oriental-scene-lite` bonus skills.
FAQ
What is the prompt formula?
Shot size and angle, subject and appearance, action, setting and weather, lighting, camera movement, style and color, mood, technical parameters, in that order.
Which models does the vocabulary support?
It is model-agnostic and works with Veo 3 and Google Flow, Kling, Sora, Runway Gen-4, Hailuo, Luma, Pika, Midjourney, Stable Diffusion, Flux and Nano Banana.
How do I use it in Claude.ai?
Zip the folder with `SKILL.md` at the archive root and upload it under Settings, Capabilities, Skills.
What do the bonus skills do?
`character-sheet-lite` makes a character sheet with three full-body views and a close-up for hero consistency. `oriental-scene-lite` writes Chinese-fantasy scenes.
How many technical keywords belong in a prompt?
By the skill's rules no more than eight, with one camera move and one main action per clip. Style, color and mood must point the same way.
Discussion
No questions or reviews yet.
Related
SkillsA skill that writes structured prompts for Seedance, Kling, Veo and Sora: a home-footage look, camera flaws, a timeline and sound
A skill that turns a plot or scene into a cinematic AI video prompt for 6 to 30 seconds, with shots, performance and sound.
Skill for staging fight scenes: an idea becomes a battle plot, move design and a shot-by-shot storyboard.
video-production-skill takes an agent from script to video: slides, speech-verified narration, subtitles and a cover.
A director skill for AI video: turns a script into a shot list, keyframes and motion prompts for Runway, Kling and Veo
Seven AI video skills: promo film planning, scene and fight prompts, acting direction and generation task reliability checks.
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Repository stars | Main difference |
|---|---|---|---|
| Cinematic Video Prompt Skill (this card) | no | 185 | |
| Cinematic Video Prompt Engineer | no | 148 | turns a story into a finished 6 to 30 second prompt; this one is a vocabulary and formula for composing prompts for any model |
| Cinematic Director Skill | no | 352 | builds storyboards and key frames for video services; this one is a film terminology reference |
README in short
A large structured cinema vocabulary plus a formula, ready combinations and a list of video-model mistakes.