Stats
Actions
Tags
Help us improve
Share bugs, ideas, or general feedback.
From backend-skills
Generates structured Google Veo 3.1 video prompts by collecting user input for subject, action, style, cinematography, and audio using the Universal Prompt Formula.
npx claudepluginhub buyoung/skills --plugin backend-skillsHow this skill is triggered — by the user, by Claude, or both
Slash command
/backend-skills:veo-prompt-directorThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Domain knowledge for generating Google Veo 3.1 video prompts based on the Universal Prompt Formula.
Provides prompting techniques for Replicate AI video models including scene descriptions, camera shots, lighting, and cinematography terms. Use for writing video prompts or building generation features.
Generates AI videos using Google Veo models via nano-banana CLI for text-to-video, image animation, lip-sync dialogue, and scene extensions.
Acts as AI creative director for video production including product ads, short films, montages, TikTok e-commerce. Analyzes inputs, writes English prompts, generates assets, submits tasks.
Share bugs, ideas, or general feedback.
Domain knowledge for generating Google Veo 3.1 video prompts based on the Universal Prompt Formula.
| Element | Description | Example |
|---|---|---|
| Subject | The main subject. Noun + state/appearance combination | "a man standing in a dark alley" |
| Action | An observable, physical action performed by the subject. Emotions are not actions | "lowers his head and slowly steps backward" |
| Style | The overall tone/genre. 1–2 clear, non-conflicting choices | "film noir", "retro aesthetic" |
| Element | Description | Example |
|---|---|---|
| Cinematography | Camera movement + composition + lens/focus | "dolly shot, close-up, shallow focus" |
| Context | Location, time of day, background elements | "a rainy city alley at night" |
| Mood | Color tone, lighting, atmosphere | "blue-toned night lighting" |
| Audio | Dialogue, sound effects, ambient noise | See audio_directing.md |
| Duration | Clip length | 4s, 6s, 8s |
| Aspect Ratio | Frame orientation | 16:9 (landscape), 9:16 (portrait) |
| Negative Prompt | Elements to exclude (use affirmative descriptions of the desired opposite) | "clear sky, dry pavement" |
Formula: [Cinematography] + [Subject] + [Action] + [Context] + [Style & Ambiance]
Full spec, composition rules, and examples → prompt_formula.md
A generated prompt consists of:
components:
- settings: "{duration} | {aspect_ratio} | {resolution}"
- prompt: "assembled prompt string following the Universal Prompt Formula"
- negative_prompt: "optional — affirmative descriptions of elements to exclude"
- checklist: "per-element confirmation of which elements are included"
safety_filter:
scope: "Applies to both generated video and uploaded images"
mechanism: "Uses the same safety filters as the Gemini family"
effect: "Prompts violating policy produce no output — the video is not generated"
guidance: "Action/state/environment descriptions produce stable results; provocative language triggers blocking"
digital_watermark:
technology: SynthID
scope: "All Veo-generated videos are automatically watermarked"
purpose: "Indicates the content is AI-generated"