Generate structured Veo 3.1 video prompts from subject, action, and style inputs.
npx skills add https://github.com/buYoung/skills --skill veo-prompt-director
Please help me install this Agent Skill. Skill: veo-prompt-director Source: https://github.com/buYoung/skills/tree/main/skills/veo-prompt-director Command: npx skills add https://github.com/buYoung/skills --skill veo-prompt-director
Veo prompts can be time-consuming to craft manually and risk inconsistency; this skill automates structured prompt generation by collecting subject, action, and style and guiding users through the Universal Prompt Formula.
Provide a subject, an observable action, and a style, and the system will generate a Veo 3.1 prompt.
High-intent search queries and answers about installing and using this skill.
To generate cinematic Veo prompts, provide a subject, an observable action, and a style. The system applies the Universal Prompt Formula to structure these inputs into a camera-ready Veo 3.1 video prompt.
The Universal Prompt Formula is a structured method that collects subject, action, style, context, and optional cinematography or audio inputs to create consistent, camera-ready Veo 3.1 prompts.
Yes, you can create multi-shot video sequences. The prompt generation supports single-shot, multi-shot, and audio-enabled scenarios for Veo 3.1 video prompts.
No, you do not need to manually format audio and cinematography inputs. The interactive collection process gathers optional audio and cinematography details to automatically build the final Veo prompt.
Manual Veo prompts often produce inconsistent video results because they lack structured formatting. Automating prompt generation with the Universal Prompt Formula ensures all necessary cinematic elements are consistently included.
okbest2024Generate videos from prompts or images using Veo 3.1.
jongwonyGenerate high-fidelity videos via Veo 3.1 API with text, image, or video input.
ag47-ptCoordinate storyboard planning and visual continuity for sequential AI video campaigns.
SheshiyerGenerate videos from text prompts using Google Veo models via the inference.sh CLI.
