Visual Skills
Two Claude Skills that turn agents into AI film directors, providing cinematic dramaturgy and exact prompt syntax for major video/image models.
smixs · 已有 AI 审核记录
安装与使用
运行命令前先阅读来源与依赖说明。复制命令不会自动安装或执行。
npx skills add smixs/visual-skills技能说明
🎬 Visual Skills — an AI Film Director for Your Agent
🇷🇺 Читать на русском
Two Claude Skills that turn your agent into a working film crew: video writes AI video prompts the way a director, screenwriter and editor would; image writes image prompts the way an art director would. Both pick the right model for the task, apply its exact syntax, and return a copy-paste-ready prompt.
Most prompting guides teach you syntax. This one teaches your agent cinema — and that is what makes it the strongest tool available for directing AI video. A beautiful frame without dramaturgy is wallpaper. Models render pixels; the skill directs them.
Supported models
Video: Seedance 1.0 / 1.5 Pro / 2.0 / 2.0 Mini / 2.5 · Kling 1.6 – 2.6 Pro, Kling 3.0 / 3.0 Turbo / 3.0 Omni · Veo 3 / 3.1. Runway Gen-4, Luma, Pika and Sora are covered by the universal rules layer.
Image: Nano Banana 2 Lite / Nano Banana 2 / Nano Banana Pro (Gemini image family) · GPT Image 2 (plus legacy 1.5 / 1 / mini).
Model files are updated as new versions ship — Seedance 2.5 has a dedicated production reference built from ByteDance's official guides of July 31, 2026 (30-second single-pass clips, 60s extension, 30-180s Ultra Long mode, 50 reference inputs, video editing, 3D camera blockout); Kling 3.0 Turbo and Omni and Nano Banana 2 Lite are already in.
Dramaturgy first, syntax second
The heart of the video skill is references/dramaturgy.md — a working distillation of how great films are actually built, adapted for 5-30 second AI clips:
- The scene formula. A scene exists only when five elements are present: the hero's desire, the obstac