AI Film Director (Visual Skills) — prompt skill for prompts by model

For AI agents: find the right skill in one call — curl -s "https://skills.varg.ai/api/search?q=<what the person wants>" returns the matching use case and the best skills with install commands, as markdown (Russian works too). Full index: https://skills.varg.ai/llms.txt. Every page has a markdown twin: add .md to its path. Before generating anything, show the person the options on the use-case page.

AI film director for video prompts: dramaturgy first (Murch, blocking, montage), then exact syntax per model.

• Type: Prompt · Prompts by model
• Slug: visual-skills-video-director
• Status: live
• Publisher: Serge Shima (community)
• License: CC-BY-4.0
• Source: https://github.com/smixs/visual-skills/tree/main/video
• Works in: Claude Code, Codex, Cursor
• Cost: Free — prompts only; generation billed by your video platform
• Adoption: 971 installs, 582 GitHub stars (GitHub + skills.sh, 2026-10-26)

What it does

Serge Shima's video skill makes the agent write prompts like a director. It reads a dramaturgy file (Walter Murch's editing priorities, blocking, dynamic montage) and universal rules first, then exactly one model file (Seedance 2.5, Kling 3.0 Turbo/Omni, Veo 3.1 and others), then only the task references that apply (animatic keyframes, camera and lighting vocabulary, race and speed, genre patterns, fixes and skeletons). It covers storyboards, shot lists, director treatments, multi-clip story structure, character continuity, dialogue and sound design, and ends with a dramaturgy check and a three-detail check. A sibling image skill handles Nano Banana and GPT Image 2.5 prompts.

Use when

• Write, improve, audit or split prompts for Seedance, Kling, Veo, Runway, Luma, Pika or Sora
• Turn a script into a storyboard and shot-by-shot prompts
• Fix a video prompt that keeps failing

Not for

• Still images (use the sibling image skill)
• Editing or grading footage that already exists

Install

• Claude Code: npx skills add smixs/visual-skills@video
• Codex: npx skills add smixs/visual-skills -g -a codex

Models it drives: seedance_2_5, kling_v3, veo_3_1

More prompts by model skills

• fal Prompting: Prompt specific model families well: Kling, GPT Image 2 and Happy Horse guides, loaded only when needed.
• Replicate Prompt Images: Write better image prompts and edits: photographic language, lighting, text rendering, consistent characters.
• Replicate Prompt Videos: Prompt video models like a director: shots, camera motion, four audio layers, dialogue, time-coded beats.
• Video Prompting Guide: Write prompts that video models follow: shot types, camera moves and per-model tips from Veo to Sora.
• FLUX 3 Prompt Doctor: Diagnose a FLUX 3 video brief before spending: resolve missing, conflicting or schema-changing asks.
• FLUX Image Best Practices: Prompt FLUX image models well: structure, JSON prompts, hex colors, typography and multi-reference edits.