Visual Skills gives an agent two packed skills: `image` for still-image prompts and `video` for motion prompts. The video side starts with dramaturgy, then applies universal rules and model-specific syntax so the output is ready to paste into tools like Seedance, Kling, and Veo. The image side chooses between Nano Banana and GPT Image based on the task and writes prompts in the right format.
Builders who want their agent to write image and video prompts with film structure instead of generic prompt text.
You can turn rough scene ideas into model-ready prompts that follow the right cinematic structure and syntax.
Loads a scene formula, shot logic, editing priorities, and rhythm rules before any model syntax is applied.
Writes prompts for Seedance, Kling, and Veo using each model's own format and failure modes.
Creates prompts for editorial images, product shots, posters, UI mockups, and continuity-preserving edits.
Chooses Nano Banana for grounding and cheap batches, and GPT Image for dense text and preservation-critical edits.
Can return a prompt audit, storyboard table, director treatment, stitched clip sequence, or Veo JSON.
Ships as a managed Claude plugin bundle as well as plain skills folders.
npx skills add smixs/visual-skills # asks where to install, offers both skills npx skills add smixs/visual-skills -g # globally, for all projects npx skills add smixs/visual-skills@video # just one of the two npx skills update # update to latest
npx skills add https://skills.sh/p/nuK9jo3sTCZGB2Ul
/plugin marketplace add smixs/visual-skills /plugin install visual-skills@visual-skills
git clone https://github.com/smixs/visual-skills.git cp -r visual-skills/video visual-skills/image ~/.claude/skills/
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.
[!IMPORTANT] Model syntax is worth nothing until the dramaturgy is there. Editing, staging, camera, light, the objects allowed in frame — hard rules, all of them written into the skill. That is what makes it a director instead of an autocomplete for adjectives. Get them right and the model finally has something worth rendering; get them wrong and no amount of correct syntax saves the shot.
The heart of the video skill is video/references/dramaturgy.md — how films are actually built, compressed into rules an agent can execute on a 5-30 second clip. Same idea, both columns below. Only one of them can be filmed.
| The prompt everyone writes four adjectives, zero facts | The prompt the skill writes one emotion · three shots · three details · one final image |
|---|---|
|
|
|
No desire, no obstacle, no geometry, no cut, no final image. The model picks all five for you — and picks differently on every run. |
Every line is a physical fact a camera could record: a reason for the move, a body carrying the emotion, a sound, an object, an ending. Nothing left for the model to invent. |
[!CAUTION] Banned everywhere:
cinematic·epic·stunning·masterpiece·beautiful lighting·dynamic camera·he is sad. Each one is a placeholder for a detail the writer failed to invent, and not one of them renders.
|
0 1 · L A W
Five elements. Name each one in a single sentence before a word of prompt is written: what the hero wants right now, what blocks it, who stands where, where the eye is forced to look, how long each shot lives. Anything less is decoration. |
0 2 · D E T A I L Every shot owns three physical facts: one environmental pressure (cold refrigerator light, wet asphalt), one micro-action of the body (jaw locks, knuckles whiten), one sound anchor or visual motif. "He is sad" does not render. A jaw does. |
|
0 3 · E D I T I N G emotion 51% █████████████████████████▌ story 23% ███████████▌ rhythm 10% █████ eye-trace 7% ███▌ screen plane 5% ██▌ 3D space 4% ██ Cutting "for pace" is item three. Serving item three ahead of emotion and story is exactly how TikTok mush gets made — and it is the default behaviour of every model you will ever prompt. | |
|
0 4 · S E L E C T I O N A shot either changes emotion, advances action, or increases pressure. A shot that does none is deleted, however pretty it came out. "Beautiful establishing shot" is not a job. |
0 5 · S T A G I N G Fincher — every camera move answers "what changed?", otherwise the camera is static. Spielberg — even in chaos the viewer knows where the hero, the threat and the exit are. Kurosawa — one weather, one pressure, carrying the whole scene. |
|
0 6 · R H Y T H M
The pause before the hit matters more than the speed of the cuts. Beat maps for 15 / 30 / 60 / 90 seconds — Hook, Pressure, Crack, Impact, Aftermath. Never skip the Crack. |
0 7 · S P E C Fourteen fields per storyboard row: framing, composition, camera, movement reason, eye-trace, duration, cut type, sound, light. An empty field is missing direction. Per piece, exactly five anchors — one emotion, one motif, one object, one break, one final image. |
None of this is advice the agent is free to skip. dramaturgy.md loads before any model file, and the output is gated twice on the way out — the six-point dramaturgy check and a three-detail audit on every shot. A prompt that fails either one is not returned.
| VIDEO · DEDICATED MODEL FILE, EXACT SYNTAX | |||||
|---|---|---|---|---|---|
 Seedance 1.0 · 1.5 Pro · 2.0 · 2.0 Mini · 2.5 |  Kling 1.6 – 2.6 Pro · 3.0 · Turbo · Omni |  Veo 3 · 3.1 | |||
| IMAGE · DEDICATED MODEL FILE, EXACT SYNTAX | |||||
 Nano Banana 2 Lite · 2 · Pro (Gemini image family) |   GPT Image 2.5 Flare · 2.5 Sunburst · legacy 2 | ||||
| COVERED BY THE UNIVERSAL-RULES LAYER | |||||
  Runway Gen-4
  Luma
  Pika
 Sora
| |||||
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.
The SKILL.md body is a thin router; the craft lives in reference files the agent is forced to load in order:
dramaturgy.md) — scene formula, beats, shot functions, rhythm.universal-rules.md) — the 12 rules that hold for every model: prompt skeleton, character anchors, show-don't-tell, duration discipline, the final-image rule.seedance.md, kling.md or veo.md: exact syntax, multi-shot markers, dialogue protocols, reference tags, failure modes with fixes.Output formats: a single prompt, a stitched multi-clip sequence with continuity blocks, a storyboard table, a prompt audit ("what breaks, what's missing, stronger version"), a director treatment, or Veo JSON.
Art direction for still images: editorial and product photography, posters, UI mockups, infographics, edits with hard preservation, character continuity across a series, storyboards and animatic keyframes for the video pipeline. It picks between Nano Banana and GPT Image 2.5 per task (grounding of real places, extreme aspect ratios and cheap batches go to Nano Banana; dense text, brand assets and preservation-critical edits go to GPT Image 2.5), then writes the prompt in that model's native structure.
The two skills chain: image builds the character sheets and keyframes, video turns them into motion with a proper motion brief instead of a re-described scene.
These skills shoot the film. The idea and the script come from their sibling skill — creative-director: an AI creative director that develops ideas and scripts for commercials (and far beyond advertising) with world-class ideation methodologies, recursive scoring and a library of 571 legendary campaigns.
The full pipeline: idea & script (creative-director) → keyframes & stills (image) → motion (video). Each stage is optional — enter wherever your project starts.
Works in Claude Code, Claude.ai Projects, Cursor, Windsurf, Cline, OpenCode, Codex, Hermes — anything that reads the Agent Skills format (plain markdown, no lock-in).
Via skills.sh — installs into any of 70+ supported agents, Codex included:
npx skills add smixs/visual-skills # asks where to install, offers both skills
npx skills add smixs/visual-skills -g # globally, for all projects
npx skills add smixs/visual-skills@video # just one of the two
npx skills update # update to latest
The full Creative Agency pack — creative-director, image and video in one command:
npx skills add https://skills.sh/p/nuK9jo3sTCZGB2Ul
As a Claude Code plugin — one managed bundle with both skills:
/plugin marketplace add smixs/visual-skills
/plugin install visual-skills@visual-skills
In Codex CLI — npx skills add smixs/visual-skills -g -a codex, or ask the built-in installer: $skill-installer install skills from https://github.com/smixs/visual-skills.
Manually:
git clone https://github.com/smixs/visual-skills.git
cp -r visual-skills/video visual-skills/image ~/.claude/skills/
"Write a Seedance prompt — a hungry guy at night finds the last sausage in the fridge, 5 seconds, multi-shot"
"Storyboard a 30-second film about guilt. Core emotion — guilt. Anchor object — a phone with an unread message."
"Audit this prompt: [...]. What's broken, how to fix?"
"Translate this script into 6 × 5-second Seedance prompts."
"Make a keyframe set for a 15-second product film, then Kling prompts to animate each"
New video/references/seedance-25.md, built from ByteDance's official User Guide and Prompt Guide (released July 31): the official prompt formulas, the ( ) < > { } 【 】 audio/dialogue/text markers, the 50-slot reference discipline with stability tables, stages + end states for 30-second single-pass clips, video editing (partial re-render), extension to 60s, Ultra Long mode (30–180s), the 3D-blockout / green-screen pipeline, and three official worked examples. Cross-model additions landed too: a transition vocabulary and an uncommon-term translation pattern in the camera file, reference-role discipline and priority declaration in the universal rules.
Serge Shima — t.me/aimastersme · sergeshima.com · aimasters.me
Dramaturgy distilled from Walter Murch (In the Blink of an Eye), Akira Kurosawa, David Fincher, Steven Spielberg, Jonathan Glazer and Bong Joon Ho. Model syntax verified against official ByteDance, Kuaishou, Google and OpenAI docs plus fal.ai prompting guides, July 2026.
Vendor marks in the model table come from lobe-icons (MIT). Each mark stays the property of its owner and is used here only to identify the model it labels.
CC BY 4.0 — use it, fork it, build on it, commercially too. One rule: credit the author. Any copy or derivative — including skills assembled by AI agents from these files — must keep the attribution line: Serge Shima — github.com/smixs/visual-skills. See LICENSE and NOTICE.
Tags: claude · claude-skills · ai-video-generation · ai-image-generation · seedance · kling · veo · nano-banana · gpt-image-2.5 · ai-film-directing · storyboard · prompt-engineering
Sign in to join the discussion.
No comments yet. Be the first to say what this is good for.
Topic in, narrated explainer video out. A Claude Code / Codex skill that turns any topic into a black-canvas motion-graphics explainer video with TTS voiceover, subtitles and a chapter progress bar. Chinese or English; every frame drawn in code with Remotion.
Public repository for Agent Skills
An AI skill that provides design intelligence for building professional UI/UX across multiple platforms.
Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop
Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.