Skip to content

smixs /visual-skills

Writes video and image prompts for Seedance, Kling and Veo
Agent skillsCC-BY-4.0English README
Stars
464
30 days
+2
Last push
16 days ago
visual-skills screenshot from its README
From the visual-skills README on GitHub.

About visual-skills

Visual Skills is two Agent Skills (plain markdown files) for your coding agent. One writes AI video prompts, the other writes art-directed image prompts. You get storyboards, multi-shot sequences and copy-paste prompts for Seedance, Kling and Veo. The README reads like an ad, and model syntax was checked in July 2026.

Best for: Solo directors who want structured, model-specific prompts instead of adjective lists.

What it does

  • Writes video prompts with a dramaturgy layer: scene formula, beats, shot cards
  • Writes image prompts for stills, keyframes and character sheets
  • Keeps a file per model with exact syntax and known failure modes
  • Returns single prompts, stitched sequences, storyboard tables or prompt audits
  • Runs a six-point check and a three-detail audit before any prompt comes back
  • Chains the two skills: image keyframes feed the video motion brief

Quickstart

Rewritten from the README. Check the repo for the latest steps.

  1. 1
    Install with the command below (add -g for all projects, or @video for one skill).
    npx skills add smixs/visual-skills
  2. 2
    Or add it as a Claude Code plugin: the command below, then the next command.
    /plugin marketplace add smixs/visual-skills
    /plugin install visual-skills@visual-skills
  3. 3
    Or clone it and copy the folders: the command below, then the next command.
    git clone https://github.com/smixs/visual-skills.git
    cp -r visual-skills/video visual-skills/image ~/.claude/skills/
  4. 4
    Ask for a prompt, for example: "Write a Seedance prompt — a hungry guy at night finds the last sausage in the fridge, 5 seconds, multi-shot".
  5. 5
    Update later with npx skills update.

Models and languages

Models it works with

  • Seedance 2.5
  • Seedance 2.0
  • Kling 3.0 Turbo
  • Kling 3.0 Omni
  • Veo 3.1
  • Nano Banana 2
  • GPT Image 2.5
  • Runway Gen-4
  • Luma
  • Sora

Interface and docs

  • English
  • Russian

Alternatives

Other agent skills projects people compare with visual-skills.

A-cat-with-carrots

OnlyShot

Claude Code skill that takes one idea to a full Chinese short drama

Agent skills
  • Seedance 2.0
  • Jimeng 5.0
  • Suno
298 GitHub stars2 months agoMIT

lixiaoxiao9888-create

manju-laoli-skill

Feed it a script and it locks assets, storyboards and model prompts

Agent skills
  • Seedance 2.5
  • Seedance 2.0
  • MiniMax H3
  • +1
987 GitHub stars+5/30d12 days agoMIT

zenstory-ai

drama-skills

Chains eleven agent skills into your whole AI short-drama pipeline

Agent skills
  • MiniMax H3
  • Seedance
  • GPT Image 2
  • +1
2.4k GitHub stars+12/30d3 days agoMIT

eternityspring

shuohao-skills

Pre-production assets for an AI short drama, straight from a novel

Agent skills
  • Qwen Image
  • GPT Image 2
  • MiniMax H3
  • +1
4k GitHub stars+13/30d6 days agoApache-2.0

Skills from this repo

Featured on OpenMicroDrama

Do you maintain visual-skills? Add this badge to your README so English speakers can find our write-up.

Featured on OpenMicroDrama
markdown
[![Featured on OpenMicroDrama](https://openmicrodrama.com/badges/featured.svg)](https://openmicrodrama.com/projects/smixs-visual-skills)

The badge links to this page. Want your description changed? Email support@openmicrodrama.com.

Reviewed Oct 1, 2026. We write these descriptions ourselves. The repo's own docs are the final word.