Shuohao Short-Drama Skills — workflow skill for stories & short dramas

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.

Seven chained skills from novel to AI short drama: characters, outline, art bible, script, staging, storyboard.

What it does

The most-starred AI short-drama pack on GitHub (5.4K stars within three months; it announced a four-figure sponsorship on 2026-10-26). Seven chained skills turn a novel or story into character sheets with image and voice prompts, a five-part adaptation outline, an art bible for scenes and props, a structured script, staging, and a storyboard that writes one MiniMax H3 video prompt per segment (a Seedance prompt reference is included). Each stage emits JSON, Markdown and a one-page review report, and its quality gates are checked by deterministic Node scripts rather than by the model. Most stages need no API key; character-refs can render reference images through ComfyUI (Qwen Image), Codex's built-in image tool or the OpenAI Images API.

Use when

Not for

Install

Models it drives: minimax_h3

Example output

https://skills.varg.ai/previews/shuohao-short-drama.webp — Character model sheet for Shen Zhiwei from the bundled sample story: headshot, front/side/back turnaround and prop/costume details, as made by the novel-characters skill. (credit: eternityspring (shuohao-skills), https://github.com/eternityspring/shuohao-skills/blob/main/skills/novel-characters/README.en.md)

More stories & short dramas skills

Run the generation on varg

varg is one API key for the models these skills drive — Seedance 2.5, Kling 4, Veo 3.1, Wan 3, Nano Banana 2.1, GPT Image 2.5, ElevenLabs v4 and 200+ more — billed in credits, with a cost estimate before anything runs.