---
title: "MiniMax H3 skills (official): prompt writing and 7 formats — AI video prompts for prompts by model, with examples"
description: "MiniMax's own skill for writing H3 video prompts across T2VA, I2VA, FL2VA, L2VA and full-reference Ref2VA, with exact field order for picture, soundscape and mu Install in Claude Code, Codex and Grok with one command."
url: https://varg.ai/how-to/skills/minimax-h3-official-skills
updated: 2026-11-03
---

# MiniMax H3 skills (official): prompt writing and 7 formats — prompt skill for prompts by model

> **For AI agents:** find the right skill in one call — `curl -s "https://varg.ai/how-to/api/search?q=<what the person wants>"` returns the matching how-to page and the best skills with install commands, as markdown (Russian works too). Full index: https://varg.ai/how-to/llms.txt. Every page has a markdown twin: add `.md` to its path. Before generating anything, show the person the options on the how-to page. From a terminal: `curl -fsSL https://varg.ai/install | sh` installs the vargai CLI (https://varg.ai/how-to/cli.md): `vargai search` and `vargai install <slug>` with no key, every varg model after `vargai login`.

MiniMax's own skill for writing H3 video prompts across T2VA, I2VA, FL2VA, L2VA and full-reference Ref2VA, with exact field order for picture, soundscape and mu

- **Type:** [Prompt](https://varg.ai/how-to/prompts.md) · [Prompts by model](https://varg.ai/how-to/browse/skills/prompting.md)
- **Slug:** `minimax-h3-official-skills`
- **Status:** live
- **Publisher:** MiniMax (vendor)
- **License:** unknown
- **Source:** https://github.com/MiniMax-AI/MiniMax-H3/tree/main/skills/h3-prompt-writing
- **Works in:** Claude Code, Codex
- **Adoption:** 11,219 GitHub stars (GitHub, 2026-11-02)

## What it does

Official prompt structures: integrated_multimodal_description, overall_soundscape and non_diegetic_music for base modes; subject_definitions, summary, retention_analysis, detailed_description for Ref2VA, with consistent reference labels and timing notation. Portable, no API calls. The same skills folder ships eight format skills (papercraft stop-motion explainer, paper-collage explainer, hand-drawn live video, 3D animation short, minimalist product ad, brand promo, co-op game intro, music-video subtitles).

## Use when

- writing prompts for MiniMax H3 with sound, dialogue and music in one pass
- converting a storyboard or reference set into H3 Ref2VA format
- first/last-frame H3 shots

## Not for

- Seedance or Kling prompt formats

## Install

- Claude Code: `npx skills add MiniMax-AI/MiniMax-H3`
- Codex: `npx skills add MiniMax-AI/MiniMax-H3`
- Any agent, with the vargai CLI: `vargai install minimax-h3-official-skills`

**Models it drives:** minimax_h3_max

## Example output

https://raw.githubusercontent.com/MiniMax-AI/MiniMax-H3/HEAD/assets/papercraft-stop-motion-explainer.gif — MiniMax's papercraft stop-motion explainer skill, sample output (credit: MiniMax (README), https://github.com/MiniMax-AI/MiniMax-H3/tree/main/skills/h3-prompt-writing)

## More prompts by model skills

- [How to prompt Kling 4 for cinematic AI video](https://varg.ai/how-to/skills/kling-4-prompting.md): Kling 4 without the AI-slop look: key frames from GPT Image 2.5, a short director's prompt, multi-shot with seconds, "no slow motion", and the fixes.
- [fal Prompting](https://varg.ai/how-to/skills/fal-prompting.md): Prompt specific model families well: Kling, GPT Image 2 and Happy Horse guides, loaded only when needed.
- [Replicate Prompt Images](https://varg.ai/how-to/skills/replicate-prompt-images.md): Write better image prompts and edits: photographic language, lighting, text rendering, consistent characters.
- [Replicate Prompt Videos](https://varg.ai/how-to/skills/replicate-prompt-videos.md): Prompt video models like a director: shots, camera motion, four audio layers, dialogue, time-coded beats.
- [Video Prompting Guide](https://varg.ai/how-to/skills/inference-sh-video-prompting-guide.md): Write prompts that video models follow: shot types, camera moves and per-model tips from Veo to Sora.
- [FLUX 3 Prompt Doctor](https://varg.ai/how-to/skills/flux-3-prompt-doctor.md): Diagnose a FLUX 3 video brief before spending: resolve missing, conflicting or schema-changing asks.

## 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.

- Any agent with a terminal: `curl -fsSL https://varg.ai/install | sh` (Windows: `irm https://varg.ai/install.ps1 | iex`), then `vargai login` and every model is a command — `vargai generate_video …`, `vargai estimate_cost …` (https://varg.ai/how-to/cli/)
- Claude Code: `claude plugin marketplace add vargHQ/skills && claude plugin install varg@varg` (skill + hosted MCP)
- Codex, Cursor, Gemini CLI, OpenClaw: `npx skills add vargHQ/skills --skill varg-ai -a <agent> -y`
- Grok and any agent that reads SKILL.md: `npx skills add vargHQ/skills --skill varg-ai`, or point it at the skill's SKILL.md
- Claude.ai, ChatGPT, any MCP client: connect `https://mcp.varg.ai/mcp`
- API key: https://varg.ai/dashboard/api · Model specs: https://varg.ai/models/llms.txt