h3-prompt-writing SKILL.md skillA

This file is byte-identical to the first copy the registry indexed, one of 4 indexed copies. Same content hash, so the same checks give both the same grade.

h3-prompt-writing from yc883123/cat-chat is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add yc883123/cat-chat/h3-prompt-writing@git:20260816.2ea24cf

Pins git:20260816.2ea24cf in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
yc883123/cat-chat
Path
skills/h3-prompt-writing/SKILL.md
Versions recorded
2
Latest version
git:20260816.2ea24cf, committed Aug 16, 2026
First version recorded
Aug 12, 2026
Size
2,623 bytes
Repository stars
36
License
none declared

Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal requests into H3 prompt structures, composing integrated_multimodal_description, overall_soundscape, and non_diegetic_music, aligning keyframes, or defining reference labels for images, videos, and audio.

Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.

What the file says

# H3 Prompt Writing

## Workflow

1. Identify the input mode: T2VA, I2VA, FL2VA, L2VA, or full-reference Ref2VA.
2. For base text/keyframe modes, read `references/base-en.txt` and follow its final prompt structure.
3. For full-reference mode, read `references/ref-en.txt` and follow its six-section rewrite format.
4. Preserve the exact field names, section order, labels, and timing notation from the selected guide.

## Base Modes

- T2VA: build the full audiovisual timeline from text.
- I2VA: start from the first frame and develop forward from it.
- FL2VA: describe the continuous path between the first and last frames.
- L2VA: infer a plausible opening and converge to the supplied last frame.

Use `integrated_multimodal_description`, `overall_soundscape`, and `non_diegetic_music` in the order shown in `references/base-en.txt`.

## Full-Reference Mode

Ref2VA rewrites use `subject_definitions`, `summary`, `retention_analysis`, `detailed_description`, `overall_soundscape`, and `non_diegetic_music` in that order. Reference labels stay consistent across all sections.

Read `references/ref-en.txt` for label rules, retention analysis, and complete examples.

## Output Rules
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add yc883123/cat-chat/h3-prompt-writing@sha256:a7000443588ca3f1

The line at the top of this page pins the label git:20260816.2ea24cf, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.

Badge

mdr badge

[![mdr](https://markdownregistry.com/badge/art_ssyzcv3pzfhby5ql.svg)](https://markdownregistry.com/a/art_ssyzcv3pzfhby5ql)

1 badge image fetches in 30 days. What the badge shows.

Versions

The registry has recorded 2 versions of this file, between Aug 12, 2026 and Aug 16, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
git:20260816.2ea24cf latest2026-08-16 2ea24cf 2,623 BA view · diff
git:20260812.a4bfd912026-08-12 a4bfd91 1,912 BA view

Audit of the latest version

A  17 of 17 checks passed. Fixed automatic checks with no AI involved, so the same checks give the same answer every run.
  • pass: Frontmatter block present
  • pass: Frontmatter declares a name
  • pass: Frontmatter declares a description
  • pass: Size between 200 bytes and 200 KB (2623 bytes)
  • pass: No zero-width or bidi control characters
  • pass: No instruction hidden inside an HTML comment
  • pass: No link to an exfiltration or paste host
  • pass: No credential-shaped string
  • pass: No instruction to send local credentials anywhere
  • pass: No text hidden with inline styles
  • pass: No prompt-injection phrasing
  • pass: No curl or wget piped into a shell
  • pass: No recursive delete of root, home or parent
  • pass: No instruction to read or print local credentials
  • pass: No base64 blob over 200 characters
  • pass: No link to a raw IP address
  • pass: No script tag

Source

GitHub

yc883123/cat-chat · 36 stars · license none declared · pushed 2026-10-19 · branch master

API

GET https://markdownregistry.com/api/v1/artifacts/art_ssyzcv3pzfhby5ql
GET https://markdownregistry.com/api/v1/resolve?ref=yc883123/cat-chat/h3-prompt-writing
GET https://markdownregistry.com/api/v1/blob/a7000443588ca3f145e3b3fd8900f14e0325dc460bd811268fac89a9dc8e56d0

Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.

Guides: the SKILL.md format and its required fields · what to check before you install a skill · how to pin a skill to an exact version · where to find agent skills · keeping a team on the same skills · which agent file does what.

More from yc883123/cat-chat

cat-chat-guide SKILL.md skill
yc883123/cat-chat · skills/cat-chat-guide/SKILL.md · Cat Chat(原名 Naiba Chat)产品使用指南知识库:功能地图、每个功能的入口路径、常见问题与教程原文索引。用户问「Cat Chat 这个功能在哪 / 怎么用 / 为什么没反应 / 怎么配…
git:20261018.9037e9d · audit A · 36 stars
comfyui-llama-model-bridge SKILL.md skill
yc883123/cat-chat · skills/comfyui-llama-model-bridge/SKILL.md · 让 ComfyUI 模型目录中的 GGUF、Safetensors 语言模型与视觉 mmproj 在 llama.cpp、Ollama、LM Studio 和 Naiba-chat…
git:20260822.7fbbe2c · audit A · 36 stars
comfyui-shortdramav2 SKILL.md skill
yc883123/cat-chat · skills/comfyui-shortdramav2/SKILL.md · 通用短剧批量生成模板:用 ComfyUI + MiniMax H3 Ref2VA 把任意单元短剧剧本(markdown,每段英文 H3 提示词 + <Picture N>/<Audio N> 参考标签)批量转成 15…
git:20260911.70bf9bb · audit A · 36 stars
copywriting SKILL.md skill
yc883123/cat-chat · skills/copywriting/SKILL.md · 中文文案写作流程与模板:口播稿、公众号图文、软件教程文案、产品介绍。动笔前先确认平台/字数/读者/目的,口语化短句、先结论后细节、给三个备选标题,附发布前自检清单。用户说「写个文案/口播稿/公众号/宣传稿/教程文案」时用它。
git:20260924.4b84e38 · audit A · 36 stars
runninghub SKILL.md skill
yc883123/cat-chat · skills/runninghub/SKILL.md · Generate images, videos, audio, and 3D models via RunningHub API (420 endpoints) and run any RunningHub AI Application…
git:20260901.5a204ee · audit A · 36 stars
shortdramav2-rh SKILL.md skill
yc883123/cat-chat · skills/shortdramav2-rh/SKILL.md · 短剧单元批量生成(云端版):以 comfyui-shortdramav2 的剧本解析与 <Picture N>/<Audio N> 标签映射逻辑为基础,通过 RunningHub AI 应用(webappId)上传参考资产、组装…
git:20260903.be42319 · audit A · 36 stars

Every file in yc883123/cat-chat

Other files named h3-prompt-writing

h3-prompt-writing SKILL.md skill
karuvanan/minimax-h3-director-cut-studio · skill default/h3-prompt-writing/SKILL.md · Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal…
git:20260823.386169a · audit A · 145 stars
h3-prompt-writing SKILL.md skill
chflame163/comfyui_qwen_h3_prompt · skills/h3-prompt-writing/SKILL.md · Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal…
git:20260816.a215b88 · audit A · 133 stars
h3-prompt-writing SKILL.md skill
swotatmk/infinite-creation · skills/h3-prompt-writing/SKILL.md · Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal…
git:20261012.75e21ad · audit A · 105 stars
h3-prompt-writing SKILL.md skill
mini-yifan/open-source-video-gen-skill · skills/h3-prompt-writing/SKILL.md · Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal…
git:20260906.fe772b9 · audit A · 38 stars
h3-prompt-writing SKILL.md skill
yc883123/naiba-chat · skills/h3-prompt-writing/SKILL.md · Write MiniMax H3 video generation prompts for T2VA, I2VA, FL2VA, L2VA, and Ref2VA. Use when rewriting multimodal…
git:20260816.2ea24cf · audit A · 36 stars

Browse by kind, by grade A, or by owner.