comfyui-shortdramav2 SKILL.md skillA

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

comfyui-shortdramav2 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/comfyui-shortdramav2@git:20260911.70bf9bb

Pins git:20260911.70bf9bb 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/comfyui-shortdramav2/SKILL.md
Versions recorded
3
Latest version
git:20260911.70bf9bb, committed Sep 11, 2026
First version recorded
Sep 1, 2026
Size
9,423 bytes
Repository stars
36
License
none declared

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 秒视频片段。任何人准备自己的角色图/声音、填一份 config.json 即可复用"解析 → 映射 → 建工作流 → 入队 → 轮询 → 收集"流水线。.

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

# 短剧 Ref2VA 批量自动化(通用模板)

一套可复用的短剧自动化模板:把「分好段的短剧剧本」批量变成「15 秒视频片段」。只靠 ComfyUI HTTP API(`/prompt` + `/history` + `/view`),资产/地址/命名全部走 `config.json`,换剧不换代码。

> 先启动 ComfyUI,再运行脚本。此 Skill 不依赖 MCP,也不会注册或安装
> MCP;没有加载本 Skill 时,仍可用 NaibaChat 的通用 `http_request` 或
> `pwsh`/`comfy` CLI 直接调用 ComfyUI。

## 什么时候用

- 剧本是单元 markdown(`单元0X_*.md`),每段 `## 第N段 …(0–15 秒)`,含 `**H3 提示词**` 的 ` ```text ``` ` 代码块(中文或英文)和 `<Picture N>` / `<Audio N>` 参考标签。
- 要批量生成 15s 片段,且角色形象/音色跨段一致。
- 后端是 ComfyUI + MiniMax H3 Ref2VA。

## 剧本格式要求(脚本按此解析)

解析行为以 `scripts/generate_unit.py` 的 `parse_markdown()` 为准,写剧本时必须满足:

1. **提示词有效内容必须从 `subject_definitions:` 开始**。脚本只提取 ` ```text ` 代码块中从该字段开始到代码块结束的内容;即使代码块前面误放了上传前缀或说明文字,也不会把它们送进 ComfyUI。找不到该字段时会跳过该段。
2. **上传模板前缀(`|本段上传(按此顺序):…|`)必须写在代码块外面**。脚本把 ` ```text ` 块内全部内容原样送进 ComfyUI 提示词框,前缀一旦进块就成了提示词的一部分。
3. **`<Picture N>` / `<Audio N>` 标签必须出现在提示词正文中**(通常在 `subject_definitions` 的 `in <Picture N>` 与 `<Audio N> is …` 行)。脚本靠"标签是否出现在提示词里"决定是否挂载对应槽位;标签只写在前缀里会导致图片/音轨全部不挂载。
4. 段标题需能被识别为提示词段:`## 第N段 …`、`## 片段 NN|…`、`## P0X-N Ref2VA(English)`、`## 二、P0X Ref2VA 六字段版(英文 …)` 等。中文和英文版本都会解析;同一段同时存在两种语言时,运行脚本会让用户选择提交语言。代码块内容从 `subject_definitions:` 开始截取,代码块前或块内误放的“本段上传……”前缀不会送入 ComfyUI。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add yc883123/cat-chat/comfyui-shortdramav2@sha256:eed4fc6ef0c8a119

The line at the top of this page pins the label git:20260911.70bf9bb, 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_fph7s6eea5c2oibt.svg)](https://markdownregistry.com/a/art_fph7s6eea5c2oibt)

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

Versions

The registry has recorded 3 versions of this file, between Sep 1, 2026 and Sep 11, 2026, about one every 5 days.

versioncommittedcommitsizeaudit
git:20260911.70bf9bb latest2026-09-11 70bf9bb 9,423 BA view · diff
git:20260901.1507aac2026-09-01 1507aac 9,421 BA view · diff
git:20260901.fa2a6432026-09-01 fa2a643 9,428 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 (9423 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_fph7s6eea5c2oibt
GET https://markdownregistry.com/api/v1/resolve?ref=yc883123/cat-chat/comfyui-shortdramav2
GET https://markdownregistry.com/api/v1/blob/eed4fc6ef0c8a119b77d67fdc7bbb07e6f0aede2bb9f2f11533c22d76eda790b

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
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
h3-prompt-writing SKILL.md skill
yc883123/cat-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
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 comfyui-shortdramav2

comfyui-shortdramav2 SKILL.md skill
yc883123/naiba-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

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