autodl-app-instance SKILL.md skillA

autodl-app-instance from mini-yifan/open-source-video-gen-skill is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add mini-yifan/open-source-video-gen-skill/autodl-app-instance@git:20260908.0a40107

Pins git:20260908.0a40107 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
mini-yifan/open-source-video-gen-skill
Path
skills/autodl-app-instance/SKILL.md
Versions recorded
3
Latest version
git:20260908.0a40107, committed Sep 8, 2026
First version recorded
Aug 30, 2026
Size
9,730 bytes
Repository stars
40
License
a license file GitHub does not identify

Powers AutoDL Art application instances on and off via official API, finds the ComfyUI panel by probing the instance's proxy service domains from the snapshot API (no SSH needed, works on macOS / Linux / Windows), and waits until ComfyUI is ready for MiniMax H3. Use when the user mentions AutoDL 应用实例, API开机, API关机, autodl.art, AUTODL_TOKEN, 远程服务器开关机, or wants the agent to boot a GPU box before minimax-h3 and shut it down after video generation. It can wrap a minimax-h3 job with…

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

# AutoDL 应用实例(开机 → 发现面板 → 关机)

管 **应用实例** 生命周期,不管提示词、不管出片。出片走 [`minimax-h3`](../minimax-h3/SKILL.md)。

官方文档:<https://autodl.art/docs/app_api/>  
脚本:当前技能目录下的 `scripts/autodl_app.py`(ZCode:`~/.zcode/skills/autodl-app-instance/scripts/autodl_app.py`)。  
接口细节 → [reference.md](reference.md)  
命令示例 → [examples.md](examples.md)

不要把 `AUTODL_TOKEN` / SSH 密码写入仓库或技能文件。不要打印 `root_password`。

---

## 和 minimax-h3 的组合执行契约(批次级)

```
解析并记录 UUID
  → boot 一次并导出最新 SEETACLOUD_BASE_URL
  → minimax-h3 执行一个或多个视频 job
  → 等所有 job 进入终态
  → finally: off 一次(本技能)
```

当目标是 AutoDL 应用实例,或用户要求“开机后生成、全部完成后关机”时:**先本技能,再 minimax-h3,最后关机。** 不要只发现完面板就结束。

本技能只管理实例生命周期,不决定 H3 的工作流、提示词、时长、画幅或画面内容。`minimax-h3` 只有在本技能报告 `COMFY_READY`、队列可访问并提供最新面板地址后才能提交任务。

组合模式下,一个父任务就是一个 AutoDL 批次。必须先保存实例 UUID,再执行一次 `boot`;批次内的多个视频、重试和追加 job 都共用这次开机。单个视频完成时不得执行 `off`。

只有当批次内所有 job 都是 `succeeded`、`failed` 或 `cancelled`,并且没有仍在运行的 H3 任务、未下载的结果或未处理的重试时,就执行一次 `off --uuid <uuid> --wait`。成功、部分失败、超时、轮询异常或用户中断,都要走批次级 `try/finally` 清理;只有用户明确要求保持开机或设置 `AUTODL_KEEP_ON=1` 时例外。

**关机时点(2026-08-29 明确)**:批次产出全部下载落盘并通过 `ffprobe` 秒级校验后**立即关机**。归一化、抽帧验收、滤镜、按用户反馈调参重跑等本地后处理不得推迟关机——GPU 空转照常按秒计费,这些活放到关机后做零成本。本地验收不达标需要重生成时,先改提示词/素材再重新 `boot`(重开成本远低于空转等待)。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add mini-yifan/open-source-video-gen-skill/autodl-app-instance@sha256:5fb70551a14d5671

The line at the top of this page pins the label git:20260908.0a40107, 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_y7gpao3joyrf4zug.svg)](https://markdownregistry.com/a/art_y7gpao3joyrf4zug)

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

Versions

The registry has recorded 3 versions of this file, between Aug 30, 2026 and Sep 8, 2026, about one every 4 days.

versioncommittedcommitsizeaudit
git:20260908.0a40107 latest2026-09-08 0a40107 9,730 BA view · diff
git:20260830.cee067c2026-08-30 cee067c 9,061 BA view · diff
git:20260830.8cf2ae72026-08-30 8cf2ae7 8,252 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 (9730 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

mini-yifan/open-source-video-gen-skill · 40 stars · license a license file GitHub does not identify · pushed 2026-09-11 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_y7gpao3joyrf4zug
GET https://markdownregistry.com/api/v1/resolve?ref=mini-yifan/open-source-video-gen-skill/autodl-app-instance
GET https://markdownregistry.com/api/v1/blob/5fb70551a14d5671896827208e373e6b8aa549362ae98d4cdcf4081e7be0b9ff

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 mini-yifan/open-source-video-gen-skill

beauty-video-gen SKILL.md skill
mini-yifan/open-source-video-gen-skill · skills/beauty-video-gen/SKILL.md · 生成超写实、真实感、亲近感的美女时尚竖屏短视频(MiniMax H3 云端生成)。当用户要求"生成美女视频 / 真实感美女 / 亲近感美女视频 / 美女短视频 / 时尚美女视频 /…
git:20260911.3d58d1d · audit A · 40 stars
character-three-view SKILL.md skill
mini-yifan/open-source-video-gen-skill · skills/character-three-view/SKILL.md · Prepares reference art for video production from a script or asset list: character reference sheets (including…
git:20260911.3d58d1d · audit A · 40 stars
cursor-image-gen SKILL.md skill
mini-yifan/open-source-video-gen-skill · skills/cursor-image-gen/SKILL.md · Generate or edit bitmap images by launching a local Cursor Agent (cursor-grok-4.6-high) and using Cursor GenerateImage…
git:20260911.3d58d1d · audit A · 40 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 · 40 stars
minimax-h3 SKILL.md skill
mini-yifan/open-source-video-gen-skill · skills/minimax-h3/SKILL.md · Use a remote SeetaCloud or AutoDL ComfyUI GPU instance to generate MiniMax H3 videos. Connects over SSH, discovers the…
git:20260908.0a40107 · audit A · 40 stars
minimax-music-gen SKILL.md skill
mini-yifan/open-source-video-gen-skill · skills/minimax-music-gen/SKILL.md · 用 AutoDL GPU 实例上的 MiniMax Music 3(ComfyUI)生成音乐:人声演唱的完整歌曲 (自定义歌词、女声/男声、任意曲风)或纯音乐 BGM(instrumental)。Use when user wants…
v3.0 · audit A · 40 stars
qwen3-tts SKILL.md skill
mini-yifan/open-source-video-gen-skill · skills/qwen3-tts/SKILL.md · 用 AutoDL GPU 实例上的 Qwen3-TTS 生成配音语音(TTS)。当用户需要旁白、画外音、 配音、台词朗读、文字转语音、特定声线(如甜妹音、大叔音、御姐音)、克隆某个人的 声音,或为 MiniMax H3…
git:20260831.07106f5 · audit A · 40 stars
short-drama-production SKILL.md skill
mini-yifan/open-source-video-gen-skill · skills/short-drama-production/SKILL.md · Orchestrate an end-to-end short-drama or short-film production from a user's theme: approved brief, then — for…
git:20260906.fe772b9 · audit A · 40 stars

Every file in mini-yifan/open-source-video-gen-skill

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