Home / isaachang / motion-video-workflow · GitHub

motion-video-workflow SKILL.md skillA

motion-video-workflow from isaachang/motion-video-workflow is an agent skill: a SKILL.md folder an AI agent loads when a task calls for it.

Install it, pinned
mdr add isaachang/motion-video-workflow/motion-video-workflow@git:20261011.0727d29

Pins git:20261011.0727d29 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
isaachang/motion-video-workflow
Path
SKILL.md
Versions recorded
5
Latest version
git:20261011.0727d29, committed Oct 11, 2026
First version recorded
Oct 5, 2026
Size
22,693 bytes
Repository stars
13
License
MIT

用户提供配音（背景音乐可选，没有就自动合成），要做口播动效视频（案例分享、AI资讯、AI知识讲解、教程）时使用：听写、抓素材、分镜、代码动效，按需出16:9或9:16成片，并出3:4和4:3封面。.

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

# 口播动效视频工作流（通用版）

用户提供**配音**；**背景音乐**可选，没有就自动合成。最终交付：
- 成片：16:9、9:16，或两种都出（开场时确认）
- 3:4 和 4:3 封面各一张（必出）

## 开场确认（拿到配音后先做，后面不再问）
用一次 AskUserQuestion 问完下面两项。用户在请求里已经说明的项直接跳过，不重复问；两项都说明了就不问。
1. **输出比例**：9:16 竖版 / 16:9 横版 / 两种都要。推荐项按用户的发布平台来定：抖音、小红书、视频号推荐 9:16；B 站、YouTube 推荐 16:9；不确定就推荐 9:16。
2. **背景音乐**（只在用户没给音乐时问）：
   - 「我自己找音乐（推荐）」：说明效果最好，节奏清楚、带鼓点的纯音乐最合适，拿到后再开工。
   - 「自动合成配乐」：说明是代码合成的极简电子乐，没有版权问题，但效果不如真人挑的音乐，之后可以随时替换后重新混音，画面不用重做。
   - 「配音里已经带了音乐」：用户自己混好了配乐，就走第 1 步的「配音自带配乐」，不再另加音乐。

后面各步只做选中的比例：只出 9:16 时跳过所有 16:9 的渲染和检查，动效只为竖版 1080×1080 内容窗设计；只出 16:9 时跳过第 7 步。

要求：
- 不加字幕，只做动效。
- 画面全部由代码生成：HTML、CSS 3D 和 Canvas 画出每一帧，再逐帧渲染。
- 每支片子按自己的内容重新设计，**不复用上一支的画面、配色和版式**。
- 复用的是这套流程、引擎和组件。

## 给用户看的输出规范（每条消息都遵守）
**模块化，不长篇大论。** 每条消息只用下面三种模块，按需组合：
1. **结论**：一到两句话，说做完了什么、结果是什么。
2. **要点**：最多 5 条短清单，或者一张小表格。内容多就用表格，不写成段落。
3. **需要你定**：有问题才出现，见下面的提问规则。

约束：
- 正文不超过 10 行（表格和图片不算）。超过就砍掉，或者合并成表格。
- 不复述用户已经知道的内容，不讲内部实现（代码、命令、组件名、文件结构），除非用户问。
- 能用图就不用字：效果图、关键帧、封面直接发图（SendUserFile），文字只写「看哪里」。
- 进度更新只写一行，比如「音频完成：配音 55.7 秒，配乐已合成」。
- 每个阶段结束都用同一个格式：结论 → 要点 → 需要你定（没有就写「下一步：……」）。

**提问一律是选择题。** 用 AskUserQuestion：
- 每题 2–4 个选项，**推荐项放第一个，标「（推荐）」**，每个选项用一句话说明选了会怎样。
- 能合并的问题一次问完，一次最多 4 题。不问能从口播或上下文推出来的事。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add isaachang/motion-video-workflow/motion-video-workflow@sha256:ba8f64f461f70888

The line at the top of this page pins the label git:20261011.0727d29, 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_cj7hxvvftybco2sx.svg)](https://markdownregistry.com/a/art_cj7hxvvftybco2sx)

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

Versions

The registry has recorded 5 versions of this file, between Oct 5, 2026 and Oct 11, 2026, about one every day.

versioncommittedcommitsizeaudit
git:20261011.0727d29 latest2026-10-11 0727d29 22,693 BA view · diff
git:20261009.9bae7ca2026-10-09 9bae7ca 21,909 BA view · diff
git:20261006.4e88fc52026-10-06 4e88fc5 21,044 BA view · diff
git:20261005.4457b932026-10-05 4457b93 19,343 BA view · diff
git:20261005.bae45802026-10-05 bae4580 18,078 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 (22693 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

isaachang/motion-video-workflow · 13 stars · license MIT · pushed 2026-10-11 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_cj7hxvvftybco2sx
GET https://markdownregistry.com/api/v1/resolve?ref=isaachang/motion-video-workflow/motion-video-workflow
GET https://markdownregistry.com/api/v1/blob/ba8f64f461f708887b2c3636038bdbc7183354f419aff1a66de3eec3c2e94047

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.

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