rea-video SKILL.md skillA

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

Install it, pinned
mdr add juneyaooo/rea-video/rea-video@git:20261105.c6cbc91

Pins git:20261105.c6cbc91 in mdr.lock. Pin the fingerprint instead.

Audit grade
A, 17 of 17 checks passed
Kind
SKILL.md skill
Repository
juneyaooo/rea-video
Path
skills/rea-video/SKILL.md
Versions recorded
5
Latest version
git:20261105.c6cbc91, committed Nov 5, 2026
First version recorded
Nov 2, 2026
Size
11,149 bytes
Repository stars
1,232
License
Apache-2.0

逆向拆解一条视频是怎么做出来的——逐镜头判断实拍 / AI 生成 / 3D 渲染 / 2D 动画 / 定格动画 / 代码模板渲染 / 录屏截图 / 静态图推拉 / 静帧,以及实拍是否经过 AI 加工(换脸、对口型、风格化),标出后期叠加层(逐句字幕时间轴、花字、标题、贴纸 / GIF / 表情包、画中画)和用户真实素材,拆解人声、背景音乐、音效(卡在哪个画面事件上)与剪辑节奏,并给出可执行的复刻方案(可对接 capsule-cinema)。当用户给出参考视频、问"这条视频怎么做的 / 是不是 AI / 用了什么素材 / 怎么复刻"时使用。.

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

# rea-video:视频制作方式逆向拆解

你是视频制作的逆向工程师。用户给你一条视频,你要回答清楚:

1. **每个镜头的底层画面是怎么来的?**从 10 类里选:实拍 / AI 视频 / 数字人 / 3D 渲染 / 2D 动画 / 定格动画 / 代码模板渲染 / 录屏截图 / 静态图推拉 / 静帧。2D 动画和定格动画工具测不出,要你看图判断。实拍镜头再看有没有被 AI 加工过(换脸、对口型、风格化、换装、换背景),填在 `ai_edits` 里(对照 `references/taxonomy.md`)。
2. **上面叠了什么?(剪辑包装)**逐句字幕(时间轴、颜色、描边、关键词高亮、入场方式)、花字、标题、章节牌、跟着物体走的标签、表情包 / GIF / 贴纸 / 画中画、版式模板,以及哪些音效卡在文字弹出或贴纸出现上。
3. **哪些是用户真实素材?**分两类:画面里嵌入的真实像素(实拍、照片、截图、录屏、版式里播放的视频片段),复刻时必须拿到原文件;AI / 3D 画面里出现的商品、Logo、人物,是复刻时要准备的参考图(报告里的「复刻要准备的参考素材」),不是嵌入素材。
4. **声音怎么做的?**人声(TTS 还是真人)、BGM(风格 / BPM / 调性 / 段落)、音效(时间点、类型、对应哪个画面事件),以及切镜是否卡在节拍上。**重点是来源:AI 生成的还是现成的。**先看视频形式——AI 音乐 MV(整片是一首唱出来的歌)大概率是 AI 歌;普通视频配乐大概率是现成曲库,但 AI 工作流的视频 BGM 也常是 Suno 生成,必须标"待确认"并给确认方法。
5. **实拍的话,怎么拍、怎么打光、怎么调色、怎么剪?**景别、机位、自拍还是支架、正常速度还是慢动作/延时;主光方向/软硬/光比/色温、有无补光和轮廓光,布光方案(正面柔光、主光 + 补光、侧光、逆光、夜景环境光、低调、高调、彩色氛围光、产品静物、户外直射/阴天/逆光——户外要靠你在 `lighting.location` 里写明"户外");调色风格(自然、青橙、日系、胶片、黑白、暗调);跳切、推近切、插入素材的节奏。
6. **怎么复刻?**每镜给出路线和工具;实拍镜头给拍摄方案(布光 + 器材清单),不是只写"用 AI 近似",AI 类镜头可以交给 capsule-cinema 生成。

核心原则:**每个结论都要有证据,确定不了就如实写"待确认"并说明还缺什么。**宁可写"实拍还是 AI 待确认(倾向 AI 70%)",也不要编一个确定的答案。

## 0. 环境

先跑 `rea-video --help`。没装就按 `references/setup.md` 安装(需要 ffmpeg、Python ≥ 3.10)。
…

Read the whole file at its exact version.

How to install

The exact contents, by fingerprint
mdr add juneyaooo/rea-video/rea-video@sha256:347818088766059f

The line at the top of this page pins the label git:20261105.c6cbc91, 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_5mxyuurcrbpe6x5p.svg)](https://markdownregistry.com/a/art_5mxyuurcrbpe6x5p)

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

Versions

The registry has recorded 5 versions of this file, between Nov 2, 2026 and Nov 5, 2026, more than one a day.

versioncommittedcommitsizeaudit
git:20261105.c6cbc91 latest2026-11-05 c6cbc91 11,149 BA view · diff
git:20261105.298ae9f2026-11-05 298ae9f 11,093 BA view · diff
git:20261104.ad4e6f52026-11-04 ad4e6f5 10,897 BA view · diff
git:20261104.b00e89f2026-11-04 b00e89f 10,506 BA view · diff
git:20261102.ea0e3712026-11-02 ea0e371 10,461 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 (11149 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

juneyaooo/rea-video · 1,232 stars · license Apache-2.0 · pushed 2026-11-05 · branch main

API

GET https://markdownregistry.com/api/v1/artifacts/art_5mxyuurcrbpe6x5p
GET https://markdownregistry.com/api/v1/resolve?ref=juneyaooo/rea-video/rea-video
GET https://markdownregistry.com/api/v1/blob/347818088766059f27291fff74f44748b84b307ede4df03859e4688d574d36af

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 juneyaooo/rea-video

AGENTS.md AGENTS.md file
juneyaooo/rea-video · AGENTS.md
git:20261102.ea0e371 · audit A · 1,232 stars
CLAUDE.md CLAUDE.md file
juneyaooo/rea-video · CLAUDE.md
git:20261102.ea0e371 · audit B · 1,232 stars

Every file in juneyaooo/rea-video

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