#450 by GitHub stars

JuneYaooo/rea-video

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。

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

skills/rea-video/SKILL.md

Week of Nov 2, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → f831fc5e089a

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit f831fc5e089ab85943bce95a765545d4b52bffd4

git clone --filter=blob:none --no-checkout https://github.com/JuneYaooo/rea-video.git .hotskills/juneyaooo-rea-video && git -C .hotskills/juneyaooo-rea-video checkout --detach f831fc5e089ab85943bce95a765545d4b52bffd4 # Copy each selected skill directory from .hotskills/juneyaooo-rea-video into .claude/skills/<skill-name>/
git clone --filter=blob:none --no-checkout https://github.com/JuneYaooo/rea-video.git .hotskills/juneyaooo-rea-video && git -C .hotskills/juneyaooo-rea-video checkout --detach f831fc5e089ab85943bce95a765545d4b52bffd4 # Copy each selected skill directory from .hotskills/juneyaooo-rea-video into .agents/skills/<skill-name>/
2.7kGitHub stars
Not availablestars in 7 days
1skill in this repository
53commits in 30 days

Heat

Insufficient history

Not enough history yet to measure heat. It appears after a few days of data.

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Nov 3, 2026Nov 6, 20262,660

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

rea-video

When your agent uses it

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。

What it loads into context

Frontmatter

203 tokens

Always available to the agent

SKILL.md

3,066 tokens

When the skill is activated

Reference documents

9,919 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. 0. 环境
  2. 1. 标准流程
  3. 2. 交付给用户
  4. 3. 复刻(需要时)
  5. 参考文件
  6. 5. 不要做的事

Files

  • ../../.claude-plugin/marketplace.jsonasset276 bytes
  • ../../.claude-plugin/plugin.jsonasset437 bytes
  • SKILL.mdcore10,461 bytes
  • SKILL.mdcore10,461 bytes
  • SKILL.mdcore10,461 bytes
  • references/audio.mddoc6,810 bytes
  • references/materials.mddoc2,447 bytes
  • references/memory.mddoc1,113 bytes
  • references/output-template.mddoc4,177 bytes
  • references/remake.mddoc3,001 bytes
  • references/review.mddoc3,515 bytes
  • references/setup.mddoc2,759 bytes
  • references/taxonomy.mddoc7,793 bytes
Read SKILL.md

# 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
View the complete source on GitHub

Skills included

  • rea-video

Repository facts

License
Apache-2.0
Created
Oct 29, 2026
Last pushed
Nov 5, 2026
Forks
310
Open issues
2
Project activity
Active

Rank over the last 12 weeks

Now #450 · best #450

  1. #956 on Nov 4
  2. #525 on Nov 5
  3. #450 since Nov 6

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 5, 2026

Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.

Show 2 notes
  • skills/rea-video/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
  • skills/rea-video/SKILL.md:1 Analysis incomplete: Referenced executable target unavailable; not analyzed
Show all 9 signals by file

.claude-plugin/plugin.json

  • Network accessline 4
    "description": "逆向拆解视频:逐镜头判断实拍 / AI / 3D / 代码渲染 / 录屏,拆剪辑包装、声音和真实素材,给出复刻方案。",   "author": { "name": "June" },   "homepage": "https://github.com/JuneYaooo/rea-video",
  • Network accessline 5
    "author": { "name": "June" },   "homepage": "https://github.com/JuneYaooo/rea-video",   "repository": "https://github.com/JuneYaooo/rea-video",
  • Network accessline 6
    "homepage": "https://github.com/JuneYaooo/rea-video",
  • Network accessline 7
    "repository": "https://github.com/JuneYaooo/rea-video",

skills/rea-video/SKILL.md

  • Access to secretsline 35
    [Credential-related source omitted]

skills/rea-video/references/output-template.md

  • Access to secretsline 40
    [Credential-related source omitted]

skills/rea-video/references/setup.md

  • Network accessline 6
    pip install "rea-video[ocr] @ git+https://github.com/JuneYaooo/rea-video"   # 需要 ffmpeg;Python ≥ 3.10
  • Access to secretsline 17
    [Credential-related source omitted]
  • Access to secretsline 20
    [Credential-related source omitted]

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Some files could not be read; the facts below still hold.

Signal confidence: 5 facts

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeManifest .claude-plugin/marketplace.json.claude/skills/<skill-name>/
CodexNativeManifest AGENTS.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md skills/rea-video/SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md skills/rea-video/SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md skills/rea-video/SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md skills/rea-video/SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.

Add this badge to your README

It updates every night and links to this page.

JuneYaooo/rea-video: #450 on hotskills, 2.7k stars

[![JuneYaooo/rea-video on hotskills](https://hotskills.dev/badge/juneyaooo-rea-video.svg)](https://hotskills.dev/skill/juneyaooo-rea-video/)