Prototype · Preview: every server in the official registry, synced every 30 minutes. Sign in with Google to write reviews.Prototype · updated every 30 min
PopNx MCPMCP servers for people who use AI · explained in plain words

rea-video Skill

Repository ↗

by JuneYaooo★ 10,5141 skills

Install

What it does

Reverse-engineer any video, shot by shot: filmed, AI-generated or coded, and how to remake it. Breakdowns in the open VIDEO.md format. 逆向一切视频,逐个镜头看是拍的、AI 生成的还是代码做的,再告诉你怎么复刻;拆解结果按 VIDEO.md 格式输出。

  • Connects Instruction files the AI reads
  • Account or key Not confirmed (README mentions a key or .env file)
  • Category Coding
For makers: add a badge to your README

If you made this, paste this code into your README. The badge links back to this page.

[![Featured on PopNx MCP](https://mcp.popnx.com/badge/skill/juneyaooo-rea-video.svg)](https://mcp.popnx.com/en/skills/juneyaooo-rea-video)

Use together with

MCP servers that connect the AI to services for the same work

REA

Reverse engineer anything from your terminal or agent with one CLI and MCP server.

by morlutoWidely used↓ 388.7K/wk★ 468KUpdated 7 days ago

MCP · Connects a serviceRuns on your computer

Fallow

Codebase intelligence for TypeScript and JavaScript, exposed as structured MCP analysis tools.

by fallow-rsWidely used↓ 2.4M/wk★ 5.4KUpdated 2 days ago

MCP · Connects a serviceRuns on your computer

Desktop Commander

MCP server for terminal commands, file operations, and process management

by wonderwhy-erWidely used↓ 740.3K/wk★ 10.3KUpdated yesterday

MCP · Connects a serviceRuns on your computer

Similar Skills

Same kind of work, ordered like the Skills list

Compared with similar ones
This one
rea-video
reaandrej-karpathy-skillsgraphifyMoneyPrinterTurbo
MakerJuneYaooomorlutomultica-aiGraphify-Labsharry0703
Skills11111
GitHub stars10,514467,235234,125149,873144,332
Last code changeNov 18, 2026Nov 18, 2026Apr 20, 2026Nov 18, 2026Nov 18, 2026
LicenseApache-2.0MIT–Apache-2.0MIT

1 skills (instruction sets) by JuneYaooo that an AI reads and follows · not an MCP server

How a Skill differs from MCP

MCP = the hands

Connects the AI to an outside service or data, such as reading Notion or creating an invoice. A program or server has to be running.

Skill = the manual

A text file that teaches the AI how to do a task. It connects to nothing.

Some overlap: a few Skills run scripts that call tools, and a few MCP servers only send knowledge. Start from the task you want done.

Works with

Claude CodeCodex

From the maker’s README and the folders in the repo

Install

Is it safe?

  • Who made it

    GitHub account JuneYaooo (person), 6 years old

  • Use and upkeep

    ★ 10,514 stars · code last changed Nov 18, 2026

  • Any scripts?

    No, plain text files the AI reads and follows

  • Uses the internet?

    No scripts, so it does not go online by itself

  • Changes machine-wide settings?

    No hooks or writes to machine settings found

Checked automatically from the repo files at commit e83d587 (read only, nothing was run). Not a safety guarantee: read it and decide for yourself

First: which AI do you use?

Pick your app and this page shows only how to install it there

Option 1Upload to claude.ai (web and app)

Uploading to claude.ai would fail: the description is over 200 characters (302). Use "Let the AI install it" instead

Option 1Let Claude Code install it

Copy this sentence and paste it into a Claude Code chat

Where to install
Please install the skill rea-video from https://github.com/juneyaooo/rea-video folder skills/rea-video (commit e83d587) for all my projects, at ~/.claude/skills/rea-video. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill rea-video from https://github.com/juneyaooo/rea-video folder skills/rea-video (commit e83d587) into the project this chat is open in (at .claude/skills/rea-video). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Restart Claude Code, then type /rea-video or ask for a matching task and Claude picks it up

Checked against official docs Nov 12, 2026 · Source: code.claude.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.claude/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    git clone --depth 1 https://github.com/juneyaooo/rea-video.git /tmp/popnx-skill-juneyaooo-rea-video-e83d587 && mkdir -p ~/.claude/skills && cp -R '/tmp/popnx-skill-juneyaooo-rea-video-e83d587/skills/rea-video' ~/.claude/skills/rea-video
  3. Restart Claude Code, then type /rea-video or ask for a matching task and Claude picks it up

Skills you install yourself work in the ChatGPT desktop app, Codex CLI and the Codex IDE extension · ChatGPT on the web and mobile cannot use skills you install yourself, only skills that come with a plugin from the directory

ChatGPT desktop app

The ChatGPT desktop app has Codex built in, and Codex reads skills from ~/.agents/skills

Option 1Let ChatGPT install it

Open Codex in the ChatGPT desktop app and paste this sentence into the chat

Where to install
Please install the skill rea-video from https://github.com/juneyaooo/rea-video folder skills/rea-video (commit e83d587) for all my projects, at ~/.agents/skills/rea-video. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill rea-video from https://github.com/juneyaooo/rea-video folder skills/rea-video (commit e83d587) into the project this chat is open in (at .agents/skills/rea-video). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Option 2Put the folder there yourself

Put the rea-video folder at ~/.agents/skills/rea-video

~ is your home folder ($HOME)

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.agents/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    git clone --depth 1 https://github.com/juneyaooo/rea-video.git /tmp/popnx-skill-juneyaooo-rea-video-e83d587 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-juneyaooo-rea-video-e83d587/skills/rea-video' ~/.agents/skills/rea-video

After installing

  • ChatGPT desktop app: open Skills in the sidebar to see that the skill is there
  • To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name
  • Codex picks up newly installed skills by itself; if one does not show up, restart Codex

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

ChatGPT on the web and mobile

Skills you install yourself do not work here; only skills that come with a plugin from the directory

To use this skill with ChatGPT, use the ChatGPT desktop app as above

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

Option 1Let Codex install it

Copy this sentence and paste it into a Codex chat · Works in Codex inside the ChatGPT desktop app, Codex CLI and the IDE extension

Where to install
Please install the skill rea-video from https://github.com/juneyaooo/rea-video folder skills/rea-video (commit e83d587) for all my projects, at ~/.agents/skills/rea-video. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill rea-video from https://github.com/juneyaooo/rea-video folder skills/rea-video (commit e83d587) into the project this chat is open in (at .agents/skills/rea-video). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Codex picks up newly installed skills by itself; if one does not show up, restart Codex · To use it: in ChatGPT type @ and pick the skill · in Codex CLI or the IDE extension run /skills or type $ and the skill name

Checked against official docs Nov 15, 2026 · Source: learn.chatgpt.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.agents/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    git clone --depth 1 https://github.com/juneyaooo/rea-video.git /tmp/popnx-skill-juneyaooo-rea-video-e83d587 && mkdir -p ~/.agents/skills && cp -R '/tmp/popnx-skill-juneyaooo-rea-video-e83d587/skills/rea-video' ~/.agents/skills/rea-video
  3. Restart Codex, then ask for a matching task; Codex lists the skill

Option 1Let Cursor install it

Copy this sentence and paste it into a Cursor chat

Where to install
Please install the skill rea-video from https://github.com/juneyaooo/rea-video folder skills/rea-video (commit e83d587) for all my projects, at ~/.cursor/skills/rea-video. First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill rea-video from https://github.com/juneyaooo/rea-video folder skills/rea-video (commit e83d587) into the project this chat is open in (at .cursor/skills/rea-video). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

In Cursor’s Agent chat, type / and pick rea-video

Checked against official docs Nov 12, 2026 · Source: cursor.com

For Terminal users

A Skill is instructions the AI will follow. Read the files before installing, and install only from makers you trust.

  1. Open Terminal

    Mac: press Command+Space and type Terminal · Windows: the command below does not work in PowerShell; use “Let AI install it” above instead

  2. Copy the skill folder to ~/.cursor/skills

    This downloads the repo to a temporary folder and copies only the folders that contain a SKILL.md

    git clone --depth 1 https://github.com/juneyaooo/rea-video.git /tmp/popnx-skill-juneyaooo-rea-video-e83d587 && mkdir -p ~/.cursor/skills && cp -R '/tmp/popnx-skill-juneyaooo-rea-video-e83d587/skills/rea-video' ~/.cursor/skills/rea-video
  3. In Cursor’s Agent chat, type / and pick rea-video

Option 1Let the AI install it

For other apps that read skills. The sentence gives the paths for Claude Code, Codex and Cursor so the AI picks the one for your app · Copy this sentence into the app’s chat

Where to install
Please install the skill rea-video from https://github.com/juneyaooo/rea-video folder skills/rea-video (commit e83d587) for all my projects, at ~/.claude/skills/rea-video (in Codex use ~/.agents/skills/rea-video, in Cursor ~/.cursor/skills/rea-video). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the full path you will install to and wait for me to agree.
Please install the skill rea-video from https://github.com/juneyaooo/rea-video folder skills/rea-video (commit e83d587) into the project this chat is open in (at .claude/skills/rea-video; in Codex use .agents/skills/rea-video, in Cursor .cursor/skills/rea-video). First show me every file and tell me whether it has scripts or changes machine settings, then tell me the project name and the full path you will install to and wait for me to agree.

For one project, paste it into a chat that is open in that project’s folder · The AI always shows you the path before installing

The AI tells you what it will do first and asks your permission at every step

Checked against official docs Nov 12, 2026 · Source: code.claude.com, learn.chatgpt.com, cursor.com

For Terminal users

Other apps that support Agent Skills (such as Gemini CLI or GitHub Copilot) use different folders. Check that app’s guide, then copy the folder with the SKILL.md there.

View on GitHub ↗

Skill folders checked against the official Claude Code, Codex and Cursor guides on Nov 11, 2026

✓ Commands checked Nov 16, 2026

View the original SKILL.md

The text below comes from the maker’s repo, not from PopNx MCP

Showing the first 8,000 characters · Open the full file on GitHub

---
name: rea-video
description: 逆向拆解一条视频是怎么做出来的——逐镜头判断实拍 / 影视片段 / 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(可用 capsule-cinema、ChatCut 等复刻)。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 / 想二创或做一条同款"时使用。
---

# 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 11 类里选:实拍 / 影视片段 / 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、定格动画和影视片段(剪进来的电影、电视剧、短剧画面)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,整条复刻也可以用 ChatCut,见 `references/remake-tools.md`。

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)。

VLM(能看图的多模态模型)建议配,不强制,配置方法也在 `references/setup.md`。没配也照常跑,不要因此中止:
- 你自己能看图:你就是这次的"VLM",按下面的「看图复核并入」做。
- 你看不了图:遵守 `references/review.md` 的「看不了图时的规则」,回复末尾一句话建议配置 VLM。

**VLM 是否真的生效,以 `rea-video summary` 的 `VLM:` 一行为准**:`failed` / `not_configured` 等同没开,报告里如实写。

## 1. 标准流程

```bash
# ⓪ 先看记住了什么:用户偏好(默认引擎、是否开 VLM、给你的偏好说明)和常见纠正类型
rea-video memory
# ① 拆解(产出 out/<名>/VIDEO.md + video/(给你读的拆片包)、report.html / report.md(给用户看)、breakdown.json、storyboard.jpg、audio.png、shots/、stems/)
rea-video --env-file <你的 .env> decompose ref.mp4 -o out/ref --vlm --lang <zh|en>   # --lang 按用户提问的语言选(见「交付给用户」);没有 VLM 配置就去掉 --env-file 和 --vlm;字幕/花字是日文就加 --ocr-lang ja,是韩文就加 --ocr-lang ko;台词是孟加拉语就加 --asr-lang bn
# ② 看紧凑摘要:低置信镜头会被标出;先看 VLM: 那一行确认 VLM 是否生效
rea-video summary out/ref/breakdown.json
```

**省 token,按拆片包逐层读**(格式见仓库 `docs/videomd.md`;地图一行一个文件:`路径 | 约 token | 内容`):先读 `out/ref/VIDEO.md`(卡片 + 概览 + 地图,约 2k token),多数问题到这里就能答;要按镜头回答时读 `video/timeline.md`(一行一镜,键名带 `~` 的是推断,不带的是画面里看得到的);要核实某一镜再打开 `video/shots/<编号>.md` 和它 `frames` 里的截图;某一方面(声音、包装、复刻方案)按地图打开对应的 `video/*.md`。不要读 `breakdown.json`(几十万字)或 `report.md`(那是给人看的)。复核时每镜看 `shots/shot_XXX.jpg` 联系表就够(已含首 / 中 / 尾帧),`_first` / `_last` 是复刻时给生成模型参照用的,不用另开。

### 看图复核并入(能看图的 agent 必做,开了 VLM 也建议做低置信镜头)

```bash
rea-video review out/ref                      # 写出 review_tasks.json(每镜要看的图、工具判断、优先级)和 review_answers.json(答案模板)
# 读 review_tasks.json 的 instructions,逐镜看 images 里的图(priority=high 必看),把 label_probs / evidence / description / narrative / embedded_assets 填进 review_answers.json;narrative 是「这个镜头在讲什么」:role 选叙事作用(抓注意 / 交代背景 / 补信息 / 给证据 / 转折 / 给结论 / 引导行动 / 渲染情绪),point 一句话写它讲的那一点,报告会连成「叙事线」;若某镜头实为多刀合并(暗底图形与暗底口播交替时容易被合成一个长镜头),可加 split_suggestion(cuts 切点秒数 + labels 各段类别 + note),报告会在该镜头标注拆分建议,镜头边界本身不变
# 有人在演的镜头填 performance:主情绪、强度、看得见的表情和动作、镜头里的变化、说话的语气;复刻提示词和配音会照它还原表演
# 大幅度全身动作本身是看点(舞蹈、打斗、健身)的镜头再填 performance.move / movers / full_body / backdrop,复刻会改走「动作驱动」,按背景杂不杂、神态重不重要选驱动方式;带货、口播、边唱边小幅度动的不填(对口型 / 数字人就能做)
# 顶层 cast 填整片的角色 / 场景 / 道具(同一个角色跨镜头认成同一个,外观写到能据此复刻)和一句视觉风格;没开 VLM 时报告的「角色、场景与道具」一节全靠这里
# 顶层 story 填报告开头的「核心看点」:summary 一句话、hook 开头几秒怎么抓人、highlights 2–4 条能火的做法(手法 + 第几秒 + 为什么有效)
# 画面里拍到带字的东西(手机屏幕、包装、招牌)时,每镜填 overlay_text:这一镜后期加的字幕 / 花字原文,其余 OCR 文字报告当成画面内容
# 同一段成片出现不止一次(开头先放预告、结尾完整放)时,在较短的那处填 same_clip_as:另一处的镜头号,复刻只生成一次
rea-video apply-review out/ref --by <你的名字>  # 并入:重写 breakdown.json、report.md、report.html,打印改判了哪些镜头
rea-video summary out/ref/breakdown.json      # 用并入后的结果写回复
```

没看过的镜头 label_probs 留空 `{}`,会被跳过。你的答案会和确定性结果融合(不是直接覆盖),所以帧率、AIGC 标识这类强证据仍然起作用;如果并入后的结论和你的看法不同,在回复里写明理由。

融合规则、看不了图时怎么办、原片 / 转码视频的特殊规则,见 `references/review.md`。能看图时**一定要做看图复核**,开了 VLM 也要做,并且独立判断,不要照抄 VLM。

然后**一定要自己复核**,不要直接转述工具输出:

1. 先看 `storyboard.jpg` 和 `audio.png`,对整片建立整体印象。
2. 对标了"低置信,需要复核"的镜头,或"次选"概率很接近的镜头:
   - 打开 `shots/shot_XXX.jpg`(首、中、尾联系表)。
   - 必要时抽帧细看:`rea-video tiles ref.mp4 --start 12.3 --end 13.1 --every 0.1 -o out/ref/check.jpg`。
   - 按 `references/taxonomy.md` 的"易混对照表"逐条核对。
3. 角色与场景:`rea-video summary` 的「角色 / 场景」几行(拆片包 `video/cast.md`)。核对同一个角色有没有被 VLM 认成几个(逐镜描述里叫法不一致是常见问题),复刻时每个角色固定一张参考图贯穿所有生成单元;不对就在 `review_answers.json` 顶层 `cast` 里改。
4. 声音按 `references/audio.md` 复核:先听 `stems/vocals.wav`(人声干声)和 `stems/music.wav`(配乐),再看 `rea-video summary` 里的"声音来源"一行(视频类型 → 人声 / 音乐 / 音效来源)。信号层面检出的音效只是**低置信候选**,音效清单以 VLM 听到的为准;没开 VLM 时要说明"轻音效可能漏检"。
5. **实拍(口播 / 桌拍 / vlog / 商品)**:`rea-video summary` 末尾按维度列出「取景 / 机位 / 打光 / 剪辑 / 形式」(拆片包 `video/look.md`,含复刻拍摄方案和器材)。
   工具在画面主体上测量:有人脸用人脸,没有人脸(桌拍、商品、手)用画面里最清晰的区域,后者的景别是估算。
   看图时在 `review_answers.json` 每镜的 `aspects` 和顶层 `aspects` 里补像素测不出的:机位角度、自拍还是支架、主光是什么光源、眼神光、轮廓光/背景灯、画面里的光源、推测设备、视频形式。报告里测量、VLM、看图三个来源并列,不平均。
   注意:平台转码会压暗部,软硬和补光的测量偏保守。AI / 3D 画面也会给光影描述,但标明「不是拍摄方案」,只用于写生成提示词。
6. 真实素材按 `references/materials.md` 复核:代码模板里嵌入的截图和照片,确定性检测能找出大部分,但**暗色、半透明的背景照片会漏**。
7. 剪辑包装(`rea-video summary` 的「包装:」几行,拆片包 `video/packaging.md`,文件在 `packaging/`):
   - 字幕时间轴和样式是测出来的,一般可信;字体是什么要你看图补(工具只给颜色、描边、底框、字高)。
   - 贴纸:标了「需要看图确认」的,看 `packaging/sticker_XX.jpg` 和 `review_tasks.json` 里的 `frame_cmd`,在 `review_answers.json` 的 `packaging.stickers` 里填 `is_overlay` 和 `what`;工具漏掉的写进 `packaging.missed`。3D / 动画 / 版式画面里突然出现的物体工具不算贴纸,你看到是后期贴的再补。
   - 花字和标签分错类时在 `packaging.text` 里改 `kind`。
   - 音效「对应画面」一列是按时间就近对齐的,没开 VLM 时补出的候选(来源 `deterministic_anchored`)实测只有约四成是真音效,写成"可能"。
   - 「按台词定位」是花字 / 标题 / 贴纸落在哪句字幕上(句中第几秒、对上哪个词),「常驻图层」是跨切镜不变的免责声明、标题栏、角标。只在有字幕时才有;定位按时间推的,看图觉得不对就在回复里说明。
8. 第 3、5、6、7 步改了 `review_answers.json` 的,改完**再跑一次** `rea-video apply-review out/ref --by <你的名字>`,否则这些修改进不了报告。
9. 如果你的判断和工具不同,以你的复核为准,在回复里写明理由;有价值的话,建议用户把这条视频加进评测集(仓库 `docs/dev/evaluation.md`)。

用户指出判错或说出长期偏好时,按 `references/memory.md` 记下来(`rea-video correct` / `rea-video prefs`)。

## 2. 交付给用户

按 `references/output-template.md` 回复:先一句话结论,再内容与角色(这条视频讲什么、主要角色和场景),叙事线(每一步在抓注意、补信息还是给结论,见 `video/content.md`;建议用户保留这条线、换成自己的案例和素材来重写,不只是换个主角),然后复刻方案(按生成单元 / 拍摄场次组织)、分镜表、剪辑包装、声音、真实素材清单、不确定点,最后给 `report.html` 路径(用户版报告:先讲三层、再给照着做的复刻步骤,用户自己就能复刻);用户要 PDF 时运行 `rea-video pdf out/ref` 生成 `report.pdf`(需要本机有 Chrome / Chromium / Edge)。不要把 breakdown.json 贴进对话。

用户想复刻、二创、做同款或照着做一条自己的,或想知道这条视频怎么做出来、怎么实现时,在回复末尾告知可以用哪些工具来做(`references/remake-tools.md` 里列的都写,各一句)。

**报告和回复都用用户的语言。**语言的判断顺序:用户明确指定的语言(「用英文出报告」「report in Chinese」)> 用户提问所用的语言 > `rea-video memory` 里的 `lang` 偏好 > 中文。
- 工具支持 `--lang zh` 和 `--lang en`:`decompose` 时就传对,报告文件(`report.html` / `report.md`)、`summary` 输出、VLM 的画面描述和提示词都会是该语言;忘了传可以在 `apply-review out/ref --lang en` 时补上(会重新生成结论和报告文字;VLM 已写好的描述和提示词保持原语言)。看图复核时,`review_answers.json` 里的 evidence / description / prompt 也用这个语言写。
- 用户用日语、韩语等工具不支持的语言提问时,跑 `--lang en`,回复用用户的语言写;用户要该语言的报告文件时,把 `report.md` 翻译成 `report_<语言>.md` 放在同一目录,并说明 `report.html` 是英文的。
- 用户设了长期偏好(「以后都出英文报告」)就 `rea-video prefs lang en` 记下来。

## 3. 复刻(需要时)

报告分两部分:第一部分是拆解(结构,和用什么模型无关),第二部分是复刻方案(按一个模型排)。拆解不要因为复刻去合并镜头。

有 AI 镜头时,复刻方案按用户的意图和实际用的模型来排:
1. 问用户:用哪个模型或平台(即梦 / Seedance、可灵、Veo、海螺……,不要替用户选);整条都用模型重做,还是只生成原片里 AI 做的镜头;要换什么、换成什么、有没有参考图。写进 `out/ref/remake/intent.yaml`:

   ```yaml
   model: seedance-2.5
   generate: all          # all:整条用模型生成;ai(默认):只生成 AI 镜头,实拍的出拍摄方案
   swaps:
     - from: 女主播
       to: 三十岁左右的男主播,短发,深色西装
     - from: 原片的口红
       to: 用户的保温杯
       image: /绝对路径/product.jpg
   ```
2. 方案按这个模型的最新实际情况来:`rea-video models <id>` 看能力地图里的资料和核实日期,再上网核对它最新的官方文档和更新(有没有新版本,单次时长、参考视频 / 参考图的数量和时长、一次多镜头、首尾帧、原生音频、提示词写法有没有变)。能力地图里没有、或和最新资料不一致的,按能力地图的格式写进 `~/.rea-video/capabilities/models/<id>.yaml`(同 id 会覆盖自带的),写上来源和核实日期。
3. `rea-video plan out/ref`:按意图和模型出报告第二部分,并做方案检查。

Discussion

Ask, share a tip or report that it does not work. Sorted by what people marked helpful.

No posts yet. Be the first to ask or share.

Posts here are written by users, not the PopNx team.

Sign in to post

From GitHub

GitHub stars
10,514
Maker
JuneYaooo
Tried for real by the PopNx team
The PopNx studio team broke down a 15-second vertical clip offline (no vision model): 14 shots, first run 27 s (including a 209 MB model download), later runs 13.8 s · kept with conditions: it mislabels AI vs filmed on re-compressed clips, and its on-screen text reader has no Thai
  • Needs Python 3.10+ and ffmpeg · a CLI + Skill, not an MCP server
  • Offline mode needs no key · --vlm mode needs a paid vision-model key
  • First run downloads about 209 MB of ONNX models from GitHub, some without a sha check
  • Upstream docs include a sponsor (ChatCut) curl … | sh install line: read before running anything
  • install_skill.sh links the skill into your Claude skills folder
License
Apache-2.0
Last code change
Nov 18, 2026
SKILL.md files in the repo (including translated copies and templates)
1
Topics
agent-skills, ai-video, aigc-detection, claude-code, codex, ffmpeg, prompt-engineering, remotion, reverse-engineering, short-video, shot-detection, subtitles