video-setup

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Video Setup

视频设置

Ten minutes, once. At the end the creator has:

the tools the other skills call, installed and checked,
```
video-agent/voice.md
```
: who they are, how they talk, what they believe, what they can prove. Every script is written from it,
the editing studio ready, so the first edit starts right away,
permission rules, so Claude can run ffmpeg, yt-dlp and Remotion without asking each time,
if they want: their accounts connected through Treg (audit and publishing), and the keys for translation and images.

只需一次，十分钟。完成后，创作者将拥有：

其他 skill 会调用的工具，且已完成安装与检查，
```
video-agent/voice.md
```
：记录他们是谁、如何表达、相信什么以及能够证明什么。所有脚本都将据此编写，
已准备就绪的剪辑 studio，可以立即开始第一次剪辑，
权限规则，让 Claude 无需每次询问即可运行 ffmpeg、yt-dlp 和 Remotion，
可选的账户与 key：通过 Treg 连接账户，用于统计和发布，并配置翻译和图像生成所需的 key。

How to run it

如何运行

Talk in the creator's language. Simple words, no jargon.
One question per message. Offer choices when you can, recommended first.
Never invent anything about them: a fact you don't have becomes a question or a
```
{{placeholder}}
```
.

使用创作者的语言交流。使用简单直白的语言，不使用专业术语。
每条消息只问一个问题。可以提供选项时，尽量提供选项，并优先推荐最佳选项。
绝不编造任何关于创作者的信息：没有依据的事实应转化为问题或
```
{{placeholder}}
```
。

1. Tools

1. 工具

Run the checks and show one line per tool (✓ version, or ✗ missing):

bash

node -v
ffmpeg -version
yt-dlp --version
deno --version
git --version

Tool	Used by	macOS	Windows	Linux
Node 18+	video-edit (Remotion)	`brew install node`	`winget install OpenJS.NodeJS.LTS`	nodejs.org or your package manager
ffmpeg	video-edit, video-steal, long-to-short-videos, video-translate, video-publish	`brew install ffmpeg`	`winget install Gyan.FFmpeg`	`sudo apt install ffmpeg`
yt-dlp	video-viral, video-steal, long-to-short-videos, voice.md from videos	`brew install yt-dlp`	`winget install yt-dlp.yt-dlp`	`pipx install "yt-dlp[default]"`
deno	yt-dlp on YouTube (it needs a JavaScript runtime)	comes with yt-dlp	`winget install DenoLand.Deno`	`curl -fsSL https://deno.land/install.sh \| sh`
git, build tools	video-edit (gets the Remotion template, builds whisper.cpp)	`xcode-select --install`	`winget install Git.Git`	`sudo apt install git build-essential`
Codex (optional)	codex-images	`npm i -g @openai/codex` , then `codex login`	same	same

Give the commands for what is missing and let them run them (or run them yourself if they say so). Scripting-only users (video-script, video-viral) only need yt-dlp and deno. Codex is only for

/codex-images

and needs a ChatGPT plan; skip it if they don't want images.

Windows: after
```
winget
```
, close and reopen the terminal (and Claude Code), or the new commands are not found.
YouTube changes often. When yt-dlp fails on a link that plays in the browser, update it first (
```
brew upgrade yt-dlp
```
,
```
winget upgrade yt-dlp.yt-dlp
```
,
```
pipx upgrade yt-dlp
```
).

运行检查命令，并每个工具显示一行结果（✓ 版本号，或 ✗ 缺失）：

bash

node -v
ffmpeg -version
yt-dlp --version
deno --version
git --version

工具	用途	macOS	Windows	Linux
Node 18+	video-edit（Remotion）	`brew install node`	`winget install OpenJS.NodeJS.LTS`	nodejs.org 或 package manager
ffmpeg	video-edit、video-steal、long-to-short-videos、video-translate、video-publish	`brew install ffmpeg`	`winget install Gyan.FFmpeg`	`sudo apt install ffmpeg`
yt-dlp	video-viral、video-steal、long-to-short-videos、从视频生成 voice.md	`brew install yt-dlp`	`winget install yt-dlp.yt-dlp`	`pipx install "yt-dlp[default]"`
deno	YouTube 上的 yt-dlp（需要 JavaScript runtime）	随 yt-dlp 一同安装	`winget install DenoLand.Deno`	`curl -fsSL https://deno.land/install.sh \| sh`
git、构建工具	video-edit（获取 Remotion template，构建 whisper.cpp）	`xcode-select --install`	`winget install Git.Git`	`sudo apt install git build-essential`
Codex（可选）	codex-images	`npm i -g @openai/codex` ，然后运行 `codex login`	相同	相同

给出缺失工具对应的安装命令，并让创作者自行运行；如果他们明确要求，也可以由你代为运行。仅使用脚本类 skill 的用户（video-script、video-viral）只需要 yt-dlp 和 deno。Codex 仅用于

/codex-images

，并且需要 ChatGPT 套餐；如果他们不需要生成图片，则跳过。

Windows：使用
```
winget
```
后，关闭并重新打开终端（以及 Claude Code），否则系统找不到新命令。
YouTube 经常发生变化。如果 yt-dlp 无法处理一个在浏览器中可以正常播放的链接，请先更新它（
```
brew upgrade yt-dlp
```
、
```
winget upgrade yt-dlp.yt-dlp
```
或
```
pipx upgrade yt-dlp
```
）。

2. The folder

2. 文件夹

Create it at the root of the current project:

text

video-agent/
├── voice.md      who they are and how they talk (step 4)
├── swipe.md      hooks that worked in their niche (video-viral)
├── audit.md      what works on their own Instagram (video-audit)
├── log.md        one line per script written, so nothing repeats
├── scripts/      one file per week (video-script)
├── takes/        raw recordings (phone, camera, webcam, screen)
├── edits/        one folder per edited video (video-edit): final.mp4, post.md, cover.jpg, published.md
├── repurpose/    one plan per long video (long-to-short-videos)
├── images/       generated images not tied to a video (codex-images)
├── studio/       the Remotion project (step 3)
├── .env          their API keys, never shared (step 6)
└── .tmp/         scratch files, deleted after each run

log.md

starts with

# Script log

swipe.md

with

# Swipe file

If the project is in git, add these lines to its

.gitignore

(videos are heavy; the text files stay tracked):

gitignore

video-agent/takes/
video-agent/edits/**/*.mp4
video-agent/studio/public/
video-agent/studio/out/
video-agent/studio/node_modules/
video-agent/studio/whisper.cpp/
video-agent/.tmp/
video-agent/.env

video-agent/.env

holds keys: it must be ignored even if they skip the rest.

在当前项目根目录创建：

text

video-agent/
├── voice.md      他们是谁以及如何表达（第 4 步）
├── swipe.md      其细分领域中有效的 hooks（video-viral）
├── audit.md      自己的 Instagram 上哪些内容有效（video-audit）
├── log.md        每编写一个脚本记录一行，避免重复
├── scripts/      每周一个文件（video-script）
├── takes/        原始录制文件（手机、摄像机、摄像头、屏幕录制）
├── edits/        每个剪辑后视频一个文件夹（video-edit）：final.mp4、post.md、cover.jpg、published.md
├── repurpose/    每个长视频一个改编方案（long-to-short-videos）
├── images/       与具体视频无关的生成图像（codex-images）
├── studio/       Remotion 项目（第 3 步）
├── .env          他们的 API key，绝不共享（第 6 步）
└── .tmp/         临时文件，每次运行后删除

log.md

以

# Script log

开头，

swipe.md

以

# Swipe file

开头。

如果项目使用 git，请将以下内容添加到项目的

.gitignore

中（视频文件很大；文本文件仍保留在版本控制中）：

gitignore

video-agent/takes/
video-agent/edits/**/*.mp4
video-agent/studio/public/
video-agent/studio/out/
video-agent/studio/node_modules/
video-agent/studio/whisper.cpp/
video-agent/.tmp/
video-agent/.env

video-agent/.env

用于存放 key：即使创作者跳过其余配置，也必须忽略此文件。

3. The studio

3. studio

The editing studio (Remotion, whisper.cpp for the captions, a speech model) takes 5 to 15 minutes and about 2 GB to set up. Ask: now (recommended if they will edit soon, the first edit then starts right away), or later (video-edit does it the first time it runs).

Now: run step 2 of

video-edit

("The studio"), including the

Short

and

Wide

compositions and the

npx tsc --noEmit

check. Say what is downloading and how big before starting. Only for video-edit, long-to-short-videos and video-translate; scripting-only users skip it.

剪辑 studio（Remotion、用于生成字幕的 whisper.cpp 和一个语音模型）需要 5 到 15 分钟及约 2 GB 的安装空间。询问：现在安装（推荐，如果他们很快就要剪辑，这样第一次剪辑可以立即开始），还是以后再装（video-edit 首次运行时会自动完成）。

现在安装：运行

video-edit

的第 2 步（“studio”），包括

Short

和

Wide

compositions，以及

npx tsc --noEmit

检查。开始前说明正在下载的内容及其大小。此步骤仅适用于 video-edit、long-to-short-videos 和 video-translate；仅使用脚本类 skill 的用户可跳过。

4. voice.md

First the two settings at the top of the file: the language they record in, and their brand color (the accent of captions and cards; default

#FFD400

, a yellow that reads on any footage). Then ask how to build the rest:

From their videos (recommended when they have posted before): 3 to 5 links of their best talking videos (YouTube, Shorts, TikTok, Instagram reels). Pull the transcripts (
```
<lang>
```
= their language code:
```
en
```
,
```
fr
```
,
```
es
```
):
bash
```
yt-dlp --skip-download --write-auto-subs --write-subs --sub-langs "<lang>.*" --sub-format vtt -o "video-agent/.tmp/%(id)s.%(ext)s" "<url>"
```
Read them and fill the template from what they actually say: their real phrases, their pace (words ÷ minutes of speech), the words they repeat, the way they open and close. Then ask only what the transcripts can't tell (positions, proof, off limits, the ask). Delete
```
video-agent/.tmp/
```
after. YouTube links almost always give a transcript. TikTok sometimes does, Instagram almost never: for those, ask for a YouTube link or switch to the interview.
From an interview: ask the template's questions one at a time, in plain words ("What do you believe that most people in your niche get wrong?").

Either way, ask them to paste 3 short texts they wrote themselves, before any AI tool (a caption, a message, an email). They go in "Real samples" and teach the scripts their rhythm.

Write

video-agent/voice.md

from references/voice-template.md. Then read it back to them in 5 lines and ask what is wrong. A voice file is never finished: say they can run

/video-setup voice

any time to update it.

先设置文件顶部的两个选项：创作者录制时使用的语言，以及品牌颜色（字幕和卡片的强调色；默认为

#FFD400

，这种黄色在任何画面上都清晰醒目）。然后询问其余内容的构建方式：

来自他们的视频（推荐用于此前发布过内容的创作者）：提供 3 到 5 个最佳口播视频链接（YouTube、Shorts、TikTok、Instagram Reels）。提取转录文本（
```
<lang>
```
= 他们的语言代码：
```
en
```
、
```
fr
```
、
```
es
```
）：
bash
```
yt-dlp --skip-download --write-auto-subs --write-subs --sub-langs "<lang>.*" --sub-format vtt -o "video-agent/.tmp/%(id)s.%(ext)s" "<url>"
```
阅读这些转录文本，并根据他们实际使用的表达填写模板：真实措辞、语速（词数 ÷ 讲话分钟数）、经常重复的词，以及开场和收尾方式。然后只追问转录文本无法说明的信息（立场、证明材料、禁忌事项，以及希望受众采取的行动）。完成后删除
```
video-agent/.tmp/
```
。 YouTube 链接几乎总能提供转录文本。TikTok 有时可以，Instagram 几乎不行：对于这些平台，请要求创作者提供 YouTube 链接，或改用访谈方式。
通过访谈获取：用通俗易懂的语言逐个询问模板中的问题（“在你的细分领域中，大多数人都理解错了什么？”）。

无论采用哪种方式，都请创作者粘贴 3 段在未使用任何 AI 工具前亲自撰写的短文本，例如字幕、消息或邮件。这些内容会进入“真实样本”（Real samples）部分，让脚本掌握他们的表达节奏。

根据 references/voice-template.md 编写

video-agent/voice.md

。然后用 5 行内容读给他们听，并询问哪里有问题。voice 文件永远需要持续迭代：说明他们可以随时运行

/video-setup voice

进行更新。

5. Permissions

5. 权限

The other skills run the same few commands again and again. Pre-approve them for this project. Show the rules, ask, then merge them into

.claude/settings.json

. Create the file if it is missing. Keep every key and rule already there, and never remove anything.

json

{
  "permissions": {
    "allow": [
      "Bash(yt-dlp *)",
      "Bash(ffmpeg *)",
      "Bash(ffprobe *)",
      "Bash(npx remotion *)",
      "Bash(node sub.mjs *)"
    ]
  }
}

Only these. Never add
```
Bash(*)
```
,
```
Bash(rm *)
```
,
```
Bash(curl *)
```
or a rule for a whole interpreter (
```
Bash(node *)
```
,
```
Bash(python *)
```
).
Rules in the shared
```
settings.json
```
apply once the folder is trusted. A creator who keeps this project in git and doesn't want to share the rules can use
```
.claude/settings.local.json
```
instead (same format, personal).
Each skill also lists its own commands in its
```
allowed-tools
```
, which covers the turn the skill runs in. These rules cover every other turn.

其他 skill 会反复运行相同的几条命令。为此项目预先批准这些命令。展示规则、征求同意，然后将其合并到

.claude/settings.json

中。如果文件不存在，则创建它。保留其中已有的每个 key 和规则，绝不删除任何内容。

json

{
  "permissions": {
    "allow": [
      "Bash(yt-dlp *)",
      "Bash(ffmpeg *)",
      "Bash(ffprobe *)",
      "Bash(npx remotion *)",
      "Bash(node sub.mjs *)"
    ]
  }
}

仅允许这些规则。绝不添加
```
Bash(*)
```
、
```
Bash(rm *)
```
、
```
Bash(curl *)
```
，也不要添加针对整个 interpreter 的规则（如
```
Bash(node *)
```
或
```
Bash(python *)
```
）。
共享
```
settings.json
```
中的规则会在文件夹被信任后生效。如果创作者希望将项目保留在 git 中但不想共享这些规则，可以改用
```
.claude/settings.local.json
```
（格式相同，属于个人配置）。
每个 skill 还会在其
```
allowed-tools
```
中列出自己的命令，这仅覆盖该 skill 运行所在的当前轮次。这些规则则覆盖所有其他轮次。

6. Accounts and keys (optional)

6. 账户与 key（可选）

Three things, each only if they want the skill that needs it. Ask once, in one message:

For	What	Cost
`/video-audit` and `/video-publish`	Treg, with their Instagram, TikTok and YouTube connected	free on their own accounts
`/video-translate` (and `/video-steal` 's music level and sound effects, optional)	an ElevenLabs API key	their ElevenLabs plan
`/codex-images`	Codex logged in with their ChatGPT account	their ChatGPT plan

ElevenLabs: they create a key at elevenlabs.io/app/settings/api-keys and paste it themselves into

video-agent/.env

ELEVENLABS_API_KEY=...

(create the empty file and open it for them). Never ask for a key in the chat. Check it is there without printing it:

grep -c ELEVENLABS_API_KEY video-agent/.env

Codex:

codex --version

, then they run

codex login

(browser, "Sign in with ChatGPT").

共有三项配置，仅在创作者需要相应 skill 时才进行。一次性用一条消息询问：

用途	配置内容	费用
`/video-audit` 和 `/video-publish`	Treg，并连接他们的 Instagram、TikTok 和 YouTube	使用自有账户免费
`/video-translate` （以及 `/video-steal` 的音乐等级和音效，可选）	ElevenLabs API key	他们的 ElevenLabs 套餐
`/codex-images`	Codex，使用他们的 ChatGPT 账户登录	他们的 ChatGPT 套餐

ElevenLabs：他们自行在 elevenlabs.io/app/settings/api-keys 创建 key，并将其粘贴到

video-agent/.env

，格式为

ELEVENLABS_API_KEY=...

（创建空文件并替他们打开）。绝不要在聊天中索要 key。检查 key 是否存在，但不要打印它：

grep -c ELEVENLABS_API_KEY video-agent/.env

。

Codex：运行

codex --version

，然后由他们执行

codex login

（在浏览器中选择“Sign in with ChatGPT”）。

Treg

yt-dlp reads YouTube for free. TikTok and Instagram hide their numbers from scripts, a creator's own stats sit behind their login, and posting needs their accounts. Treg fills that gap: their own accounts connected once (stats and publishing, free), other creators' public numbers for about $0.001 a call. New verified accounts get $1.00 of credit once, enough for hundreds of calls.

Two ways to plug it in:

CLI, macOS and Linux. It needs uv (recommended, it fetches the right Python), or pipx or pip with Python 3.12 or 3.13. There is no Windows installer.
bash
```
curl -fsSL https://treg.to/install.sh | sh
treg login
```
```
treg login
```
opens the browser (GitHub, Google or an email code).

MCP, any OS, nothing to install:

claude mcp add --transport http treg https://treg.to/mcp/

, then

/mcp

to sign in. Each

treg catalog search

catalog get

call

and

balance

below becomes the MCP tool

catalog_search

catalog_get

call

balance

Their own accounts (connecting needs the CLI).

--capability post

asks for the rights to read their stats and to post; posting still waits for their yes on each video:

bash

treg connections connect --provider instagram --capability post
treg connections connect --provider tiktok --capability post
treg connections connect --provider youtube --capability post
treg connections ls

Each

connect

opens the platform's own login; they approve it there. Connect only the platforms they post on. Instagram needs a professional account (Creator or Business, a free switch in the app: Profile → menu → Account type and tools). Treg prints tips on stderr: add

2>/dev/null

when you read its JSON.

Instagram connected: offer

/video-audit

right after, it is the best first look at what works for them.

How every Treg call works, the rule for all the skills:

```
treg catalog search "<what you want to do>"
```
: describe the job, not a vendor ("list a TikTok account's videos with view counts").
```
treg catalog get <id>
```
: the parameters and the price. Say the price before calling. Their own connected accounts are marked free.
```
treg call <id> --query key=value
```
. A failed call is not charged.
```
treg balance
```
shows what is left; a 402 error means the balance is empty.

Permissions: add only the free, read-only commands, so every paid

treg call

still asks first:

json

"Bash(treg catalog *)",
"Bash(treg balance)",
"Bash(treg connections ls)"

yt-dlp 可以免费读取 YouTube。TikTok 和 Instagram 会向脚本隐藏相关数据，创作者自己的统计数据位于登录权限之后，而发布内容则需要使用他们的账户。Treg 填补了这一空白：一次连接他们自己的账户即可获取统计数据并发布内容，且免费；还可以按每次调用约 $0.001 获取其他创作者的公开数据。新完成验证的账户可一次性获得 $1.00 额度，足以支持数百次调用。

有两种接入方式：

CLI，适用于 macOS 和 Linux。它需要 uv（推荐，它会获取正确的 Python），也可以使用 pipx，或使用带 Python 3.12 或 3.13 的 pip。Windows 没有安装程序。
bash
```
curl -fsSL https://treg.to/install.sh | sh
treg login
```
```
treg login
```
会打开浏览器，可使用 GitHub、Google 或邮箱验证码登录。
MCP，适用于任何 OS，无需安装：运行
```
claude mcp add --transport http treg https://treg.to/mcp/
```
，然后使用
```
/mcp
```
登录。下文的每个
```
treg catalog search
```
、
```
catalog get
```
、
```
call
```
和
```
balance
```
命令，分别对应 MCP 工具
```
catalog_search
```
、
```
catalog_get
```
、
```
call
```
或
```
balance
```
。

连接他们自己的账户（连接操作需要使用 CLI）。

--capability post

会请求读取统计数据和发布内容的权限；每次发布仍需他们确认。

bash

treg connections connect --provider instagram --capability post
treg connections connect --provider tiktok --capability post
treg connections connect --provider youtube --capability post
treg connections ls

每次执行

connect

都会打开相应平台的登录页面；创作者需要在那里批准授权。仅连接他们实际发布内容的平台。Instagram 需要专业账户（Creator 或 Business，可在 App 中免费切换：Profile → menu → Account type and tools）。Treg 会在 stderr 输出提示：读取其 JSON 时，可以添加

2>/dev/null

。

连接 Instagram 后，建议立即运行

/video-audit

。这是了解哪些内容对他们最有效的最佳第一步。

每次 Treg 调用的工作方式，这是所有 skill 共同遵循的规则：

```
treg catalog search "<what you want to do>"
```
：描述要完成的任务，而不是供应商（“列出某个 TikTok 账户的视频和播放次数”）。
```
treg catalog get <id>
```
：返回参数和价格。调用前先说明价格。已连接的自有账户会标记为免费。
```
treg call <id> --query key=value
```
。失败的调用不会收费。
```
treg balance
```
显示剩余额度；402 错误表示余额已耗尽。

权限：仅添加免费、只读的命令，让每次付费的

treg call

仍会先请求确认：

json

"Bash(treg catalog *)",
"Bash(treg balance)",
"Bash(treg connections ls)"

7. Wrap up

7. 收尾

Show what is ready (✓ or skipped, one line each) and the path forward:

```
/video-audit
```
: what works on their own Instagram (fills audit.md).
```
/video-viral
```
: what works in their niche (fills swipe.md; once a month).
```
/video-script
```
: this week's scripts, hooks first, humanized.
Record them: phone, camera or webcam, one take per script, saved in
```
video-agent/takes/<slug>.mp4
```
.
```
/video-edit
```
: a short (vertical) or a full YouTube video (horizontal).
```
/video-steal
```
: a creator's reel they love into a style
```
video-edit
```
can use.
```
/long-to-short-videos
```
: a long video into finished shorts.
```
/video-translate
```
: a take in another language, in their voice.
```
/codex-images
```
: thumbnails and covers.
```
/video-publish
```
: YouTube, Instagram and TikTok.

展示已经准备就绪的内容（✓ 或已跳过，每项一行），以及后续操作路径：

```
/video-audit
```
：查看他们自己的 Instagram 上哪些内容有效（填充 audit.md）。
```
/video-viral
```
：查看其细分领域中哪些内容有效（填充 swipe.md；每月运行一次）。
```
/video-script
```
：生成本周的脚本，优先产出 hooks，并进行人性化处理。
录制：使用手机、摄像机或摄像头，每个脚本录制一条，保存到
```
video-agent/takes/<slug>.mp4
```
。
```
/video-edit
```
：制作竖版短视频或横版完整 YouTube 视频。
```
/video-steal
```
：将喜欢的创作者 reel 转换为
```
video-edit
```
可用的风格。
```
/long-to-short-videos
```
：将长视频转换为可直接发布的 shorts。
```
/video-translate
```
：将一条 take 翻译为其他语言，同时保留他们的语气。
```
/codex-images
```
：生成缩略图和封面。
```
/video-publish
```
：发布到 YouTube、Instagram 和 TikTok。

Later

后续

/video-setup <part>

jumps to one part:

tools

studio

voice

(rebuild or update voice.md),

permissions

treg

keys

/video-setup <part>

可以直接跳转到指定部分：

tools

、

studio

、

voice

（重新构建或更新 voice.md）、

permissions

、

treg

、

keys

。