start

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Start

Paths:

${CLAUDE_SKILL_DIR}

means the folder containing this SKILL.md, and

${CLAUDE_PLUGIN_ROOT}

the plugin folder two levels above it.

Read

${CLAUDE_PLUGIN_ROOT}/PRINCIPLES.md

first: the rules every video follows (where, asking, looking real, motion, story, privacy, cost).

Every question goes in the question box: the AskUserQuestion tool (2-4 options, recommended first). Only in an agent without it, ask numbered questions in text.

Attached images: <paths>

in an answer: Read each first.

The user's whole job: drop a video, answer a few questions, approve the cut, approve the stills, both on the review page. Everything else is this skill's job.

P="${CLAUDE_PLUGIN_ROOT}/lib/ai_editor/profile.py"

. Run it with

python3

on Mac and Linux,

py

on Windows.

First run (the session-start line says so, or

setup.py doctor --quiet

prints a line): the setup skill's step 0 first (window, then installs in the background), then carry on here.

路径：

${CLAUDE_SKILL_DIR}

表示包含此 SKILL.md 的文件夹，

${CLAUDE_PLUGIN_ROOT}

表示向上两级的插件文件夹。

先阅读

${CLAUDE_PLUGIN_ROOT}/PRINCIPLES.md

：这是所有视频都必须遵循的规则（发布位置、提问方式、真实感、动态效果、叙事、隐私、成本）。

所有问题都应通过问题框提出：使用 AskUserQuestion 工具（2-4 个选项，第一项为推荐项）。只有在没有该工具的 Agent 中，才用文本提出编号问题。如果答案中含有

Attached images: <paths>

：先逐一读取。

用户的全部工作只有：投放视频、回答少量问题、批准剪辑、批准静帧，后两项都在审核页上完成。其余全部由本 skill 负责。

P="${CLAUDE_PLUGIN_ROOT}/lib/ai_editor/profile.py"

。在 Mac 和 Linux 上使用

python3

运行，在 Windows 上使用

py

运行。

首次运行（会话启动行有说明，或

setup.py doctor --quiet

输出了相应提示）：先执行 setup skill 的步骤 0（先显示窗口，然后在后台安装），然后回到此处继续。

0. Links first

0. 链接优先

If the message has any link, @handle or file path, route it before anything else. Never ask what a link is; the classifier knows.

bash

L="${CLAUDE_PLUGIN_ROOT}/lib/ai_editor/links.py"
python3 "$L" route "<the user's whole message>" [--own]

--own

only when the user says the video link is theirs ("my video", "I posted this"). It prints a list, already in the order to handle it: questions, creators, own footage, long videos, websites, music. Each item has a

kind

kind	do
`ask`	One question box for all `ask` items together (at most four): each item's `question` word for word, its `options` labels in order, the first marked "(Recommended)". The answer becomes the kind.
`creator`	creator-teardown quick mode on `handle` and `platform` (no platform: ask, TikTok first). With `urls` , write them to `picks.txt` and use `list <handle> --urls picks.txt` . Save it as the profile creator.
`own`	`python3 "$L" fetch "<url>" edits/<name>` ( `name` is in the item). It prints the file path; that is the video for step 1.
`long`	the clips skill, with this link as its source.
`product`	the product-video skill with this URL. A plain website (not a video site, file or share link) is always `product` , even after "edit my video": go straight to its brief, with no "did you mean your own footage" line.
`music`	the music question with rights (style-edit, or product-video's `music` step).
`unsupported`	say its `note` to the user, word for word, and go on with the rest.

An item with a

note

(Instagram profiles, Spotify, app stores, OneDrive): say the note once. fetch exit 3 means the site wants a login: ask in the question box "Use your browser's login for this one download?" (No, I'll download it myself (Recommended) / Yes, Chrome / Yes, another browser), and only on a yes re-run with

--cookies-from-browser <browser>

. Exit 1: say its message. Only download what the user may edit; a creator's video is for the teardown, not to re-edit.

如果消息中有任何链接、@handle 或文件路径，先对其进行路由处理，不要先做其他操作。永远不要询问某个链接是什么；分类器知道。

bash

L="${CLAUDE_PLUGIN_ROOT}/lib/ai_editor/links.py"
python3 "$L" route "<the user's whole message>" [--own]

仅当用户表示视频链接属于自己时使用

--own

（“我的视频”“这是我发布的”）。它会输出一个列表，且已按处理顺序排列：问题、创作者、自有素材、长视频、网站、音乐。每个条目都有一个

kind

：

kind	操作
`ask`	将所有 `ask` 项合并到一个问题框中（最多四项）：逐字使用每个条目的 `question` ，按顺序使用其 `options` 标签，第一项标记为“(Recommended)”。回答结果将成为该条目的 kind。
`creator`	针对 `handle` 和 `platform` 运行 creator-teardown 快速模式（没有 platform：先询问，TikTok 优先）。如果有 `urls` ，将它们写入 `picks.txt` ，然后使用 `list <handle> --urls picks.txt` 。将其保存为用户资料中的 creator。
`own`	`python3 "$L" fetch "<url>" edits/<name>` （ `name` 位于条目中）。它会输出文件路径；该路径就是步骤 1 使用的视频。
`long`	使用此链接作为来源运行 clips skill。
`product`	使用此 URL 运行 product-video skill。普通网站（而非视频站点、文件或分享链接）始终归为 `product` ，即使用户说过“edit my video”也一样：直接进入其 brief，不显示“did you mean your own footage”这一行。
`music`	音乐及版权问题（style-edit，或 product-video 的 `music` 步骤）。
`unsupported`	逐字向用户说明其 `note` ，然后继续处理其余内容。

带有

note

的条目（Instagram 资料、Spotify、应用商店、OneDrive）：将 note 告知一次。

fetch

退出码 3 表示站点要求登录：在问题框中询问“这次下载要使用你的浏览器登录吗？”（“不用，我会自己下载（推荐）”/“是，Chrome”/“是，其他浏览器”），仅在用户选择“是”后，使用

--cookies-from-browser <browser>

重新运行。退出码 1：原样告知其消息。仅下载用户有权编辑的内容；创作者的视频用于 teardown，而不是重新编辑。

1. The video

1. 视频

"Open the home page" (

nextwork-editor

/ai-editor:start

), "listen for jobs" or "take job <id>":

references/home.md

. No video, link or creator (a bare "edit my video"): ask Open the home page (Recommended) / I'll give the path / Use the sample take (cut's "No video yet?"). Edit folder:

IMG_1234.MOV

edits/img-1234

“打开主页”（

nextwork-editor

、

/ai-editor:start

）、“监听任务”或“领取任务 <id>”：参见

references/home.md

。如果没有视频、链接或创作者（用户只说“剪辑我的视频”）：询问 打开主页（推荐） / 我会提供路径 / 使用示例素材（

cut

的“还没有视频？”）。编辑目录：

IMG_1234.MOV

edits/img-1234

。

2. Intake: ask nothing the profile or style answers

2. 信息采集：不询问资料或风格已经回答的问题

bash

python3 "$P" missing --style     # answered at setup, or by the style picked in the window

JOB video

(the window picked the style), "just edit it", or no id printed: run

python3 "$P" defaults

and ask nothing. It keeps every saved answer and fills the rest with the first option (audience "people curious about the topic", goal follow, names found in what they say). Post no status about defaults: the review page shows an audience only when the user gave one (

review.py <edit> status "For <their audience>"

). Otherwise read

references/intake.md

and ask the printed ids in one question box. Profile:

python3 "$P" show

bash

python3 "$P" missing --style     # answered at setup, or by the style picked in the window

如果出现

JOB video

（窗口中选择了风格）、用户说“直接剪辑”（

just edit it

），或未打印任何 id：运行

python3 "$P" defaults

，不要提问。该命令会保留所有已保存的答案，并用第一个选项补全其余内容（受众为“对主题感兴趣的人”，目标为关注，名称从用户所述内容中查找）。不要发布任何有关默认值的状态说明：只有用户明确提供了受众时，审核页才显示受众（

review.py <edit> status "For <their audience>"

）。否则，读取

references/intake.md

，并在一个问题框中询问输出的所有 id。用户资料：

python3 "$P" show

。

3. Route

3. 路由

Do each step in order, skipping what is already done. Read each skill's SKILL.md before its step.

setup, if any step fails because a tool is missing (
```
setup.py doctor
```
says
```
FIX
```
).
creator-teardown in quick mode (its SKILL.md "Quick mode") for every profile creator without
```
creator-teardowns/<handle>/style.json
```
. Say the time first (about a minute per creator). Run several creators in parallel when the platform allows.
Blend the style:
```
python3 "$P" style edits/<name>
```
writes
```
edits/<name>/style.json
```
from the parts the user ticked for each creator, with the caption and sound answers laid over (no creator: the default style). It prints the copied style's skill (
```
skill: edit-like-<h> -> <path>
```
): read it and follow its learned rules through the cut and the edit.
```
no creator style.json found
```
: run step 2 again.
cut on the raw take, from its step 0b (start has already decided: cut, wait for the cut page approval, then style). The user approves the cut page. This is approval 1 of 2.
style-edit with
```
edits/<name>/style.json
```
. Renders on the cut's approve; the edit is approval 2. It reads the profile itself: the brand kit sets the look,
```
names
```
get real logos and captures,
```
assets_dir
```
images go on screen first,
```
avoid
```
is enforced by plan.py. Letterbox (wide take, title on top): cut
```
--max-pause 0.5
```
,
```
--layout letterbox
```
.
```
skill=<skill>
```
on the job: step 5 is that skill, not style-edit (
```
references/home.md
```
, Skill style).

Between steps say one line about what is next. Never ask the user to do a step the skill can do.

按顺序执行每个步骤，跳过已经完成的内容。执行每一步之前，先阅读相应 skill 的 SKILL.md。

setup：如果任何步骤因缺少工具而失败（
```
setup.py doctor
```
显示
```
FIX
```
），则执行此步骤。
对用户资料中每个尚无
```
creator-teardowns/<handle>/style.json
```
的创作者，以快速模式运行 creator-teardown（其 SKILL.md 中的“Quick mode”）。先告知预计耗时（每位创作者约一分钟）。如果平台允许，并行处理多个创作者。
融合风格：
```
python3 "$P" style edits/<name>
```
会根据用户为每位创作者勾选的部分，将字幕和声音答案叠加其上，写入
```
edits/<name>/style.json
```
（没有创作者时则使用默认风格）。它会输出所复制风格的 skill（
```
skill: edit-like-<h> -> <path>
```
）：读取该 skill，并在 cut 和 edit 全程遵循其学习到的规则。出现
```
no creator style.json found
```
时：再次执行步骤 2。
cut：从其步骤 0b 开始，对原始拍摄素材执行 cut（start 已决定流程：先 cut，等待 cut 页面获得批准，再进行 style）。用户需要在 cut 页面批准。这是两次批准中的第 1 次。
style-edit：使用
```
edits/<name>/style.json
```
。在批准 cut 后开始渲染；编辑成品是第 2 次批准。它会自行读取 profile：brand kit 决定视觉风格，
```
names
```
使用真实 logo 和实拍画面，
```
assets_dir
```
中的图片最先出现在画面中，
```
avoid
```
由
```
plan.py
```
强制执行。Letterbox（宽幅素材，标题置顶）：运行
```
cut --max-pause 0.5
```
、
```
--layout letterbox
```
。任务中指定
```
skill=<skill>
```
时：步骤 5 使用该 skill，而不是 style-edit（
```
references/home.md
```
的“Skill style”部分）。

每一步之间，用一行说明接下来要做什么。绝不要让用户去完成 skill 本可自行执行的步骤。

4. After

4. 后续处理

The render is handed over on the review page (style-edit step 8). Corrections go to the taste skill; a change of brand, creators or platform goes back into the profile with

python3 "$P" set ...

渲染结果会在审核页交付（style-edit 步骤 8）。需要修正时，转至 taste skill；需要更改品牌、创作者或平台时，使用

python3 "$P" set ...

将变更写回 profile。