make-a-video

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Make a Video — The Beginner-to-Finished-MP4 Skill

制作视频——从新手到成品MP4的技能指南

Two phases, eight sequential gates. Every gate produces a concrete artifact the next gate consumes. Don't skip gates.

分为两个阶段，八个连续环节。每个环节生成的具体成果将作为下一个环节的输入，请勿跳过任何环节。

When to use this skill — and when to hand off

何时使用本技能——以及何时转交其他工具

Use this skill when:

The user is new to HyperFrames and starting from a concept, script, or outline
They want an end-to-end walkthrough, not framework reference material
They haven't decided on format yet

Hand off when:

The user pastes a URL and wants a video from that site → invoke
```
/website-to-hyperframes
```
The user explicitly wants a 9:16 vertical talking-head with face-cam + scene overlays → run Gates 1–4 here, then invoke
```
/short-form-video
```
from Gate 5 onward
The user asks for framework rules, not a video → invoke
```
/hyperframes
```

使用本技能的场景：

用户是HyperFrames新手，从概念、脚本或大纲开始创作
用户需要端到端的引导流程，而非框架参考资料
用户尚未确定视频格式

转交其他工具的场景：

用户粘贴URL并希望从该网站生成视频 → 调用
```
/website-to-hyperframes
```
用户明确想要9:16竖屏带摄像头画面+场景叠加的访谈类视频 → 完成本技能的第1-4环节后，从第5环节开始调用
```
/short-form-video
```
用户询问框架规则而非视频制作方法 → 调用
```
/hyperframes
```

The two phases

两个阶段

Phase 1 — INTERVIEW (Gates 1–4): one conversational pass to gather everything before touching code. Intent, format, script, voice, style, assets, pacing. Synthesize into a
```
BRIEF.md
```
and wait for explicit approval.
Phase 2 — BUILD (Gates 5–8): scaffold → storyboard → compositions → lint → Studio preview → draft render → visual verification → MP4 preview → final render.

阶段1 — 需求访谈（第1-4环节）： 通过一轮对话收集所有需求后再进行代码操作。包括目标意图、格式、脚本、语音、风格、素材、节奏。将信息整理为
```
BRIEF.md
```
并等待用户明确批准。
阶段2 — 视频构建（第5-8环节）： 搭建项目框架→制作分镜脚本→合成视频→代码检查→Studio预览→草稿渲染→视觉验证→MP4预览→最终渲染。

Gate 1 · Intent & format

第1环节 · 目标意图与格式

Ask one question at a time via

AskUserQuestion

, multiple-choice where possible.

What's this video for? (promo · social ad · launch teaser · product demo · tutorial · explainer · intro/outro card · other)
Who's the audience? (open-ended)
Target duration? (10–20s short · 20–45s promo · 45–90s explainer · 1.5–3 min lesson · custom)
Aspect ratio? (16:9 1920×1080 · 9:16 1080×1920 · 1:1 1080×1080)
Frame rate? (30 default · 60 for crisp UI · 24 cinematic)
Platform / delivery constraints? (file size · deadline · where it'll play)

Gate: all six captured. If the answer is 9:16 + face-cam, plan to hand off to

/short-form-video

at Gate 5.

Full question bank:

Read: references/interview-questions.md

通过

AskUserQuestion

逐个提问，尽可能采用选择题形式。

该视频的用途是什么？（推广·社交广告·发布预告·产品演示·教程·讲解·片头/片尾卡片·其他）
目标受众是谁？（开放式问题）
目标时长？（10-20秒短视频·20-45秒推广视频·45-90秒讲解视频·1.5-3分钟课程·自定义时长）
画面比例？（16:9 1920×1080 · 9:16 1080×1920 · 1:1 1080×1080）
帧率？（默认30帧·清晰UI用60帧·电影质感用24帧）
平台/交付限制？（文件大小·截止日期·播放平台）

完成标志： 收集到以上6项信息。如果用户选择9:16比例+摄像头画面，计划在第5环节转交至

/short-form-video

。

完整问题库：

Read: references/interview-questions.md

Gate 2 · Script & voice

第2环节 · 脚本与语音

Script source? (paste · outline → I'll draft · I'll record · TTS from text · no narration)
If TTS: voice preference. Offer choices from
```
npx hyperframes tts --help
```
. Also capture pace.
If face-cam: recording path · full-screen or corner placement · need transcription? (
```
npx hyperframes transcribe <file> --model small.en --json
```
)
Captions? (off · hype · corporate · karaoke-word-by-word · minimal)

Gate: script captured (or drafted), audio plan captured, caption plan captured.

脚本来源？（粘贴脚本·提供大纲→我来撰写·自行录制·文本转语音（TTS）·无旁白）
若选择TTS：语音偏好。提供
```
npx hyperframes tts --help
```
中的选项，同时记录语速要求。
若使用摄像头画面：录制文件路径·全屏或角落放置·是否需要转录？（命令：
```
npx hyperframes transcribe <file> --model small.en --json
```
）
是否添加字幕？（关闭·活力风格·商务风格·逐词卡拉OK风格·极简风格）

完成标志： 已收集到脚本（或已撰写）、音频方案、字幕方案。

Gate 3 · Style intake

第3环节 · 风格采集

Before asking the user anything, inventory existing assets. Check

<workspace-root>/assets/

and any project

assets/

folder. Don't ask for what's already there.

Then ask progressively — they don't need answers to all of these:

Style guide or brand doc? (paste/path · no)
Color palette? (hex codes · none — use MOTION_PHILOSOPHY defaults)
Fonts? (Google Fonts name(s) · file paths · none — use Inter + JetBrains Mono defaults)
Logo file? (path · none — use text wordmark instead)
Reference videos for vibe? (URLs/paths · none)
Other assets? (screenshots · product photos · b-roll · music — list paths)
MOTION_PHILOSOPHY aesthetic (black canvas · chrome type · perspective grid · whip transitions) or a different feel?
Pacing? (kinetic 1–2s · balanced 2–3s · relaxed 3–5s)
Music? (none · ambient pad 0.15 · music bed 0.4 · full 0.8 — file path if they have one)
Outro / call-to-action text?

Never impose a brand on the user. Fall back to MOTION_PHILOSOPHY defaults only when they explicitly decline to supply a style.

Full style flow + MOTION_PHILOSOPHY defaults:

Read: references/style-intake.md

在向用户提问前，先盘点现有素材。检查

<workspace-root>/assets/

及项目的

assets/

文件夹，不要询问已存在的素材。

然后逐步提问——用户无需回答所有问题：

是否有风格指南或品牌文档？（粘贴内容/提供路径·无）
配色方案？（十六进制代码·无——使用MOTION_PHILOSOPHY默认配色）
字体？（Google Fonts名称·文件路径·无——使用Inter + JetBrains Mono默认字体）
Logo文件？（路径·无——使用文字标识替代）
参考风格视频？（URL/路径·无）
其他素材？（截图·产品照片·B-roll素材·音乐——列出路径）
采用MOTION_PHILOSOPHY美学风格（黑色画布·镀铬文字·透视网格·快速转场）还是其他风格？
节奏？（动感1-2秒·平衡2-3秒·舒缓3-5秒）
音乐？（无·氛围铺垫0.15·背景音乐0.4·完整配乐0.8——若有文件请提供路径）
片尾/行动号召（CTA）文本？

切勿向用户强加品牌风格。仅当用户明确拒绝提供风格信息时，才使用MOTION_PHILOSOPHY默认设置。

完整风格采集流程+MOTION_PHILOSOPHY默认设置：

Read: references/style-intake.md

Gate 4 · Brief synthesis (HARD-GATE before building)

第4环节 · 需求简报整理（构建前的强制环节）

Read
MOTION_PHILOSOPHY.md
if it exists in the workspace root — mandatory if present. If missing, proceed with the defaults in
```
references/style-intake.md
```
and note the absence in the brief.
Ask where projects live if it's not obvious:
- If
```
video-projects/
```
  exists → use
```
video-projects/<slug>/
```
- Otherwise → ask the user
Write
<project-folder>/BRIEF.md
:
- slug · intent · audience · dimensions · fps · duration
- script (full or outline)
- voice choice · caption plan · face-cam plan
- style profile: palette (hex), fonts, logo path, reference videos
- pacing
- asset inventory with paths
- outro / CTA text
Show the brief. WAIT for explicit approval. Don't proceed to Gate 5 without a clear "yes, build it."

阅读
MOTION_PHILOSOPHY.md
：如果工作区根目录存在该文件则必须阅读；若缺失，使用
```
references/style-intake.md
```
中的默认设置，并在简报中注明文件缺失。
询问项目存储位置（若不明确）：
- 若
```
video-projects/
```
  已存在 → 使用
```
video-projects/<slug>/
```
- 否则 → 询问用户
撰写
<project-folder>/BRIEF.md
：
- 项目标识（slug）·目标意图·受众·尺寸·帧率·时长
- 脚本（完整内容或大纲）
- 语音选择·字幕方案·摄像头画面方案
- 风格配置：配色（十六进制）、字体、Logo路径、参考视频
- 节奏
- 素材清单及路径
- 片尾/CTA文本
展示简报，等待用户明确批准。未得到明确的“同意，开始构建”前，请勿进入第5环节。

Gate 5 · Scaffold & storyboard

第5环节 · 搭建项目框架与制作分镜脚本

Handoff check first

先检查是否需要转交

If the brief describes a 9:16 vertical talking-head with face-cam + scene overlays, invoke

/short-form-video

NOW and hand off the brief. Its 4-layer scaffold is purpose-built for that format.

Otherwise continue:

如果简报描述的是9:16竖屏带摄像头画面+场景叠加的访谈类视频，立即调用

/short-form-video

并转交简报。该工具的4层框架专为该格式设计。

否则继续以下步骤：

Scaffold

搭建项目框架

```
mkdir <project-folder>
```
If a sibling project with similar format exists, offer to copy its
```
hyperframes.json
```
+
```
meta.json
```
as a template. Otherwise from inside the folder:
```
npx hyperframes init
```
Edit
```
meta.json
```
with the user's slug, dimensions, fps.
Copy supplied assets into
```
<project-folder>/assets/
```
.
Create
```
<project-folder>/assets/style-profile.md
```
from Gate 3 — single source of truth for palette/fonts/logo.

```
mkdir <project-folder>
```
若存在格式类似的同级项目，可提议复制其
```
hyperframes.json
```
+
```
meta.json
```
作为模板。否则进入项目文件夹执行：
```
npx hyperframes init
```
编辑
```
meta.json
```
，填入用户的项目标识（slug）、尺寸、帧率。
将提供的素材复制到
```
<project-folder>/assets/
```
。
根据第3环节的内容创建
```
<project-folder>/assets/style-profile.md
```
——作为配色/字体/Logo的唯一参考来源。

Storyboard

制作分镜脚本

Generate

<project-folder>/STORYBOARD.md

using the template in

references/storyboard-template.md

. Every beat gets:

Beat N — TITLE (start–end, duration) — Concept in one sentence
Visual elements: [each element, size, animation, timing]
Motion language: [kind of motion]
Eases used: [3–4 distinct GSAP eases]
Exit: [transition into next beat]
Audio: [VO line / SFX / music layer]

Top of file: a timing table with scene · start · duration · composition file.

Propose a rule-of-threes structure:

Act 1 (hook) ≈ 20% of duration
Act 2 (body) ≈ 55%
Act 3 (payoff + outro with 4–6 second hold) ≈ 25%

(MOTION_PHILOSOPHY §0 Law 9, §1.)

Map user intents → catalog blocks:

Read: references/catalog-intent-map.md

Gate: show storyboard + timing table. Iterate until the user approves.

使用

references/storyboard-template.md

中的模板生成

<project-folder>/STORYBOARD.md

。每个节拍需包含：

节拍N — 标题（开始-结束时间，时长）—— 一句话描述概念
视觉元素：[每个元素的大小、动画、时间点]
动效语言：[动效类型]
缓动效果：[3-4种不同的GSAP缓动效果]
转场：[进入下一节拍的转场方式]
音频：[旁白台词/音效/音乐层]

文件顶部：包含场景·开始时间·时长·合成文件的时间轴表格。

建议采用三段式结构：

第一幕（钩子）≈ 总时长的20%
第二幕（主体）≈ 总时长的55%
第三幕（收尾+片尾停留4-6秒）≈ 总时长的25%

（MOTION_PHILOSOPHY §0 第9条，§1）

用户意图→组件映射：

Read: references/catalog-intent-map.md

完成标志： 展示分镜脚本+时间轴表格，迭代至用户批准。

Gate 6 · Build compositions

第6环节 · 合成视频

Invoke

/hyperframes

for framework rules. This skill owns the scaffold and discipline;

/hyperframes

enforces the rules.

调用

/hyperframes

获取框架规则。本技能负责项目框架和流程规范；

/hyperframes

负责执行规则。

Scaffold every sub-composition

搭建每个子合成模块

html

<div data-composition-id="scene-name" data-start="..." data-duration="...">
  <style>[data-composition-id="scene-name"] { /* scoped */ }</style>
  <!-- DOM -->
  <script>
    (function(){
      const SLOT_DURATION = ...;
      const tl = gsap.timeline({ paused: true });
      // ... tweens ...
      tl.to({}, { duration: SLOT_DURATION }, 0);   // anchor — MOTION_PHILOSOPHY Law 11
      window.__timelines["scene-name"] = tl;
    })();
  </script>
</div>

Full boilerplate + captions pattern + ambient-bg pattern:

Read: references/composition-scaffold.md

html

<div data-composition-id="scene-name" data-start="..." data-duration="...">
  <style>[data-composition-id="scene-name"] { /* 作用域样式 */ }</style>
  <!-- DOM元素 -->
  <script>
    (function(){
      const SLOT_DURATION = ...;
      const tl = gsap.timeline({ paused: true });
      // ... 动画补间 ...
      tl.to({}, { duration: SLOT_DURATION }, 0);   // 锚点——MOTION_PHILOSOPHY第11条规则
      window.__timelines["scene-name"] = tl;
    })();
  </script>
</div>

完整模板+字幕模式+背景模式：

Read: references/composition-scaffold.md

Build rules

构建规则

Ambient background on
```
data-track-index="0"
```
for the full composition duration.
Kinetic-type openers: per-word stagger 0.06–0.10s.
Captions as body-level siblings of the root composition in
```
index.html
```
, each with
```
data-track-index ≥ 20
```
. Never inside scene timelines (MOTION_PHILOSOPHY §3.13).
Catalog blocks installed via
```
npx hyperframes add <name>
```
. Immediately scope the block's CSS to
```
[data-composition-id="..."]
```
— catalog blocks ship with
```
html, body { ... }
```
rules that bleed into the parent document when loaded as sub-compositions.
Vertical + face-cam: wrap native 1920×1080 face in a transform (
```
translate
```
+
```
scale
```
) for bottom-half or full-screen mode. (If you end up here instead of
```
/short-form-video
```
, strongly consider the handoff.)
Apply ONLY what the user supplied. Their palette, their fonts, their logo. Don't inject anything else. If they chose MOTION_PHILOSOPHY defaults, pull the palette + font pair from
```
references/style-intake.md
```
.

背景层放在
```
data-track-index="0"
```
，覆盖整个合成时长。
动感文字开场：逐字 stagger 0.06-0.10秒。
字幕作为
```
index.html
```
中根合成模块的同级元素，每个字幕的
```
data-track-index ≥ 20
```
。切勿放在场景时间轴内（MOTION_PHILOSOPHY §3.13）。
组件库模块通过
```
npx hyperframes add <name>
```
安装。立即将模块的CSS作用域限定为
[data-composition-id="..."]
——组件库模块默认带有
```
html, body { ... }
```
规则，作为子合成加载时会影响父文档。
竖屏+摄像头画面：将原生1920×1080摄像头画面通过transform（
```
translate
```
+
```
scale
```
）调整为下半屏或全屏模式。（若未转交至
```
/short-form-video
```
而进入此步骤，强烈建议转交。）
仅使用用户提供的内容：用户指定的配色、字体、Logo。请勿添加其他内容。若用户选择MOTION_PHILOSOPHY默认设置，从
```
references/style-intake.md
```
中获取配色+字体组合。

Determinism

确定性要求

Math.random()

, no

Date.now()

, no render-time

fetch()

. Use seeded PRNGs or harmonic-sin hashes (MOTION_PHILOSOPHY §3.10).

禁止使用

Math.random()

、

Date.now()

、渲染时的

fetch()

。仅使用种子化伪随机数生成器（PRNG）或谐波正弦哈希（MOTION_PHILOSOPHY §3.10）。

Gate 7 · Lint → Studio preview (PREVIEW GATE 1 — MANDATORY)

第7环节 · 代码检查→Studio预览（强制预览环节1）

```
npx hyperframes lint
```
— fix all errors, triage warnings.
```
npx hyperframes preview
```
in the background.
Wait for "Studio running" on
```
http://localhost:3002
```
.
Hand the user the URL plus individual composition URLs (
```
http://localhost:3002/?comp=<id>
```
). If the project has WebGL shader blocks, lead with the individual URLs — software WebGL fallback can stall the master composition.
WAIT for explicit "looks good, render a draft" before proceeding. Silence is not approval.

Hot reload is on — edits show up live.

```
npx hyperframes lint
```
— 修复所有错误，分类处理警告。
在后台执行
```
npx hyperframes preview
```
。
等待提示“Studio running”，地址为
```
http://localhost:3002
```
。
将URL加上单个合成模块的URL（
```
http://localhost:3002/?comp=<id>
```
）提供给用户。如果项目包含WebGL着色器模块，优先提供单个模块的URL——软件WebGL fallback可能会导致主合成模块加载卡顿。
**等待用户明确回复“看起来不错，渲染草稿”**后再继续。沉默不代表批准。

热重载已开启——修改内容会实时显示。

Gate 8 · Draft render → visual verification → MP4 preview → final

第8环节 · 草稿渲染→视觉验证→MP4预览→最终渲染

Draft render

草稿渲染

bash

npx hyperframes render --quality draft --output renders/<slug>-draft.mp4

bash

npx hyperframes render --quality draft --output renders/<slug>-draft.mp4

Visual verification (MANDATORY before delivery)

视觉验证（交付前强制环节）

Lint passing ≠ design working. Extract frames and view them.

```
mkdir -p renders/frames
```

For every beat hero moment AND every transition:

bash

ffmpeg -y -ss <t> -i renders/<slug>-draft.mp4 -frames:v 1 -q:v 2 renders/frames/t<t>.png

Call the
Read
tool on every PNG. The Read tool loads the image into context — don't just list filenames.
Confirm per frame: no cropped faces, correct face-mode per scene, text readable and on-palette, no overflow, transitions land on intended words, no blank frames.
If anything's wrong: fix → re-render → re-verify. Never ship a broken draft.

代码检查通过≠设计无误。提取帧并查看每帧内容。

```
mkdir -p renders/frames
```

针对每个节拍的关键画面以及每个转场执行：

bash

ffmpeg -y -ss <t> -i renders/<slug>-draft.mp4 -frames:v 1 -q:v 2 renders/frames/t<t>.png

对每张PNG调用
Read
工具。Read工具会将图片加载到上下文——请勿仅列出文件名。
逐帧确认：无面部裁剪、每个场景的摄像头模式正确、文字清晰且符合配色、无内容溢出、转场落在预期文字上、无空白帧。
若发现问题：修复→重新渲染→重新验证。切勿交付有问题的草稿。

MP4 preview (PREVIEW GATE 2 — MANDATORY)

MP4预览（强制预览环节2）

bash

npx serve renders -p 8080 -n

Do NOT use Python's

http.server

— it doesn't support HTTP Range requests, so scrubbing breaks.

Hand the user

http://localhost:8080/<slug>-draft.mp4

. WAIT for explicit sign-off on playback and audio sync.

bash

npx serve renders -p 8080 -n

请勿使用Python的
http.server
——它不支持HTTP Range请求，会导致拖拽播放失效。

将

http://localhost:8080/<slug>-draft.mp4

提供给用户。等待用户明确确认播放和音频同步无误。

Final render

最终渲染

bash

npx hyperframes render --quality standard --output renders/<slug>-final.mp4

Report the output path. Done.

Full preflight + pre-delivery checklist:

Read: references/build-checklist.md

bash

npx hyperframes render --quality standard --output renders/<slug>-final.mp4

告知用户输出路径。完成。

完整预检+交付前检查清单：

Read: references/build-checklist.md

Non-negotiables (load-bearing — do not soften)

不可协商规则（核心要求——请勿放宽）

DO NOT skip PREVIEW GATE 1 (Studio) or PREVIEW GATE 2 (rendered MP4). Two gates per build, always.
DO NOT claim a render is done until frames have been extracted AND Read via the Read tool.
DO NOT build anywhere but inside a dedicated project folder. Never put
```
index.html
```
at the workspace root.
DO NOT ask the user for assets before inventorying their workspace.
DO NOT skip the
tl.to({}, { duration: SLOT_DURATION }, 0)
anchor tween at the end of every sub-composition timeline. MOTION_PHILOSOPHY Law 11.
DO NOT use
Math.random()
/
Date.now()
inside render logic. Seeded hashes only.
DO NOT add
class="clip"
to
<video>
tags. It breaks them.
DO NOT impose a brand on the user. Ask first; fall back to MOTION_PHILOSOPHY defaults only when they explicitly decline.

请勿跳过预览环节1（Studio）或预览环节2（渲染后的MP4）。每次构建必须经过这两个环节。
除非提取帧并通过Read工具查看，否则请勿宣称渲染完成。
请勿在专用项目文件夹外构建。切勿将
```
index.html
```
放在工作区根目录。
在盘点用户工作区素材前，请勿向用户索要素材。
请勿省略每个子合成时间轴末尾的
tl.to({}, { duration: SLOT_DURATION }, 0)
锚点补间。这是MOTION_PHILOSOPHY第11条规则。
请勿在渲染逻辑中使用
Math.random()
/
Date.now()
。仅使用种子化哈希。
请勿给
<video>
标签添加
class="clip"
。这会导致视频失效。
请勿向用户强加品牌风格。先询问；仅当用户明确拒绝提供时，才使用MOTION_PHILOSOPHY默认设置。

References

参考资料

```
references/interview-questions.md
```
— full question bank by Gate
```
references/style-intake.md
```
— style interview + MOTION_PHILOSOPHY defaults
```
references/catalog-intent-map.md
```
— "user says X → install Y"
```
references/storyboard-template.md
```
— beat-by-beat template + worked example
```
references/composition-scaffold.md
```
— scoped-styles + IIFE GSAP boilerplate
```
references/build-checklist.md
```
— preflight + pre-delivery gates

External (workspace-level):

```
MOTION_PHILOSOPHY.md
```
— the one external reference this skill assumes exists. Aesthetic baseline. Fallback lives in
```
references/style-intake.md
```
if the file is missing.

```
references/interview-questions.md
```
— 各环节的完整问题库
```
references/style-intake.md
```
— 风格访谈+MOTION_PHILOSOPHY默认设置
```
references/catalog-intent-map.md
```
— “用户需求X→安装组件Y”映射
```
references/storyboard-template.md
```
— 逐节拍模板+示例
```
references/composition-scaffold.md
```
— 作用域样式+IIFE GSAP模板
```
references/build-checklist.md
```
— 预检+交付前环节

外部（工作区级别）：

```
MOTION_PHILOSOPHY.md
```
— 本技能假设存在的唯一外部参考资料，作为美学基准。若文件缺失，使用
```
references/style-intake.md
```
中的 fallback 设置。

make-a-video

Original

Translation

Make a Video — The Beginner-to-Finished-MP4 Skill

制作视频——从新手到成品MP4的技能指南

When to use this skill — and when to hand off

何时使用本技能——以及何时转交其他工具

The two phases

两个阶段

Gate 1 · Intent & format

第1环节 · 目标意图与格式

Gate 2 · Script & voice

第2环节 · 脚本与语音

Gate 3 · Style intake

第3环节 · 风格采集

Gate 4 · Brief synthesis (HARD-GATE before building)

第4环节 · 需求简报整理（构建前的强制环节）

Gate 5 · Scaffold & storyboard

第5环节 · 搭建项目框架与制作分镜脚本

Handoff check first

先检查是否需要转交

Scaffold

搭建项目框架

Storyboard

制作分镜脚本

Gate 6 · Build compositions

第6环节 · 合成视频

Scaffold every sub-composition

搭建每个子合成模块

Build rules

构建规则

Determinism

确定性要求

Gate 7 · Lint → Studio preview (PREVIEW GATE 1 — MANDATORY)

第7环节 · 代码检查→Studio预览（强制预览环节1）

Gate 8 · Draft render → visual verification → MP4 preview → final

第8环节 · 草稿渲染→视觉验证→MP4预览→最终渲染

Draft render

草稿渲染

Visual verification (MANDATORY before delivery)

视觉验证（交付前强制环节）

MP4 preview (PREVIEW GATE 2 — MANDATORY)

MP4预览（强制预览环节2）

Final render

最终渲染

Non-negotiables (load-bearing — do not soften)

不可协商规则（核心要求——请勿放宽）

References

参考资料

Related skills

相关技能