editorial-collage-motion

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

半色调拼贴动效

Halftone Collage Motion

把创作分成两段：先将视觉解码为可编辑规范，再从获批静帧或透明图层构建动画。默认使用本地兼容工作流，真实记录每个生成器和渲染器。

Divide creation into two stages: first decode the visuals into an editable specification, then build the animation from approved stills or transparent layers. Use the local-compatible workflow by default and accurately record every generator and renderer.

选择交付范围

Choose the Delivery Scope

先判断用户要哪一层：

仅分析：交付拆解、通用提示词和 JSON 视觉规范。
仅静帧：完成分析并生成、筛选静帧。
拼贴动效：完成静帧审批后制作无声动画底片。
完整视频：把本 Skill 作为视觉阶段，继续服从视频生产契约、字幕、配音、数字人和归档规则。

缺参考图但用户明确要求“照这张图分析”时，先索取图片。只有简述时，直接草拟规范，不重复询问已知信息。

First determine which level the user requires:

Analysis only: deliver the breakdown, generic prompt, and JSON visual specification.
Stills only: complete the analysis and generate and curate stills.
Collage motion: complete still approval and then produce a silent animation base.
Full video: use this Skill as the visual stage while continuing to comply with the video production contract, captions, voiceover, digital humans, and archiving rules.

If no reference image is provided but the user explicitly asks to “analyze this image,” request the image first. If only a brief description is provided, draft the specification directly and do not repeatedly ask for information that is already known.

选择执行路径

Choose the Execution Path

默认采用本地路径：

静帧或图层：加载
```
imagegen
```
Skill，使用 Codex 内置
```
image_gen
```
。不得默认切换到 OpenAI API、CLI 或其他生图模型。
简单逐层组装：使用
```
scripts/render_assembly.py
```
。
复杂排版、多个转场或组件级时间轴：加载
```
hyperframes
```
Skill，沿用本规范和来源声明。

只有用户明确要求 Arcads、Nano Banana、Seedance 或 Kling，并且对应工具在当前会话可调用时，才读取

references/provider-boundaries.md

并进入外部路径。上传本地品牌图、产品图或人物图前，必须说明上传位置、费用和用途并取得用户确认。

不得根据提示词、文件名或预期模型推断实际提供方。未实际调用的模型只能写成“目标提示词”或“兼容风格”，不能写成输出来源。

Use the local path by default:

Stills or layers: load the
```
imagegen
```
Skill and use Codex's built-in
```
image_gen
```
. Do not switch by default to the OpenAI API, CLI, or another image-generation model.
Simple layer-by-layer assembly: use
```
scripts/render_assembly.py
```
.
Complex layouts, multiple transitions, or component-level timelines: load the
```
hyperframes
```
Skill and follow this specification and its provenance declarations.

Only when the user explicitly requests Arcads, Nano Banana, Seedance, or Kling, and the corresponding tool is callable in the current session, read

references/provider-boundaries.md

and enter the external path. Before uploading local brand images, product images, or images of people, explain the upload destination, cost, and purpose and obtain the user's confirmation.

Do not infer the actual provider from prompts, filenames, or the expected model. Any model that was not actually invoked may only be described as a “target prompt” or a “compatible style,” never as the output source.

默认生产链路（硬默认）

Default Production Pipeline (Hard Default)

严格按以下顺序执行：

解码参考图或简述，生成拆解、通用提示词和 JSON 视觉规范。
使用 Codex 内置
```
image_gen
```
为每幕单独生成完整静帧。品牌图、产品图或人物参考要在所有相关调用中保持可见。
把生成结果从 Codex 默认生成目录复制到工程
```
assets/stills/
```
，不得让工程长期引用
```
$CODEX_HOME/generated_images/
```
下的文件。
向用户展示完整静帧。用户未明确确认静帧前，禁止生成动画、FFmpeg 组装计划或正式视频。
静帧确认后，使用 Codex 内置
```
image_gen
```
生成各独立剪纸元素。需要透明 PNG 时，先生成纯色 chroma-key 背景，再调用
```
imagegen
```
Skill 指定的
```
remove_chroma_key.py
```
本地抠像，并通过 alpha 预检。
使用获批静帧锁定最终构图，用透明图层建立
```
assembly-plan.json
```
，再用本地 FFmpeg 或 HyperFrames 从空背景逐件组装。

完成媒体探针、关键帧检查和来源 manifest。默认记录

actual_still_provider: codex-image-gen

、

actual_motion_provider: local-ffmpeg

或

hyperframes

、

external_uploads: false

。

如果用户直接提供全部静帧或透明图层，把

actual_still_provider

改为

user-supplied

。只有真实发生外部调用时才能填写 Arcads、Nano Banana、Seedance 或 Kling。

Follow this sequence strictly:

Decode the reference image or brief description and produce a breakdown, generic prompt, and JSON visual specification.
Use Codex's built-in
```
image_gen
```
to generate a complete still for each scene separately. Brand, product, or people references must remain visible in every relevant call.
Copy the generated results from Codex's default generated-images directory to the project's
```
assets/stills/
```
. The project must not continue referencing files under
```
$CODEX_HOME/generated_images/
```
.
Display the complete stills to the user. Do not generate an animation, FFmpeg assembly plan, or final video until the user has explicitly approved the stills.
After the stills are approved, use Codex's built-in
```
image_gen
```
to generate the individual paper-cut elements. When transparent PNGs are required, first generate a solid-color chroma-key background, then perform local key removal with the
```
remove_chroma_key.py
```
script specified by the
```
imagegen
```
Skill, followed by an alpha preflight.
Use the approved still to lock the final composition, build
```
assembly-plan.json
```
from the transparent layers, and then use local FFmpeg or HyperFrames to assemble the elements one by one from an empty background.

Complete the media probe, keyframe inspection, and provenance manifest. By default, record

actual_still_provider: codex-image-gen

actual_motion_provider: local-ffmpeg

hyperframes

, and

external_uploads: false

If the user directly supplies all stills or transparent layers, change

actual_still_provider

user-supplied

. Arcads, Nano Banana, Seedance, or Kling may be listed only when they were genuinely invoked through an external call.

阶段 A：解码参考

Stage A: Decode the Reference

首次解码时完整阅读

references/visual-contract.md

和

references/schemas.md

。按以下顺序输出：

```
### 拆解
```
：媒介与工艺、色场、元素与切边、构图与层级、单幕创意、文字、安全区、情绪。
```
### 通用提示词
```
：写成不依赖“上图”的自包含自然语言提示词。

### JSON 规范

：从

assets/templates/collage-spec.json

复制并填写，保持有效 JSON。

把观察写成可复现参数。例如写“黑白圆点半色调，约 65 lpi，白色细描边，右下 6px 柔和阴影”，不要只写“有纸感”。

多张参考图要分别解码，再补一段共同风格摘要。用户要求“保持外观，只改颜色”时，只改相应字段，但重新输出完整 JSON。

During the initial decoding, read

references/visual-contract.md

and

references/schemas.md

in full. Output the following in order:

```
### Breakdown
```
: medium and craft, color fields, elements and cut edges, composition and hierarchy, single-scene concept, text, safe area, and mood.
```
### Generic Prompt
```
: a self-contained natural-language prompt that does not depend on “the image above.”

### JSON Specification

: copied from

assets/templates/collage-spec.json

and completed while remaining valid JSON.

Express observations as reproducible parameters. For example, write “black-and-white circular halftone dots at approximately 65 lpi, with a thin white outline and a soft 6px shadow at the bottom right,” rather than merely saying “has a paper texture.”

Decode multiple reference images separately, then add a shared style summary. If the user asks to “preserve the appearance and change only the colors,” modify only the relevant fields, but output the complete JSON again.

阶段 B：规划场景

Stage B: Plan the Scenes

每幕只保留一个核心创意。为每幕锁定：

背景色和画幅。
主要元素、辅助元素、层级和最终坐标。
文字内容、排版和可编辑方式。
从空背景到完整构图的进入顺序。
真人、数字人、字幕、Logo 和平台 UI 的避让区。

从

assets/templates/assembly-plan.json

建立组装计划。正式成片优先使用

layered

模式，每个元素提供一张带透明通道的 PNG。

bands

模式只是将整张静帧切成条带滑入，只能用于快速预览或用户明确接受的简化版本。

Keep only one core concept per scene. Lock the following for each scene:

Background color and aspect ratio.
Primary elements, secondary elements, hierarchy, and final coordinates.
Text content, typography, and editable method.
Entry order from an empty background to the completed composition.
Avoidance zones for real people, digital humans, captions, logos, and platform UI.

Build the assembly plan from

assets/templates/assembly-plan.json

. For the final production, prefer

layered

mode, with each element supplied as a PNG with an alpha channel.

bands

mode merely slices a complete still into strips that slide into view and may only be used for a quick preview or a simplified version explicitly accepted by the user.

阶段 C：生成与审批静帧

Stage C: Generate and Approve the Stills

加载

imagegen

Skill，使用 Codex 内置

image_gen

先生成或组合完整静帧，再展示给用户审批。保持品牌或产品参考在所有相关生成调用中可见。

本地正式模式按以下顺序工作：

每幕发起一次独立的内置
```
image_gen
```
调用，生成完整构图静帧；不同场景不要用一次调用拼成大图。
把选中的静帧复制到工程
```
assets/stills/
```
，记录最终提示词和参考图角色。
展示静帧并获得用户明确确认。未确认时只允许调整提示词和重新生成。
确认后再生成独立拼贴元素。按
```
imagegen
```
的 chroma-key 加本地抠像路径取得透明 PNG，保留白色 keyline 和柔和阴影。
用获批静帧校准图层的大小、坐标和层级。文字默认保留为 HyperFrames、HTML 或 Remotion 的可编辑文本层。
导出场景静帧和图层清单，再进入动画阶段。

内置

image_gen

不可用或失败时，不得自动改用 CLI。先告知用户 CLI/API 路径需要

OPENAI_API_KEY

，只在用户明确同意后切换。

如果只拿到一张完整静帧，可以先用

bands

模式做低成本运动预览，但不得把矩形条带滑入描述成真正的“逐元素组装”。

Load the

imagegen

Skill and use Codex's built-in

image_gen

to generate or combine the complete stills first, then present them for user approval. Keep brand or product references visible in every relevant generation call.

The local production mode works in this order:

Make one separate built-in
```
image_gen
```
call per scene to generate a complete compositional still. Do not combine different scenes into a single large image through one call.
Copy the selected stills to the project's
```
assets/stills/
```
and record the final prompts and reference-image roles.
Display the stills and obtain explicit user approval. Before approval, only prompt adjustments and regeneration are allowed.
After approval, generate the individual collage elements. Use the
```
imagegen
```
chroma-key and local key-removal path to obtain transparent PNGs, preserving white keylines and soft shadows.
Calibrate each layer's size, coordinates, and hierarchy against the approved still. By default, retain text as editable text layers in HyperFrames, HTML, or Remotion.
Export the scene stills and layer manifest before proceeding to the animation stage.

If the built-in

image_gen

is unavailable or fails, do not automatically switch to the CLI. Explain that the CLI/API path requires

OPENAI_API_KEY

, and switch only after the user explicitly agrees.

If only one complete still is available, the

bands

mode can provide a low-cost motion preview, but rectangular strip slide-ins must not be described as true element-by-element assembly.

阶段 D：本地逐层组装

Stage D: Assemble Layers Locally

先验证规范和计划：

bash

python3 .claude/skills/editorial-collage-motion/scripts/validate_collage.py \
  --spec /absolute/path/collage-spec.json \
  --plan /absolute/path/assembly-plan.json \
  --project /absolute/path/project

再渲染无声底片：

bash

python3 .claude/skills/editorial-collage-motion/scripts/render_assembly.py \
  --project /absolute/path/project \
  --plan /absolute/path/assembly-plan.json \
  --output /absolute/path/project/renders/collage-assembly.mp4

动画必须从纯色空场开始，元素按计划从画面边缘进入并落位。禁止用镜头晃动、整图漂移或持续缩放冒充组装。落位后留足可读时间。

First validate the specification and plan:

bash

python3 .claude/skills/editorial-collage-motion/scripts/validate_collage.py \
  --spec /absolute/path/collage-spec.json \
  --plan /absolute/path/assembly-plan.json \
  --project /absolute/path/project

Then render the silent base:

bash

python3 .claude/skills/editorial-collage-motion/scripts/render_assembly.py \
  --project /absolute/path/project \
  --plan /absolute/path/assembly-plan.json \
  --output /absolute/path/project/renders/collage-assembly.mp4

The animation must begin with a solid-color empty canvas, with elements entering from the edges of the frame and settling into place according to the plan. Camera shake, whole-image drift, or continuous zooming must not be used to imitate assembly. Leave enough readable time after the elements settle.

阶段 E：质检和来源声明

Stage E: Quality Assurance and Provenance

完整阅读

references/qc-and-provenance.md

，至少完成：

媒体探针：尺寸、比例、帧率、时长、编码和可解码性。
首帧、每幕落位前后、幕中点和末帧抽查。
空场起步、逐件进入、阴影稳定、文字可读、安全区和画面密度检查。
```
render-manifest.json
```
与实际输出、输入计划和生成器一致。

在制作说明中明确写出：

```
actual_still_provider
```
```
actual_motion_provider
```
```
external_uploads
```
是否属于
```
compatible_render
```
，以及兼容的是哪套视觉规范

当前会话没调用 Arcads MCP 时，固定使用“Arcads 风格兼容渲染”或“editorial collage 本地渲染”，不得写成 Nano Banana 或 Seedance 原生输出。

Read

references/qc-and-provenance.md

in full and complete at least the following:

Media probe: dimensions, aspect ratio, frame rate, duration, encoding, and decodability.
Inspect the first frame, the frames immediately before and after each scene settles, each scene's midpoint, and the final frame.
Check the empty-background start, element-by-element entry, shadow stability, text readability, safe areas, and visual density.
Ensure that
```
render-manifest.json
```
agrees with the actual outputs, input plan, and generators.

Explicitly state the following in the production notes:

```
actual_still_provider
```
```
actual_motion_provider
```
```
external_uploads
```
Whether the output is a
```
compatible_render
```
, and which visual specification it is compatible with

When Arcads MCP was not called in the current session, always use “Arcads-style compatible render” or “editorial collage local render.” Never describe the output as native Nano Banana or Seedance output.

资源

Resources

```
references/visual-contract.md
```
：风格词汇、硬性视觉合同和反例。
```
references/schemas.md
```
：视觉规范与组装计划字段说明。
```
references/provider-boundaries.md
```
：本地和外部生成路径的权限与披露边界。
```
references/qc-and-provenance.md
```
：交付质检和来源记录。
```
assets/templates/collage-spec.json
```
：可复制的视觉规范模板。
```
assets/templates/assembly-plan.json
```
：可复制的本地组装计划模板。
```
assets/templates/assembly-plan-bands.json
```
：只有完整静帧时使用的条带预览模板。
```
scripts/validate_collage.py
```
：规范、计划和素材预检。
```
scripts/render_assembly.py
```
：FFmpeg 确定性逐层或条带组装器。

```
references/visual-contract.md
```
: style vocabulary, mandatory visual contract, and counterexamples.
```
references/schemas.md
```
: field descriptions for visual specifications and assembly plans.
```
references/provider-boundaries.md
```
: permission and disclosure boundaries for local and external generation paths.
```
references/qc-and-provenance.md
```
: delivery quality assurance and provenance recording.
```
assets/templates/collage-spec.json
```
: reusable visual specification template.
```
assets/templates/assembly-plan.json
```
: reusable local assembly plan template.
```
assets/templates/assembly-plan-bands.json
```
: strip-preview template used only when a complete still is available.
```
scripts/validate_collage.py
```
: preflight validation for specifications, plans, and assets.
```
scripts/render_assembly.py
```
: deterministic FFmpeg renderer for layer-by-layer or strip-based assembly.