layer-store-assets

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Layer Store Assets

Layer 商店素材

Overview

概览

Store art is seen small, beside competitors, and briefly. Each asset has one job at its smallest display size: the icon is recognisable, the capsule shows the logo, the screenshots say what the player does. An asset judged at full resolution on a large monitor has not been judged.

The second rule is consistency. A listing is a set: icon, capsules, and screenshots must read as the same game. Derive every size from one approved master instead of generating each one, because each fresh generation moves the character and shifts the palette.

Store sizes and rules change and differ by store. Take every exact pixel size, and every content rule, from the user or from the store's current published spec. Do not supply them from memory.

Mechanics and the spend gate are in the

layer

skill, prompt craft in

layer-image

, reframing and upscaling in

layer-image-editing

, exact type in

layer-typography

, and video assembly in

layer-video-timeline

If a sibling skill named here is missing from your available skills, ask the user to install it (

npx skills add layerai/skills --skill <name>

); unattended, proceed from tool schemas and flag the gap.

商店素材通常以很小的尺寸展示，与竞品并排出现，而且只会吸引用户片刻注意。每项素材在最小展示尺寸下都只有一个核心任务：图标应易于识别，胶囊图应展示 Logo，截图应说明玩家会做什么。如果只在大显示器上按素材的完整分辨率进行评判，就等于还没有完成评判。

第二条规则是一致性。一个商店页面是一组素材：图标、胶囊图和截图必须让人看出属于同一款游戏。应从一张获批的主视觉源图派生所有尺寸，而不是分别生成每一种尺寸，因为每次重新生成都会改变角色位置并偏移配色。

商店尺寸和规则会变化，而且不同商店之间也有所差异。每个精确的像素尺寸和每项内容规则，都应从用户或商店当前发布的规范中获取。不要凭记忆提供这些信息。

layer

skill 包含相关机制和 Creative Units 消耗门槛，

layer-image

包含提示词设计，

layer-image-editing

包含重构图和放大，

layer-typography

包含精确排版，

layer-video-timeline

包含视频组装。

如果这里提到的某个同级 skill 不在可用 skills 中，请让用户安装它（

npx skills add layerai/skills --skill <name>

）；在无人值守的情况下，则依据工具 schema 继续执行，并标记这一缺失。

Quick reference

快速参考

Asset	Start from	Tools
Icon	One subject, square, no text	`text_to_image` with `square` , then `image_editing`
Icon variants	The approved icon as `init_image`	`image_editing` , one change per variant
Capsule or feature	One wide key art master	`reframing` to each size, `compose_image` for the logo
Screenshot set	The user's real gameplay captures	`render_text` and `compose_image` , one shared layout
Preview video	Captured gameplay clips	`render_video_timeline`
Size check	Any finished asset	`compose_image` downscaled to its display size

素材	起点	工具
图标	单一主体，方形，无文字	带 `square` 的 `text_to_image` ，然后使用 `image_editing`
图标变体	将获批图标作为 `init_image`	`image_editing` ，每个变体只改一项
胶囊图或 Feature Graphic	一张宽幅主视觉源图	对每个尺寸使用 `reframing` ，用 `compose_image` 合成 Logo
截图集	用户的真实游戏画面捕获	`render_text` 和 `compose_image` ，统一布局
预览视频	捕获的游戏画面片段	`render_video_timeline`
尺寸检查	任意完成的素材	用 `compose_image` 缩小到展示尺寸

Icons

图标

One subject, centred, filling most of the square, against a simple background with strong contrast to it. The usual subject is the game's hero or its signature object, cropped close. Leave out text, small props, and fine detail: none of it survives the smallest size the store displays, and type on an icon reads as noise.

Filter

list_base_models

with

use_case: "text_to_image"

and

capabilities: {square: true}

, adding

image_editing: true

when the hero must match approved art attached as

reference_image

Variants for an icon test start from the approved icon as

init_image

use_case: "image_editing"

, and change one thing each: background colour, expression, or a seasonal prop. State what stays fixed ("keep the character, pose, framing and outline exactly as they are"). Generate every variant from the approved icon, never from the previous variant, or drift compounds.

主体应只有一个，位于中心，占据方形画布的大部分区域，并置于与主体形成强烈对比的简单背景上。常见主体是游戏主角或标志性物体，且应紧密裁切。不要加入文字、小型道具和精细细节：这些内容都无法在商店采用的最小尺寸下保留下来，而图标上的文字只会呈现为噪点。

筛选

list_base_models

，设置

use_case: "text_to_image"

和

capabilities: {square: true}

；当主角必须与作为

reference_image

附加的获批美术图保持一致时，再添加

image_editing: true

。

图标测试的变体应以获批图标作为

init_image

，并使用

use_case: "image_editing"

；每次只更改一项：背景颜色、表情或季节性道具。应明确说明哪些内容保持不变（“保持角色、姿势、取景和轮廓完全不变”）。每个变体都应从获批图标生成，绝不能从上一个变体生成，否则偏差会不断累积。

Judge at display size

按展示尺寸评判

compose_image

spends no Creative Units and can shrink anything: a canvas of the display size, one layer with the asset, both edges anchored at 0, and

resize_strategy: "fit_and_pad"

. Look at that output. If the hero's silhouette or the logo is unreadable there, the fix is fewer elements and heavier shapes in the master, not a sharper upscale.

compose_image

不消耗 Creative Units，并且可以缩小任何内容：创建一张展示尺寸的画布，只放置一层素材，将两条边都锚定在 0，并设置

resize_strategy: "fit_and_pad"

。查看该输出。如果主角的剪影或 Logo 在该尺寸下无法辨认，应在主视觉源图中减少元素并采用更粗壮的形状，而不是进行更锐利的放大。

Capsules, headers, and feature graphics

胶囊图、头图和 Feature Graphic

Approve one master key art wider and larger than the largest target, with the subject composed away from the area the logo will occupy. Derive each size from it with

use_case: "reframing"

, the master as

init_image

, and both

width

and

height

set; with either missing and an init image attached, the output takes the master's shape. If the master is too small for the largest size, upscale it (

use_case: "upscaling"

) rather than regenerating.

The logo is the user's file, uploaded once with

request_file_upload_url

, never generated: models degrade lettering. Place it with

compose_image

in a box sized for that capsule using

fit_and_pad

, key art underneath with

fit_and_crop

. On the smallest capsule the logo is the asset, so give it most of the frame and check it at display size.

先批准一张比最大目标尺寸更宽、更大的主视觉源图，并使主体的构图避开 Logo 将要占据的区域。使用

use_case: "reframing"

派生每个尺寸，将主视觉源图作为

init_image

，并同时设置

width

和

height

；如果缺少其中任一项且附加了 init image，输出会采用主视觉源图的形状。如果主视觉源图对于最大目标尺寸而言太小，应使用

use_case: "upscaling"

放大，而不是重新生成。

Logo 应使用用户的文件，通过

request_file_upload_url

只上传一次，绝不能生成，因为模型会让字形质量退化。使用

compose_image

将其放入按该胶囊图尺寸设定的框中，采用

fit_and_pad

；主视觉图置于底层，采用

fit_and_crop

。在最小的胶囊图中，Logo 本身就是核心内容，因此应让其占据画面的大部分，并在展示尺寸下检查。

Screenshot sets

截图集

Screenshots show the real game. Use the user's captures, uploaded once, and put generated or designed art in the frame around them, not in place of them. Check the store's current policy on what a screenshot may show.

A set reads as a set when every frame shares one layout: the same caption band position and height, the same font, colour and size, the same background treatment. Fix that layout once and reuse the same

compose_image

geometry for every frame:

A background plate (generated from the key art, or a flat colour) with
```
fit_and_crop
```
.
The capture in a fixed box with
```
fit_and_pad
```
.
The caption from
```
render_text
```
with the brand font as
```
font_file_id
```
, on a canvas the size of the caption band, so it is barely scaled when placed.

One caption per frame, a few words, each naming what the player does. Order the set so the first frames carry the pitch, since they are the ones every visitor sees.

截图应展示真实游戏。使用用户的捕获画面，只上传一次，并将生成或设计的美术素材放在画面周围，而不是用它们替代真实捕获画面。还要查看商店当前关于截图可展示内容的政策。

当每帧采用同一布局时，整组截图才会呈现为一套：说明文案栏的位置和高度相同，字体、颜色和字号相同，背景处理方式也相同。先确定该布局，然后对每一帧复用相同的

compose_image

几何参数：

背景板（由主视觉图生成，或使用纯色），采用
```
fit_and_crop
```
。
将捕获画面放入固定框中，采用
```
fit_and_pad
```
。
使用
```
render_text
```
生成说明文案，将品牌字体指定为
```
font_file_id
```
，并在与文案栏相同大小的画布上生成，使其放置时几乎不需要缩放。

每帧只放一条说明文案，文字应简短，并分别说明玩家会做什么。安排整组截图时，让前几帧传达核心卖点，因为每位访客都会先看到这些画面。

Preview video

预览视频

Build it from captured gameplay with

render_video_timeline

: short shots, the core loop in the opening seconds, captions inside the safe area, and the logo at the end. Whether generated footage may appear in a preview is store policy; ask before adding any.

使用捕获的游戏画面和

render_video_timeline

制作：镜头要短，核心循环应在开头数秒内出现，字幕位于安全区内，Logo 放在结尾。商店是否允许在预览视频中使用生成的片段，取决于商店政策；加入任何此类内容前应先询问。

Worked example

实例

"We have key art and a logo. Make our Steam capsules and a small set of icon variants."

The key art carries a
```
file_id
```
; upload the logo with
```
request_file_upload_url
```
.
Ask for the exact capsule sizes from the store's current spec, or take them from the user.

list_base_models

with

use_case: "reframing"

; one run per capsule size, key art as

init_image

, explicit

width

and

height

```
compose_image
```
per capsule: reframed art with
```
fit_and_crop
```
, logo in its box with
```
fit_and_pad
```
. Then shrink the smallest capsule to its display size and check the logo reads.
Icon variants:
```
use_case: "image_editing"
```
, approved icon as
```
init_image
```
, three variants that change only the background colour.
Before step 3, estimate one reframe per distinct size and one icon edit times three, present the total, and wait for an explicit yes above 20 CUs. Poll every run at
```
poll_interval_seconds
```
.

“我们已有主视觉图和 Logo。请为我们的 Steam 制作 Capsule 和一小套图标变体。”

主视觉图带有一个
```
file_id
```
；使用
```
request_file_upload_url
```
上传 Logo。
向用户索取商店当前规范中的精确 Capsule 尺寸，或从用户处获取。
调用
```
list_base_models
```
，设置
```
use_case: "reframing"
```
；每个 Capsule 尺寸运行一次，以主视觉图为
```
init_image
```
，并显式设置
```
width
```
和
```
height
```
。
为每个 Capsule 调用
```
compose_image
```
：重构后的主视觉图采用
```
fit_and_crop
```
，Logo 在其框内采用
```
fit_and_pad
```
。然后将最小的 Capsule 缩小到展示尺寸，并检查 Logo 是否清晰可辨。
图标变体：使用
```
use_case: "image_editing"
```
，以获批图标为
```
init_image
```
，创建三个仅改变背景颜色的变体。
在第 3 步之前估算消耗：每种不同尺寸需要一次重构图，三种图标变体需要三次图标编辑；给出总消耗，并在总额超过 20 CUs 时等待明确的同意。以
```
poll_interval_seconds
```
轮询每次运行。

Common mistakes

常见错误

Judging an icon or a capsule at its generated size instead of its display size.
Text or fine detail on an icon.
Generating each capsule size separately instead of reframing one master.
Passing only
```
width
```
or
```
height
```
when reframing.
Generating the logo instead of compositing the user's file.
Screenshot captions that change position, font, or size from frame to frame.
Generated scenes presented as gameplay screenshots.
Pixel sizes or store rules stated from memory.
Building icon variants from the last variant instead of the approved icon.

在生成尺寸而不是展示尺寸上评判图标或 Capsule。
在图标中加入文字或精细细节。
分别生成每个 Capsule 尺寸，而不是从一张主视觉图重构。
重构图时只传入
```
width
```
或
```
height
```
。
生成 Logo，而不是合成用户的文件。
各帧的截图说明文案在位置、字体或字号上不一致。
把生成的场景当作游戏截图展示。
凭记忆给出像素尺寸或商店规则。
从上一个变体而不是获批图标制作图标变体。