scenario-asset-analysis

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Scenario Asset Analysis

Scenario 资产分析

Overview

概述

Four tools read assets back instead of making new ones: three fixed-purpose, one open-ended. With

search

(default toolset) they answer the questions that come after a batch lands, which is where most of the work actually is: is this on brief, what look is this, what does this show, what can the next model condition on, where did last week's approved version go.

None of them are in the default toolset. Get schemas with

scenario_tools_search

, then run each through the executor matching its

permission

asset_caption

and

asset_describe

are read-class,

asset_analyze

and

asset_detect

are write-class. Or reconnect with

?toolsets=full

. Connection and scope: see the

scenario

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

npx skills add scenario-labs/skills --skill <name>

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

有四款工具用于读取资产信息而非生成新资产：三款为固定用途，一款为开放式。结合

search

（默认工具集），它们可以解答批量生成后出现的问题——这也是实际工作中占比最大的部分：是否符合brief要求、是什么风格、展示了什么内容、下一个模型可以用什么作为条件、上周通过的版本在哪里。

这四款工具都不在默认工具集中。可通过

scenario_tools_search

获取schema，然后根据每个工具的

permission

（权限）使用对应的执行器运行：

asset_caption

和

asset_describe

属于读取类，

asset_analyze

和

asset_detect

属于写入类。也可以通过

?toolsets=full

重新连接。连接方式与适用范围：参见本仓库中的

scenario

Skill。如果你的可用Skill中缺少这里提到的同级Skill，请让用户安装（命令：

npx skills add scenario-labs/skills --skill <name>

）；若处于无人值守模式，则从工具schema继续执行并标记缺失项。

Quick reference

快速参考

Need	Tool	Shape
A caption for one image	`asset_caption` (read)	`details_level` : `action` or `action+style`
A reusable look off one image	`asset_describe` (read)	Returns a full description plus a promptable synthesis
Anything else, in your own words	`asset_analyze` (write)	`instruction` plus up to 10 `images` and 10 `text_inputs`
A conditioning map for another model	`asset_detect` (write)	`modality` , one of ten including canny, depth, pose, segmentation

All four bill credits and all four take

dry_run: true

for an estimate first. Read-class does not mean free.

需求	工具	功能详情
为单张图像生成说明文字	`asset_caption` （读取类）	`details_level` 可选值： `action` 或 `action+style`
从单张图像提取可复用的风格	`asset_describe` （读取类）	返回完整描述以及可用于提示词的合成风格
其他任何自定义需求，用你自己的话描述	`asset_analyze` （写入类）	需传入 `instruction` ，以及最多10张 `images` 和10个 `text_inputs`
为其他模型生成条件控制图	`asset_detect` （写入类）	`modality` 支持10种类型，包括canny、depth、pose、segmentation

这四款工具都会消耗credits，且都支持先传入

dry_run: true

进行预估。读取类不代表免费。

The four facts that change the plan

改变使用方案的四个要点

asset_analyze
batches. One call carries up to 10 images against one
```
instruction
```
, so reviewing 200 assets is 20 calls, not 200.
```
num_outputs
```
(1 to 5) is unrelated: it returns several distinct answers to the same instruction, not one answer per image. Ask for a fixed per-image output shape in the
```
instruction
```
so the answers stay parseable.
asset_detect
strips the background by default.
```
remove_background
```
defaults to true, so a depth or pose map comes back with the frame's context already gone. Set it false whenever the map has to cover the whole image.
It reads a render, not the file. On a vector or layered source it cannot confirm what the file is or report its exact values: one call called a 16-path SVG raster, shifted a
```
#101614
```
fill to
```
#131A18
```
, and missed an off-palette path. Parse the file for exact color and structure; the tool judges what the render shows.
Fixed beats flexible when it fits.
```
asset_caption
```
and
```
asset_describe
```
are purpose-built and faster than instructing an LLM to do the same job. Reach for
```
asset_analyze
```
for classification, extraction, comparison, translation, or a verdict against a brief. One carve-out: for a structured pass/warn/fail verdict against a configured brand brief, teams with the Quality Gate add-on have a dedicated tool that stores its verdict and re-reads it free (see
```
scenario-quality-gate
```
);
```
asset_analyze
```
stays the route when the add-on is missing or the brief exists only as prose.

asset_analyze

and

asset_detect

wait up to 180s and then hand back a

job_id

; carry on with

jobs_wait

as anywhere else.

asset_analyze
支持批量处理。单次调用可针对一条
```
instruction
```
处理最多10张图像，因此审核200个资产只需20次调用，而非200次。
```
num_outputs
```
（1到5）与此无关：它是针对同一条指令返回多个不同的答案，而非每张图像返回一个答案。请在
```
instruction
```
中要求固定的单张图像输出格式，以确保答案可解析。
asset_detect
默认移除背景。
```
remove_background
```
默认值为true，因此返回的深度或姿态图会去掉画面的背景上下文。如果需要控制图覆盖整张图像，请将其设为false。
它读取的是渲染结果，而非源文件。 对于矢量或分层源文件，它无法确认文件本身的信息或返回精确值：有一次调用将16路径的SVG识别为栅格图，将
```
#101614
```
的填充色误判为
```
#131A18
```
，还漏掉了一条调色板外的路径。如需精确的颜色和结构信息，请直接解析源文件；该工具仅判断渲染后呈现的内容。
适用场景下，固定工具优于灵活工具。
```
asset_caption
```
和
```
asset_describe
```
是专用工具，比直接指令LLM完成同类任务速度更快。如需分类、提取、比较、翻译或针对brief的评估结论，请使用
```
asset_analyze
```
。一个例外：如果需要针对已配置的品牌brief生成结构化的通过/警告/不通过结论，拥有Quality Gate附加组件的团队可以使用专用工具，该工具会存储评估结论且可免费重新读取（参见
```
scenario-quality-gate
```
）；如果没有该附加组件，或brief仅为文字描述，则仍需使用
```
asset_analyze
```
。

asset_analyze

和

asset_detect

的最长等待时间为180秒，之后会返回

job_id

；后续可像其他场景一样使用

jobs_wait

继续处理。

Finding an asset again

重新检索资产

Retrieval is

search

with

target="assets"

, and at least one of

query

filters

filter

image

, or

images

must be set: an empty call is a 400, not an everything-list.

By text.
```
query
```
is keyword matching by default;
```
query_semantic_ratio
```
moves it toward meaning (0.5 to 0.8 suits mood queries like "dark medieval atmosphere", 1 is pure semantic).
```
sort_by
```
(say
```
["createdAt:desc"]
```
) is ignored while that ratio is above 0, so a newest-first list needs keyword mode.
By similarity.
```
image
```
takes one asset id or image URL and returns lookalikes;
```
images
```
takes
```
{"like": [...], "unlike": [...]}
```
to steer with positive and negative examples (the two fields are mutually exclusive).
```
image_semantic_ratio
```
decides what similar means: 1, the default, matches subject and mood; 0 matches image features, the setting for hunting near-duplicates and crops. Add a
```
query
```
beside it for "like these, but more stylized".

By structure.

filters

narrows on

kind

tags

model_id

collection_ids

, and

created_after

created_before

, ANDed with everything above.

资产检索使用

search

工具并设置

target="assets"

，且必须至少设置

query

、

filters

、

filter

、

image

、

images

中的一个参数：空调用会返回400错误，而不是返回所有资产列表。

按文本检索。
```
query
```
默认是关键词匹配；
```
query_semantic_ratio
```
可调整为语义匹配模式（0.5到0.8适合情绪类查询，比如“黑暗中世纪氛围”，1为纯语义匹配）。当该比值大于0时，
```
sort_by
```
（例如
```
["createdAt:desc"]
```
）会被忽略，因此需要按最新排序的列表请使用关键词模式。
按相似性检索。
```
image
```
参数传入单个资产ID或图像URL，返回相似图像；
```
images
```
参数传入
```
{"like": [...], "unlike": [...]}
```
格式，通过正例和负例引导检索（两个字段互斥）。
```
image_semantic_ratio
```
决定相似性的判定标准：默认值为1，匹配主题和氛围；0匹配图像特征，用于查找近似重复图和裁剪图。可同时添加
```
query
```
参数实现“类似这些，但风格更突出”的检索效果。
按结构检索。
```
filters
```
可通过
```
kind
```
、
```
tags
```
、
```
model_id
```
、
```
collection_ids
```
以及
```
created_after
```
/
```
created_before
```
进行筛选，且与上述所有条件为逻辑与关系。

Worked example: reviewing a batch against a brief

示例：针对brief审核批量资产

Collect the asset ids from the run (
```
jobs_wait
```
returns them).
```
asset_analyze
```
with
```
dry_run: true
```
on the first chunk to price the pass.
```
asset_analyze
```
with
```
images
```
set to 10 ids and an
```
instruction
```
that states the brief and fixes the output: "For each image in order, reply
```
<index>: pass|fail, <reason in under 12 words>
```
, a reason on every line, passes included. Fail anything not centered, not on a plain field, or carrying text." Repeat per chunk. Answers land as text assets (one, or one per image):
```
asset_download
```
them to read the verdicts.
```
asset_describe
```
on the strongest pass. Its promptable synthesis goes straight into the next batch's prompt, which holds the look without a training run (see
```
scenario-consistency
```
); when the synthesis is only a short title, prompt with the description instead.
File the result:
```
collection_create
```
, then
```
collection_add_assets
```
in chunks of at most 49 ids.
```
asset_add_tags
```
is additive, so tag the failures rather than rebuilding a tag set. The set comes back later with
```
search
```
```
filters={"collection_ids": [...]}
```
, and its lookalikes with
```
images={"like": [...]}
```
.

从运行任务中收集资产ID（
```
jobs_wait
```
会返回这些ID）。
对第一批资产调用
```
asset_analyze
```
并设置
```
dry_run: true
```
，预估本次审核的成本。
调用
```
asset_analyze
```
，将
```
images
```
设为10个ID，并在
```
instruction
```
中说明brief要求和固定输出格式：“按顺序处理每张图像，回复
```
<index>: pass|fail, <12字以内的原因>
```
，每行一个结果，通过的也要写原因。任何未居中、背景不简洁或带有文字的图像都判定为不通过。” 每批重复此操作。结果会以文本资产的形式返回（要么是一个文本文件，要么每张图像对应一个）：使用
```
asset_download
```
下载后即可查看评审结论。
对最优的通过资产调用
```
asset_describe
```
。它返回的可用于提示词的合成风格可以直接用于下一批次的提示词中，无需训练即可保持风格一致（参见
```
scenario-consistency
```
）；如果合成结果只是短标题，则用完整描述作为提示词。
归档结果：先调用
```
collection_create
```
创建集合，然后以最多49个ID为一批调用
```
collection_add_assets
```
添加资产。
```
asset_add_tags
```
是追加式的，因此只需给不通过的资产打标签即可，无需重建标签集。后续可以通过
```
search
```
的
```
filters={"collection_ids": [...]}
```
检索该集合，通过
```
images={"like": [...]}
```
检索相似资产。

Common mistakes

常见错误

One
```
asset_analyze
```
call per asset when 10 fit in a call.
Treating
```
num_outputs
```
as a batch size over
```
images
```
.
Leaving
```
remove_background
```
at its default on an
```
asset_detect
```
map that must match the source frame.
Running
```
asset_analyze
```
or
```
asset_detect
```
through
```
scenario_tool_execute_read
```
: both are write-class and the call is rejected by lane, not by argument.
Sending more than 49 ids to
```
collection_add_assets
```
, or re-adding an asset already in the collection: both are hard errors, not no-ops.
Asking
```
asset_analyze
```
to produce an image. It returns text; control maps come from
```
asset_detect
```
and final renders from
```
model_run
```
.

每个资产调用一次
```
asset_analyze
```
，但实际上单次调用可处理10个资产。
将
```
num_outputs
```
当成
```
images
```
的批量大小。
在需要与源画面匹配的
```
asset_detect
```
控制图中，仍保持
```
remove_background
```
的默认值。
通过
```
scenario_tool_execute_read
```
运行
```
asset_analyze
```
或
```
asset_detect
```
：这两个都是写入类工具，调用会被通道拒绝，而非参数校验失败。
向
```
collection_add_assets
```
传入超过49个ID，或者重复添加已在集合中的资产：这两种情况都会触发硬错误，而非无操作。
要求
```
asset_analyze
```
生成图像。它只返回文本；控制图由
```
asset_detect
```
生成，最终渲染图由
```
model_run
```
生成。