ai-product-photo-scene-planner

ai-product-photo-scene-planner Visual Quality Diagnosis Assistant

Quick Start

More Skills

Overview

The visual quality diagnosis assistant is used to answer "is this image good enough to publish", AI generation, prompts, and visual creativity. It is suitable for marketing, operations, content media, and e-commerce to invoke after clarifying business goals, content materials, or analysis objects. It combines inputs such as product information, category, appearance, material, specifications, price range, core selling points, packaging, and details that must be truthfully presented... to organize key context and output a summary, diagnostic conclusions, action recommendations, and reusable deliverables, making it easy to continue execution, review, or delivery.

When to Use

Applicable Scenarios

• The user asks questions such as "is this image good enough to publish" and needs to quickly break down goals, determine priorities, and form executable results
• Marketing, operations, content media, and e-commerce need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the visual quality diagnosis assistant
• The user has already prepared image goals (for example, increasing clicks, explaining features, building a premium feel, highlighting gift-giving, supporting promotions, or reducing returns.), brand visual requirements (supplementing brand tone, primary colors, prohibited styles, competitor differences, fonts, or image restrictions.), and number of scenes (number of scenes), and hopes to organize them into executable analysis or optimization results
• The user needs to turn materials related to the visual quality diagnosis assistant into clear conclusions, priorities, and next actions

How to Invoke

Directly call the AI Skills API through the exported Python runner:

Command Example

Basic Call

python3 scripts/run.py --params '{}'

Call with Common Parameters

python3 scripts/run.py --params '{"usageGoal":"图片目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
usageGoal	string	No	-	For example, increasing clicks, explaining features, building a premium feel, highlighting gift-giving, supporting promotions, or reducing returns
brandStyle	string	No	-	Supplement brand tone, primary colors, prohibited styles, competitor differences, fonts, or image restrictions
sceneCount	number	No	6	Number of scenes
productInfo	string	No	-	Fill in category, appearance, material, specifications, price range, core selling points, packaging, and details that must be truthfully presented
marketRegion	string	No	中国大陆	Market region; optional values:中国大陆、北美、欧洲、日本、韩国、东南亚、中东、拉美、全球通用
targetChannel	string	No	电商详情页	Usage channel; optional values:电商详情页、商品主图、广告投放、小红书/社媒、直播间贴片、独立站、亚马逊
targetAudience	string	No	-	Describe the buyer, user, age group, lifestyle, and usage scenarios
imageReferenceFile	string	No	-	Upload product images, packaging images, reference images, or visual asset packs to supplement scene planning
productImagesBrief	string	No	-	Describe product features in white-background images, packaging images, model images, reference images, or uploaded images

See the complete machine-readable parameter structure at references/form-schema.json。

Parameter Value Reference

The current skill has no categorical parameters that require additional lookup tables.

Supported Input Formats

The current skill directly accepts JSON parameters and does not involve share link parsing.

Example request

The example parameters below can be passed directly to scripts/run.py, and the runner will send them to the AI Skills API.

python3 scripts/run.py --params '{"usageGoal":"图片目标"}'

Equivalent --params JSON：

{
  "usageGoal": "图片目标"
}

Example response

{
  "success": true,
  "data": {
    "message": "示例结果请以技能真实返回结构为准。"
  },
  "meta": {
    "executionTime": 842,
    "cached": false
  }
}

Deliverables

• Summary, diagnostic conclusions, action recommendations, and reusable deliverables: core results organized around the user's goals that can be directly read, reviewed, or delivered.
• Interpretation of input materials: extract key context and basis for judgment by combining the image goals (for example, increasing clicks, explaining features, building a premium feel, highlighting gifting, supporting promotions, or reducing returns.), brand visual requirements (supplement brand tone, primary colors, prohibited styles, competitor differentiation, fonts, or visual constraints.), and number of scenes (number of scenes).
• Next steps: provide priorities, execution suggestions, or a content framework that can be further worked on.

Suggestions for using the results

• First determine whether the output answers the user's core question about the "Visual Quality Diagnosis Assistant".
• Then check whether the results cover the summary, diagnostic conclusions, action recommendations, and reusable deliverables, and whether clear next steps are provided.
• If there is little input material, it is recommended to have the user supplement the goals, audience, constraints, or source materials before running.

Preparation before running

• AISKILLS_BASE_URL: default https://ai-skills.ai
• AISKILLS_API_KEY: required, used for authenticated calls
• AISKILLS_TENANT_ID: default default