extract-design-system

extract-design-system Visual Quality Diagnostic Assistant

Quick Start

More Skills

Overview

The Visual Quality Diagnostic Assistant is used to answer "Is this image good enough to publish?", UI design, UX review, and design system questions. It is suitable for product, operations, technical, and software teams to call after clarifying business goals, content materials, or analysis targets. It combines inputs such as interface and component descriptions, pasted page descriptions, component lists, brand guidelines, design notes, existing style rules, or page copy, organizes key context, and outputs summaries, diagnostic conclusions, action recommendations, and reusable deliverables for further execution, review, or delivery.

When to Use

Applicable Scenarios

• Users ask questions like "Is this image good enough to publish?" and need to quickly break down goals, determine priorities, and form executable results
• Product, operations, technical, and software teams need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the Visual Quality Diagnostic Assistant
• Users have already prepared extraction goals (explaining the hope to unify the interface, consolidate components, support refactoring, improve delivery efficiency, or establish standards.), standard users (explaining the usage scenarios of designers, front-end engineers, content teams, outsourcing teams, or product teams.), product or component library links (filling in publicly accessible product pages, component library documentation, prototypes, brand pages, or competitor reference links.), and hope to organize them into executable analysis or optimization results
• Users need to turn materials related to the Visual Quality Diagnostic Assistant into clear conclusions, priorities, and next steps

How to Invoke

Call the AI Skills API directly through the exported Python runner:

Command Example

Basic Call

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

Call with Common Parameters

python3 scripts/run.py --params '{"goal":"提取目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
goal	string	No	-	Explain the hope to unify the interface, consolidate components, support refactoring, improve delivery efficiency, or establish standards
audience	string	No	-	Explain the usage scenarios of designers, front-end engineers, content teams, outsourcing teams, or product teams
materialUrl	string	No	-	Fill in publicly accessible product pages, component library documentation, prototypes, brand pages, or competitor reference links; a complete accessible URL must be provided
reviewDepth	string	No	标准诊断	Choose quick extraction, standard design system draft, or deep component inventory; optional values:快速体检、标准诊断、深度改稿
materialFile	string	No	-	Supports multi-page screenshots, component screenshots, design specification documents, brand manuals, PDFs, or annotated images
materialText	string	No	-	Paste page descriptions, component lists, brand guidelines, design notes, existing style rules, or page copy
targetPlatform	string	No	-	Choose Web, mobile, backend system, multi-platform product, marketing site, or other design system scope
brandRequirements	string	No	-	Supplement brand assets, color/font restrictions, component library constraints, accessibility requirements, and information that must be retained

For the complete machine-readable parameter structure, see references/form-schema.json。

Parameter Value Reference

The current skill has no classification parameters that require additional lookup.

Supported Input Formats

The current skill directly accepts JSON parameters; if the parameters contain a link field, please pass a complete, accessible URL.

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 '{"goal":"提取目标"}'

Equivalent --params JSON：

{
  "goal": "提取目标"
}

Example Return Result

{
  "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: organize the core results around the user's goals that can be directly read, reviewed, or delivered.
• Interpretation of input materials: combine the extraction goals (explain the desire to unify the interface, consolidate components, support refactoring, improve delivery efficiency, or establish standards.), standard users (explain the usage scenarios of designers, front-end engineers, content teams, outsourcing teams, or product teams.), and product or component library links (fill in publicly accessible product pages, component library documentation, prototypes, brand pages, or competitor reference links.) to distill key context and the basis for judgment.
• Next steps: provide priorities, execution recommendations, or a content framework that can be further processed.

Suggestions for Using the Results

• First determine whether the output answers the user's core question about the "Visual Quality Diagnostic 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 original 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