frontend-design

frontend-design Visual Quality Diagnosis Assistant

Overview

The visual quality diagnosis assistant is used to answer "Is this image good enough to publish?", UI design, UX review, and design systems. It is suitable for product, operations, technical, and software teams to invoke after clarifying business goals, content materials, or analysis targets. It combines inputs such as interface descriptions and page copy, pasted page structures, component descriptions, design draft annotations, product requirements, frontend UI copy, or current... to organize key context, and outputs a summary, diagnostic conclusions, action recommendations, and reusable deliverables for continued execution, retrospective review, or delivery.

When to Use

Applicable Scenarios

When users ask questions such as "Is this image good enough to publish?" and need to quickly break down the goal, determine priorities, and form actionable results.
When product, operations, technical, and software need to generate a summary, diagnostic conclusions, action recommendations, and reusable deliverables around the visual quality diagnosis assistant.
When users have already prepared interface goals (explaining the desired task completion rate, conversion, information comprehension, retention, or operational efficiency), target users (explaining user roles, device environment, proficiency, access scenarios, and key concerns), and page or prototype links (providing publicly accessible web pages, prototype previews, design notes, or competitor reference links), and want to organize them into actionable analysis or optimization results.
When users need to turn materials related to the visual quality diagnosis assistant into clear conclusions, priorities, and next-step actions.

How to Invoke

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

Command Examples

Basic Invocation

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

Invocation with Common Parameters

python3 scripts/run.py --params '{"goal":"界面目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
`goal`	string	No	-	Explain the desired task completion rate, conversion, information comprehension, retention, or operational efficiency.
`audience`	string	No	-	Explain user roles, device environment, proficiency, access scenarios, and key concerns.
`materialUrl`	string	No	-	Provide publicly accessible web pages, prototype previews, design notes, or competitor reference links; an accessible full URL must be provided.
`reviewDepth`	string	No	`标准诊断`	Choose quick checkup, standard review, or deep design brief; optional values:`快速体检`、`标准诊断`、`深度改稿`
`materialFile`	string	No	-	Supports web page screenshots, mobile screenshots, Figma exports, PRDs, PDFs, or design description documents.
`materialText`	string	No	-	Paste page structure, component descriptions, design draft annotations, product requirements, frontend UI copy, or current experience issues.
`targetPlatform`	string	No	-	Choose Web, mobile Web, backend system, responsive site, or other interface carrier.
`brandRequirements`	string	No	-	Supplement brand guidelines, component library constraints, styles that must be retained, prohibited expressions, and compliance requirements.

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

Parameter Value Reference

This skill currently has no categorical parameters that require an additional lookup table.

Supported input formats

This skill currently accepts JSON parameters directly; if the parameters include a link field, 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":"界面目标"}'

Equivalent --params JSON：

{
  "goal": "界面目标"
}

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 read, reviewed, or delivered directly.
Interpretation of input materials: refine key context and the basis for judgment based on the interface goals (explain the desired improvement in task completion rate, conversion, information comprehension, retention, or operational efficiency.), target users (explain the user role, device environment, proficiency, access scenarios, and key concerns.), and page or prototype links (provide publicly accessible web pages, prototype previews, design specifications, or competitor reference links.).
Next steps: provide priorities, execution recommendations, or a content framework that can be further developed.

Suggestions for using the results

First determine whether the output answers the user's core questions 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 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