ai-stitch-design-taste

ai-stitch-design-taste Visual Quality Diagnosis Assistant

Overview

The Visual Quality Diagnosis Assistant is used to answer "Is this image ready to publish?", performance diagnosis, website quality, and experience metrics. It is suitable for technical, product, marketing, and software use after clarifying business objectives, content materials, or analysis targets. It combines inputs such as visual brief or screenshot descriptions, pasted visual briefs, screenshot descriptions, brand guidelines, page issues, platform specifications, or modifications... to organize key context and output visual/creative diagnoses, prompts or storyboard plans, and publishing specification checks, making it easy to continue execution, review, or delivery. Capability positioning supplement: skills.sh all-time/trending signals show that stitch-design-taste has user demand; the platform displays it as a design_media business assistant directory, outputting reviewable diagnoses, suggestions, or production preparation packages.

When to Use

Applicable Scenarios

Users ask questions like "Is this image ready to publish?" and need to quickly break down objectives, identify priorities, and form executable results
technical, product, marketing, and software need to generate visual/creative diagnoses, prompts or storyboard plans, and publishing specification checks around the Visual Quality Diagnosis Assistant
Users have already prepared the review objective (explain the layout, readability, brand consistency, conversion goal, or delivery standard to be checked.), usage scenario (explain the platform, audience, device, campaign, or review scenario the visual materials are intended for.), page or material link (fill in a publicly accessible page, material, design draft preview, or reference link; for restricted content, please upload instead.), and hope to organize it into executable analysis or optimization results
Users need to turn materials related to the Visual Quality Diagnosis Assistant into clear conclusions, priorities, and next actions

How to Invoke

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

Command Example

Basic Invocation

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

Invocation with Common Parameters

python3 scripts/run.py --params '{"goal":"审查目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
`goal`	string	No	-	Explain the layout, readability, brand consistency, conversion goal, or delivery standard to be checked
`audience`	string	No	-	Explain the platform, audience, device, campaign, or review scenario the visual materials are intended for
`materialUrl`	string	No	-	Fill in a publicly accessible page, material, design draft preview, or reference link; for restricted content, please upload instead; a complete accessible URL is required
`materialFile`	string	No	-	Upload screenshots, images, presentation decks, brand guidelines, product images, or visual reference files
`materialText`	string	No	-	Paste visual briefs, screenshot descriptions, brand guidelines, page issues, platform specifications, or modification goals
`brandRequirements`	string	No	-	Supplement brand guidelines, size ratios, platform restrictions, unchangeable elements, accessibility requirements, or manual review priorities

See the complete machine-readable parameter structure at 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":"审查目标"}'

Equivalent --params JSON：

{
  "goal": "审查目标"
}

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

Visual/creative diagnosis, prompt or storyboard plan, publishing specification check: organize the core results that can be directly read, reviewed, or delivered around the user's goals.
Interpretation of input materials: combine the review objectives (specify the layout, readability, brand consistency, conversion goals, or delivery standards to be checked.), usage scenarios (specify the platform, audience, device, campaign, or review scenario the visual materials are intended for.), page or material links (fill in publicly accessible pages, materials, design draft previews, or reference links; for restricted content, please upload instead.) to extract key context and the basis for judgment.
Next steps: provide priorities, execution suggestions, 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 visual/creative diagnosis, prompt or storyboard plan, and publishing specification check, and whether they provide clear next steps.
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