image-edit

image-edit 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?", AI generation, prompts, and visual creativity. It is suitable for marketing, operations, content media, and e-commerce to call after clarifying business goals, content materials, or analysis targets. It combines inputs such as image editing requirement descriptions, pasted original image descriptions, elements to keep/delete/replace, local editing goals, prompt drafts, or... to organize key context, and outputs summaries, diagnostic conclusions, action recommendations, and reusable deliverables for continued 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 Diagnostic Assistant
• The user has already prepared the image editing goal (for example, fixing flaws, changing the background, unifying style, improving click-through, highlighting selling points, compliance cleanup, or platform adaptation.), the viewing audience (explaining who the edited image is for, such as consumers, advertising audiences, social media followers, channel partners, or internal review.), and image reference links (providing original images, reference images, material descriptions, product pages, or brand visual links accessible without login.), and wants to organize them into executable analysis or optimization results
• The user needs to turn materials related to the Visual Quality Diagnostic Assistant into clear conclusions, priorities, and next-step actions

How to Call

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":"改图目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
goal	string	No	-	For example, fixing flaws, changing the background, unifying style, improving click-through, highlighting selling points, compliance cleanup, or platform adaptation
audience	string	No	-	Explain who the edited image is for, such as consumers, advertising audiences, social media followers, channel partners, or internal review
materialUrl	string	No	-	Provide original images, reference images, material descriptions, product pages, or brand visual links accessible without login; a complete accessible URL must be provided
materialFile	string	No	-	Upload original images, reference images, brand materials, local annotation images, or visual materials to help organize the editing brief
materialText	string	No	-	Paste original image descriptions, elements to keep/delete/replace, local editing goals, prompt drafts, or publishing requirements
brandRequirements	string	No	-	Supplement required elements to keep, prohibited modification areas, brand colors, copyright authorization, output restrictions, and compliance requirements

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

Parameter Value Reference

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

Supported Input Formats

The current skill directly receives JSON parameters; if the parameters include 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":"改图目标"}'

Equivalent --params JSON：

{
  "goal": "改图目标"
}

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 image editing goals (for example, fixing flaws, changing the background, unifying style, improving click-through rate, highlighting selling points, compliance cleanup, or platform adaptation.), the viewing audience (explain who the edited image is intended for, for example, consumers, advertising audiences, social media followers, channel partners, or internal review.), and image reference links (fill in the original image, reference image, material description, product page, or brand visual link that can be accessed without logging in.) to extract key context and the basis for judgment.
• Next steps: provide priorities, execution suggestions, or a content framework that can be further processed.

Suggestions for using the results

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