image-to-video

image-to-video Video Quality Diagnostic Assistant

Overview

The Video Quality Diagnostic Assistant is used to answer "Is this video 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 the first-frame motion description, description of the reference image content, desired action, camera movement, video duration, style, and usage scenario. It organizes key context from inputs and outputs a summary, diagnostic conclusions, action recommendations, and reusable deliverables for continued execution, review, or delivery.

When to Use

Applicable Scenarios

When users ask questions such as "Is this video good enough to publish" and need to quickly break down goals, judge priorities, and form executable results
When marketing, operations, content media, and e-commerce need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the Video Quality Diagnostic Assistant
When users have already prepared dynamic goals (for example, making the product feel more premium, creating atmosphere, increasing retention, demonstrating action, reinforcing selling points, or making advertising materials), target audience (describing the viewers the video is aimed at, such as consumers, fans, ad delivery audiences, course students, or internal reviewers), and first-frame reference link (providing a reference image, sample video, product page, or visual description link accessible without login), and want to organize them into executable analysis or optimization results
When users need to turn materials related to the Video Quality Diagnostic Assistant into clear conclusions, priorities, and next steps

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":"动态化目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
`goal`	string	No	-	For example, making the product feel more premium, creating atmosphere, increasing retention, demonstrating action, reinforcing selling points, or making advertising materials
`audience`	string	No	-	Describes the viewers the video is aimed at, such as consumers, fans, ad delivery audiences, course students, or internal reviewers
`materialUrl`	string	No	-	Provide a reference image, sample video, product page, or visual description link accessible without login; a complete accessible URL must be passed
`materialFile`	string	No	-	Upload a first-frame image, last-frame image, product image, character image, style image, or short video reference for planning image-to-video motion
`materialText`	string	No	-	Describe the reference image content, desired action, camera movement, video duration, style, and usage scenario
`brandRequirements`	string	No	-	Supplement with immutable subject requirements, brand colors, character/voice authorization, prohibited actions, copyright restrictions, 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 additional lookup tables.

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":"动态化目标"}'

Equivalent --params JSON：

{
  "goal": "动态化目标"
}

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 centered on the user's goals that can be directly read, reviewed, or delivered.
Interpretation of input materials: refine key context and basis for judgment by combining dynamic goals (for example, making the product more textured, creating atmosphere, increasing dwell time, showcasing actions, strengthening selling points, or creating advertising materials.), viewing audience (explain the audience the video is aimed at, for example consumers, fans, ad delivery audiences, course students, or internal reviewers.), and first-frame reference link (fill in a reference image, sample clip, product page, or visual description link that can be accessed without logging in.).
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 question about the "Video Quality Diagnosis Assistant".
Then check whether the results cover the summary, diagnostic conclusions, action recommendations, and reusable deliverables, and whether clear next steps are given.
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