ai-video-generation

ai-video-generation video quality diagnosis assistant

Quick Start

More Skills

Overview

The video quality diagnosis assistant is used to answer "Is this video ready 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 will combine input such as video creative scripts, pasted video topics, scripts, storyboards, voiceovers, shot ideas, prompt drafts, or campaign requirements, organize key context, and output summaries, diagnostic conclusions, action recommendations, and reusable deliverables for continued execution, review, or delivery.

When to Use

Applicable Scenarios

• Users ask questions such as "Is this video ready to publish?" and need 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 video quality diagnosis assistant
• Users have already prepared the video goal (for example, improve completion rate, explain the product clearly, guide clicks, create a memorable point, training explanation, or ad conversion.), viewing audience (describe the audience the video is aimed at, for example, consumers, potential customers, course students, investors, or internal reviewers.), video reference link (fill in a reference video, script page, landing page, or competitor video link that can be accessed without logging in.), and hope to organize it into executable analysis or optimization results
• Users need to turn materials related to the video quality diagnosis 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":"视频目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
goal	string	No	-	For example, improve completion rate, explain the product clearly, guide clicks, create a memorable point, training explanation, or ad conversion
audience	string	No	-	Describe the audience the video is aimed at, for example, consumers, potential customers, course students, investors, or internal reviewers
materialUrl	string	No	-	Fill in a reference video, script page, landing page, or competitor video link that can be accessed without logging in; a complete accessible URL must be provided
materialFile	string	No	-	Upload reference videos, storyboard documents, image references, brand materials, or script files to help organize the video brief
materialText	string	No	-	Paste the video topic, script, storyboard, voiceover, shot ideas, prompt drafts, or campaign requirements
brandRequirements	string	No	-	Supplement the visual tone, narration style, person/voice authorization, brand prohibitions, information that must appear, and compliance restrictions

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

Parameter Value Reference

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

Supported Input Formats

The current skill directly accepts JSON parameters; 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":"视频目标"}'

Equivalent --params JSON：

{
  "goal": "视频目标"
}

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: extract key context and the basis for judgment by combining the video goal (for example, improving completion rate, explaining the product clearly, guiding clicks, creating a memorable point, training explanation, or ad conversion.), the viewing audience (describe the viewers the video targets, for example, consumers, potential customers, course participants, investors, or internal reviewers.), and the video reference link (fill in a reference video, script page, landing page, or competitor video link that can be accessed without logging in.).
• 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 "Video Quality Diagnostic Assistant".
• Then check whether the results cover the summary, diagnostic conclusions, action recommendations, and reusable deliverables, and whether clear next steps are given.
• If the input materials are limited, 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