Overview
The risk review assistant is used to answer questions such as "What risks are here?", ad copy, compliance, and conversion. It is suitable for operations, marketing, sales, and legal teams to invoke after clarifying business objectives, content materials, or analysis targets. It combines ad placement copy, pasteable ad titles, body text, selling points, CTA, or spoken scripts; it is recommended to retain inputs such as the placement platform and review... to organize key context and output a summary, diagnostic conclusions, action recommendations, and reusable deliverables, making it easy to continue execution, review, or delivery.
When to Use
Applicable Scenarios
- The user asks questions like "What risks are here?" and needs to quickly break down objectives, determine priorities, and form actionable results
- Operations, marketing, sales, and legal teams need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the risk review assistant
- The user has already prepared conversion objectives (for example, increasing click-through rate, reducing review risk, improving lead quality, driving consultations or orders.), target audience (explain the audience and placement scenarios the ad targets, for example, new customers in feed ads, high-intent search users, or remarketing audiences.), and ad landing links (fill in ad pages, product pages, campaign pages, or placement preview links that can be accessed without logging in.). and wants to organize them into actionable analysis or optimization results
- The user needs to turn risk review assistant-related materials into clear conclusions, priorities, and next-step actions
How to Invoke
Invoke 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":"转化目标"}'
Parameter Description
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
goal |
string | No | - | For example, increase click-through rate, reduce review risk, improve lead quality, drive consultations or orders |
audience |
string | No | - | Explain the audience and placement scenarios the ad targets, for example, new customers in feed ads, high-intent search users, or remarketing audiences |
materialUrl |
string | No | - | Fill in ad pages, product pages, campaign pages, or placement preview links that can be accessed without logging in; a complete accessible URL is required |
reviewDepth |
string | No | 标准诊断 |
Diagnosis depth; optional values:快速体检、标准诊断、深度改稿 |
materialFile |
string | No | - | Supports ad documents such as docx, pdf, md, and txt, suitable for submitting multiple versions of ad copy, scripts, or review drafts |
materialText |
string | No | - | Pasteable ad titles, body text, selling points, CTA, or spoken scripts; it is recommended to retain the placement platform and review-sensitive expressions |
targetPlatform |
string | No | 广告投放 |
Target platform; optional values:广告投放、信息流、搜索广告、朋友圈广告 |
complianceRules |
string | No | - | Industry prohibited words, platform review requirements, or brand legal requirements |
brandRequirements |
string | No | - | Supplement platform restrictions, industry compliance requirements, prohibited words, discounts or product facts that must be retained |
See for the complete machine-readable parameter structure references/form-schema.json。
Parameter Value Reference
The current skill does not have any 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":"转化目标"}'
Equivalent --params JSON：
{
"goal": "转化目标"
}
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 around the user's goals that can be directly read, reviewed, or delivered.
- Interpretation of input materials: combine the conversion goal (for example, increasing click-through rate, reducing review risk, improving lead quality, or driving consultation or orders.), target audience (explain the audience and placement scenario the ad targets, for example, new customers in feeds, high-intent search users, or remarketing audiences.), and ad landing link (fill in an ad page, product page, campaign page, or placement preview 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 developed.
Suggestions for using the results
- First determine whether the output answers the user's core question about the "Risk Review Assistant".
- Then check whether the results cover the summary, diagnostic conclusions, action recommendations, and reusable deliverables, and whether clear next steps are provided.
- 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: defaulthttps://ai-skills.aiAISKILLS_API_KEY: required, used for authenticated callsAISKILLS_TENANT_ID: defaultdefault