live-commerce-script-compliance-review

live-commerce-script-compliance-review Risk Review Assistant

Overview

The Risk Review Assistant is used to answer "what risks are here," e-commerce operations, product conversion, and user feedback. It is suitable for operations, marketing, sales, and product teams to invoke after clarifying business goals, content materials, or analysis targets. It combines livestream scripts, pasted host openings, product introductions, closing pitches, benefits, pricing, after-sales, and interactive scripts. and other inputs, organizes key context, and outputs summaries, diagnostic conclusions, action recommendations, and reusable deliverables for continued execution, review, or delivery.

When to Use

Applicable Scenarios

Users raise questions like "what risks are here," requiring quick breakdown of goals, judgment of priorities, and formation of executable results
Operations, marketing, sales, and product teams need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the Risk Review Assistant
Users have already prepared the livestream platform (livestream platform), product and qualification information (supplement category, selling points, scope of application, testing/certification, prohibited expressions, and information that must be retained.), review focus (review focus), and want to organize it into executable analysis or optimization results
Users need to turn Risk Review Assistant-related materials into clear conclusions, priorities, and next-step actions

How to Invoke

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

Command Examples

Basic Call

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

Call with Common Parameters

python3 scripts/run.py --params '{"platform":"通用直播电商"}'

Parameter Description

Parameter	Type	Required	Default	Description
`platform`	string	No	`通用直播电商`	Livestream platform; optional values:`通用直播电商`、`抖音电商`、`淘宝直播`、`快手电商`、`小红书直播`、`视频号直播`、`TikTok Shop`
`productInfo`	string	No	-	Supplement category, selling points, scope of application, testing/certification, prohibited expressions, and information that must be retained
`reviewFocus`	string	No	`风险提示与安全改写`	Review focus; optional values:`风险提示与安全改写`、`价格优惠话术`、`功效卖点话术`、`逼单促销话术`、`主播提示卡`
`liveTalkFile`	string	No	-	Supports livestream scripts, product card materials, campaign plans, review sheets, or script documents
`liveTalkText`	string	No	-	Paste host openings, product introductions, closing pitches, benefits, pricing, after-sales, and interactive scripts
`promotionRules`	string	No	-	Fill in price, final price, discount threshold, gifts, time-limited/quantity-limited offers, inventory, after-sales, and shipping notes
`industryCategory`	string	No	`通用品类`	Product industry; optional values:`通用品类`、`食品饮料`、`保健营养`、`美妆个护`、`母婴儿童`、`家清日化`、`服饰鞋包`、`数码家电`、`医疗健康`、`金融/教育服务`

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 lookup tables.

Supported Input Formats

This skill directly accepts JSON parameters and does not involve share-link parsing.

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 '{"platform":"通用直播电商"}'

Equivalent --params JSON：

{
  "platform": "通用直播电商"
}

Example Response

{
  "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 so they can be directly read, reviewed, or delivered.
Interpretation of input materials: combine the livestream platform (livestream platform), product and qualification information (supplement category, selling points, scope of application, testing/certification, prohibited expressions, and information that must be retained.), and review priorities (review priorities) to extract key context and the basis for judgment.
Next steps: provide priorities, execution recommendations, 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 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