Overview
The Conversion Experiment Assistant is used to answer "Is this change worth testing?", 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 objects. It combines inputs such as detail page copy, pasted product titles, above-the-fold selling points, detail descriptions, specifications, FAQ, guarantee statements, and other page… to 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 like "Is this change worth testing?" and need to quickly break down goals, determine priorities, and form actionable results
- Operations, marketing, sales, and product teams need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the Conversion Experiment Assistant
- Users have already prepared uploaded page materials (supports detail page screenshots, copy documents, image briefs, or operations material packages.), sales platform (sales platform), basic product information (supplement category, price range, specifications, core selling points, fulfillment information, promotion mechanisms, and facts that must be retained.), and want to organize them into actionable analysis or optimization results
- Users need to turn Conversion Experiment Assistant-related materials into clear conclusions, priorities, and next steps
How to Invoke
Directly call the AI Skills API through the exported Python runner:
Command Examples
Basic Invocation
python3 scripts/run.py --params '{}'
Invocation with Common Parameters
python3 scripts/run.py --params '{"pageFile":1}'
Parameter Description
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
pageFile |
string | No | - | Supports detail page screenshots, copy documents, image briefs, or operations material packages |
platform |
string | No | 通用电商 |
Sales platform; optional values:通用电商、淘宝/天猫、京东、拼多多、抖音电商、小红书店铺、独立站、亚马逊 |
productInfo |
string | No | - | Supplement category, price range, specifications, core selling points, fulfillment information, promotion mechanisms, and facts that must be retained |
reviewDepth |
string | No | 标准诊断 |
Diagnosis depth; optional values:快速诊断、标准诊断、深度优化 |
targetAudience |
string | No | - | Describe the main buyer, user, gift recipient, or segmented scenario |
competitorLinks |
string | No | - | Enter public competitor links, or paste competitor titles, prices, main image selling points, review summaries, and detail page structure |
productPageText |
string | No | - | Paste page content such as product titles, above-the-fold selling points, detail descriptions, specifications, FAQ, and guarantee statements |
customerConcerns |
string | No | - | Supplement high-frequency customer service questions, negative review summaries, return reasons, purchase hesitation points, or after-sales disputes |
productImagesBrief |
string | No | - | Describe main images, scene images, detail images, comparison images, certificate images, and text information in the current images |
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 table lookup.
Supported Input Formats
The current skill directly receives JSON parameters and does not involve parsing share links.
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 '{"pageFile":1}'
Equivalent --params JSON：
{
"pageFile": 1
}
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 uploaded page materials (supports detail page screenshots, copy documents, image briefs, or operations material packages.), sales platform (sales platform), and basic product information (supplement category, price range, specifications, core selling points, fulfillment information, promotion mechanisms, and facts that must be retained.) to extract key context and basis for judgment.
- Next steps: provide priorities, execution recommendations, 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 "Conversion Experiment 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 are few input materials, 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