Overview
The conversion experiment assistant is used to answer "is this change worth testing," sales enablement, customer research, and follow-up plans, and is suitable for sales, marketing, operations, and product to invoke after clarifying business goals, content materials, or analysis targets. It combines inputs such as product and GTM background, pasted product introduction, target customers, pricing, competition, cases, channels, current growth issues, or team..., 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 such as "is this change worth testing," and need to quickly break down goals, determine priorities, and form actionable results
- Sales, marketing, operations, and product need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the conversion experiment assistant
- Users have already prepared the current stage (choose the stage of the product or growth to facilitate strategic trade-offs.), strategy depth (strategy depth), business goals (such as initial leads, pilot customers, channel validation, launch campaigns, sales efficiency, or retention improvement.), and hope to organize them into actionable analysis or optimization results
- Users need to turn materials related to the conversion experiment assistant into clear conclusions, priorities, and next steps
How to Invoke
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 '{"stage":"想法验证"}'
Parameter Description
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
stage |
string | No | 正式发布 |
Choose the stage of the product or growth to facilitate strategic trade-offs; optional values:想法验证、内测、正式发布、增长优化 |
reviewDepth |
string | No | 标准策略 |
Strategy depth; optional values:快速一页纸、标准策略、深度 GTM 计划 |
businessGoal |
string | No | - | For example, initial leads, pilot customers, channel validation, launch campaigns, sales efficiency, or retention improvement |
marketContext |
string | No | - | Supplement with industry, region, competitors, customer segmentation, market constraints, or existing research conclusions |
gtmContextFile |
string | No | - | Supports product, market, or growth plan files such as docx, pdf, md, and txt |
productContext |
string | No | - | Paste product introduction, target customers, pricing, competition, cases, channels, current growth issues, or team constraints |
For the complete machine-readable parameter structure, see references/form-schema.json。
Parameter Value Reference
This skill has no categorical parameters that require additional lookup.
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 '{"stage":"想法验证"}'
Equivalent --params JSON:
{
"stage": "想法验证"
}
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: extract key context and judgment basis in light of the current stage (choose the stage of the product or growth to facilitate control over strategic trade-offs.), strategic depth (strategic depth), and business goals (e.g., first batch of leads, pilot customers, channel validation, launch campaign, sales efficiency improvement, or retention improvement.).
- 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 is little input material, it is recommended to have the user supplement the goals, audience, constraints, or source materials before running.
Preparation Before Running
AISKILLS_BASE_URL: defaulthttps://ai-skills.aiAISKILLS_API_KEY: required, used for authenticated callsAISKILLS_TENANT_ID: defaultdefault