Overview
The Conversion Experiment Assistant is used to answer "Is this change worth testing?", conversion rate, growth marketing, and copywriting questions. It is suitable for marketing, operations, product, and sales to invoke after clarifying business goals, content materials, or analysis targets. It combines inputs such as conversion page content, pasted above-the-fold content, selling points, CTAs, form fields, FAQs, pricing explanations, or screenshot OCR ... 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 raise questions such as "Is this change worth testing?" and need to quickly break down goals, determine priorities, and form actionable results
- Marketing, operations, product, and sales need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the Conversion Experiment Assistant
- Users have already prepared the page goal (for example, sign-up, lead capture, demo booking, purchase, download, trial, add-to-cart, or checkout completion.), target visitors (supplement visitor source, buying role, awareness stage, pain points, main concerns, and decision conditions.), page link (fill in a publicly accessible landing page, product page, sign-up page, pricing page, or checkout page link.), and want 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-step actions
Invocation Method
Call 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":"页面目标"}'
Parameter Description
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
goal |
string | No | - | For example, sign-up, lead capture, demo booking, purchase, download, trial, add-to-cart, or checkout completion |
audience |
string | No | - | Supplement visitor source, buying role, awareness stage, pain points, main concerns, and decision conditions |
materialUrl |
string | No | - | Fill in a publicly accessible landing page, product page, sign-up page, pricing page, or checkout page link; a complete accessible URL must be provided |
reviewDepth |
string | No | 标准诊断 |
Choose Quick Check, Standard Diagnosis, or Deep CRO Review; optional values:快速体检、标准诊断、深度改稿 |
materialFile |
string | No | - | Supports page materials such as docx, pdf, md, and txt, suitable for submitting page drafts, wireframe descriptions, review versions, or research summaries |
materialText |
string | No | - | Paste above-the-fold content, selling points, CTAs, form fields, FAQs, pricing explanations, or screenshot OCR text; preserving section order is better for diagnosis |
targetPlatform |
string | No | - | For example, Web, mobile web, App WebView, store page, campaign page, or SaaS console |
brandRequirements |
string | No | - | Supplement brand tone, sections that must be retained, prohibited expressions, compliance reminders, and evidence boundaries |
See the complete machine-readable parameter structure at references/form-schema.json。
Parameter Value Reference
The current skill has no categorical parameters that require an additional lookup table.
Supported input formats
The current skill directly accepts JSON parameters; if the parameters include 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":"页面目标"}'
Equivalent --params JSON:
{
"goal": "页面目标"
}
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 page goal (for example, registration, lead capture, demo booking, purchase, download, trial, add to cart, or completing checkout.), target visitors (supplement visitor source, buying role, awareness stage, pain points, main concerns, and decision conditions.), and page link (fill in a publicly accessible landing page, product page, registration page, pricing page, or checkout page link.) 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 "Conversion Experiment Assistant".
- Then check whether the results cover the summary, diagnostic conclusions, action recommendations, and reusable deliverables, and whether clear next steps are given.
- 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