Overview
The Conversion Experiment Assistant is used to answer "Is this change worth testing?", conversion rate, growth marketing, and copywriting. It is suitable for marketing, operations, product, and sales to call after clarifying business goals, content materials, or analysis objects. It will combine copy drafts, pasted headlines, body text, selling points, CTAs, advertising slogans, email paragraphs, or product descriptions; retain context... and other inputs, organize key context, and output summaries, diagnostic conclusions, action recommendations, and reusable deliverables for continued execution, review, or delivery.
When to Use
Applicable Scenarios
- The user raises questions such as "Is this change worth testing?" and needs to quickly break down goals, determine priorities, and form executable results
- Marketing, operations, product, and sales need to generate summaries, diagnostic conclusions, action recommendations, and reusable deliverables around the Conversion Experiment Assistant
- The user has already prepared the copywriting goal (for example, registration, purchase, lead capture, click, booking, reply, downloading materials, or understanding product value.), target audience (supplement buying role, user stage, pain points, awareness level, and decision influencers.), and the link where the copy is located (fill in a publicly accessible webpage, campaign page, document preview, or product description link.), and hopes to organize it into executable analysis or optimization results
- The user needs to turn materials related to the Conversion Experiment Assistant into clear conclusions, priorities, and next-step actions
How to Call
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 '{"goal":"文案目标"}'
Parameter Description
| Parameter | Type | Required | Default | Description |
|---|---|---|---|---|
goal |
string | No | - | For example, registration, purchase, lead capture, click, booking, reply, downloading materials, or understanding product value |
audience |
string | No | - | Supplement buying role, user stage, pain points, awareness level, and decision influencers |
materialUrl |
string | No | - | Fill in a publicly accessible webpage, campaign page, document preview, or product description link; a complete accessible URL must be provided |
reviewDepth |
string | No | 标准诊断 |
Choose quick polish, standard diagnosis, or deep rewrite; optional values:快速体检、标准诊断、深度改稿 |
materialFile |
string | No | - | Supports copy files such as docx, pdf, md, txt, suitable for submitting complete pages, campaign drafts, or brand review versions |
materialText |
string | No | - | Paste headlines, body text, selling points, CTAs, advertising slogans, email paragraphs, or product descriptions; retaining context is better for judgment |
targetPlatform |
string | No | - | For example, official website, email, social media, advertising, in-app messages, sales materials, or offline materials |
brandRequirements |
string | No | - | Supplement brand tone, prohibited words, information that must be retained, compliance reminders, and promises that cannot be exaggerated |
See the complete machine-readable parameter structure at references/form-schema.json。
Parameter Value Reference
The current skill has no categorical parameters that require additional table lookup.
Supported input formats
This skill currently accepts JSON parameters directly; if the parameters include a link field, 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":"文案目标"}'
Equivalent --params JSON:
{
"goal": "文案目标"
}
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 copy goals (for example, registration, purchase, lead capture, clicks, appointments, replies, downloading materials, or understanding product value.), target audience (supplement the buying role, user stage, pain points, awareness level, and decision influencers.), and the link where the copy is located (provide a publicly accessible webpage, campaign page, document preview, or product description link.) 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 "Conversion Experiment Assistant."
- Then check whether the results cover the summary, diagnostic conclusions, action recommendations, and reusable deliverables, and whether they provide clear next steps.
- 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: defaulthttps://ai-skills.aiAISKILLS_API_KEY: required, used for authenticated callsAISKILLS_TENANT_ID: defaultdefault