churn-prevention

churn-prevention Conversion Experiment Assistant

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 churn and retention content, pasted cancellation reasons, customer service records, user feedback, renewal prompts, win-back emails, in-app messages, or... to organize 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 executable 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 retention goals (for example, reducing cancellations, explaining value, guiding successful setup, win-back of dormant users, reducing refunds, or increasing renewal willingness.), churn risk segments (supplementing subscription stage, usage frequency, customer segmentation, main objections, historical behavior, and whether manual intervention is suitable.), and retention touchpoint links (fill in publicly accessible cancellation pages, help documents, renewal pages, product pages, feedback forms, or message preview links.). They hope to organize them into executable analysis or optimization results
Users need to turn materials related to the Conversion Experiment Assistant 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 '{"goal":"留存目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
`goal`	string	No	-	For example, reducing cancellations, explaining value, guiding successful setup, win-back of dormant users, reducing refunds, or increasing renewal willingness
`audience`	string	No	-	Supplement subscription stage, usage frequency, customer segmentation, main objections, historical behavior, and whether manual intervention is suitable
`materialUrl`	string	No	-	Fill in publicly accessible cancellation pages, help documents, renewal pages, product pages, feedback forms, or message preview links; a complete accessible URL must be passed
`reviewDepth`	string	No	`标准诊断`	Choose quick checkup, standard diagnosis, or in-depth retention strategy analysis; optional values:`快速体检`、`标准诊断`、`深度改稿`
`materialFile`	string	No	-	Supports retention materials such as docx, pdf, md, txt, suitable for submitting feedback summaries, customer service excerpts, touchpoint copy, or research records
`materialText`	string	No	-	Paste cancellation reasons, customer service records, user feedback, renewal prompts, win-back emails, in-app messages, or cancellation page copy
`targetPlatform`	string	No	-	For example, in-app messages, email, customer service scripts, cancellation pages, renewal pages, CRM, community, or help center
`brandRequirements`	string	No	-	Supplement brand tone, service commitment boundaries, privacy reminders, prohibited expressions, and information that must be retained

See the full machine-readable parameter structure at references/form-schema.json。

Parameter Value Reference

This skill currently has no categorical parameters that require additional lookup.

Supported Input Formats

This skill directly accepts JSON parameters; if the parameters contain 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":"留存目标"}'

Equivalent --params JSON：

{
  "goal": "留存目标"
}

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 user goals that can be directly read, reviewed, or delivered.
Interpretation of input materials: combine the retention goal (for example, reducing cancellations, explaining value, guiding successful setup, reactivating silent users, reducing refunds, or increasing renewal intent.), the churn-risk audience (supplement the subscription stage, usage frequency, customer segment, main objections, historical behavior, and whether human intervention is appropriate.), and retention touchpoint links (fill in publicly accessible cancellation pages, help documentation, renewal pages, product pages, feedback forms, or message preview links.) 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 "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: Default https://ai-skills.ai
AISKILLS_API_KEY: Required, used for authenticated calls
AISKILLS_TENANT_ID: Default default