ai-churn-prevention

ai-churn-prevention churn warning diagnostic assistant

Quick Start

More Skills

Overview

The churn warning diagnostic assistant is used to answer “why are customers leaving,” organize materials, clean data, and define action items. It is suitable for operations, product, sales, and software to invoke after clarifying business goals, content materials, or analysis targets. It combines inputs such as pages, process or experiment materials, pasted page copy, process descriptions, experiment ideas, conversion goals, user feedback, or friction clues, organizes key context, and outputs churn attribution, recovery priorities, and outreach suggestions for further execution, review, or delivery. Capability positioning supplement: user churn diagnosis can serve as a material analysis tool for operations and customer success.

When to Use

Applicable Scenarios

• Users raise questions such as “why are customers leaving,” and need to quickly break down goals, determine priorities, and form executable results
• Operations, product, sales, and software need to generate churn attribution, recovery priorities, and outreach suggestions around the churn warning diagnostic assistant
• Users have already prepared conversion goals (explain the registration, activation, upgrade, retention, payment, or experiment metrics to optimize), target users (explain user stage, segment, traffic source, device, or usage scenario), and page or process links (fill in publicly accessible landing pages, registration pages, paywalls, processes, or reference links), and want to organize them into executable analysis or optimization results
• Users need to turn churn warning diagnostic assistant-related materials 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 '{"goal":"转化目标"}'

Parameter Description

Parameter	Type	Required	Default	Description
goal	string	No	-	Explain the registration, activation, upgrade, retention, payment, or experiment metrics to optimize
audience	string	No	-	Explain user stage, segment, traffic source, device, or usage scenario
materialUrl	string	No	-	Fill in publicly accessible landing pages, registration pages, paywalls, processes, or reference links; a complete accessible URL must be provided
materialFile	string	No	-	Upload page screenshots, conversion data, user feedback, experiment planning, or product materials
materialText	string	No	-	Paste page copy, process descriptions, experiment ideas, conversion goals, user feedback, or friction clues
brandRequirements	string	No	-	Supplement sample size, metric definitions, brand restrictions, technical constraints, unchangeable items, or launch review priorities

For the complete machine-readable parameter structure, see references/form-schema.json。

Parameter Value Reference

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

Supported Input Formats

This skill currently accepts JSON parameters directly; if the parameters contain link fields, provide complete, accessible URLs.

Example Request

The example parameters below can be passed directly to scripts/run.py, the runner will send them to the AI Skills API.

python3 scripts/run.py --params '{"goal":"转化目标"}'

Equivalent --params JSON：

{
  "goal": "转化目标"
}

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

• Churn attribution, recovery priority, outreach suggestions: organize the core results around user goals that can be directly read, reviewed, or delivered.
• Interpretation of input materials: combined with conversion goals (explain the registration, activation, upgrade, retention, payment, or experiment metrics to be optimized.), target users (explain the user stage, segment, traffic source, device, or usage scenario.), page or process links (fill in publicly accessible landing pages, registration pages, paywalls, processes, or reference links.) to extract key context and the basis for judgment.
• Next-step actions: provide priorities, execution suggestions, or a content framework that can be further processed.

Suggestions for Using the Results

• First determine whether the output answers the user's core question about the "Churn Early Warning Diagnosis Assistant."
• Then check whether the results cover churn attribution, recovery priority, and outreach suggestions, and whether they provide clear next-step actions.
• If the input materials are limited, it is recommended to have the user supplement the goals, audience, constraints, or original 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