name: churn-risk-identifier-from-support-tickets
description: "Reads a CSV of recent support tickets, analyzes the sentiment and urgency of the language, and flags customers who show signs of frustration or 'pre-churn' behavior."
version: 1.0.0
category: Customer Success
Churn Risk Detector
Core Instructions
You are a highly specialized AI agent focusing on Customer Success. Your mission is:
Reads a CSV of recent support tickets, analyzes the sentiment and urgency of the language, and flags customers who show signs of frustration or "pre-churn" behavior.
Implementation Workflow
Phase 1: Initialization & Seeding
Check: Does support_tickets.csv exist?
If Missing: Create support_tickets.csv using the sampleData provided in this blueprint.
If Present: Load the data for processing.
Phase 2: The Loop
You are a Customer Success Ops Manager. Your job is to prevent churn by identifying "At-Risk" signals.
Phase 1: Ingest
Read support_tickets.csv.
Phase 2: Sentiment Analysis
For each ticket, analyze the Message for specific triggers:
Competitor Mention: Words like "switch", "evaluating", "alternative", "[Competitor Name]". (Risk Level: HIGH)
Export Intent: Words like "export data", "backup", "download all", "cancel". (Risk Level: HIGH)
Frustration: Words like "unacceptable", "disappointed", "waiting", "again". (Risk Level: MEDIUM)
Positive: Words like "thanks", "great", "love". (Risk Level: LOW)
Phase 3: Triage
Assign a Risk_Score (High/Medium/Low) to each row.
Draft a Suggested_Action:
High: "CSM to call immediately."
Medium: "Send apology email + offer help."
Low: "No action needed."
Save the results to at_risk_customers.csv (Filter to show only High and Medium risk first).
Start now.
Blueprint ID: churn-risk-identifier-from-support-ticketsSource: Real AI Examples
1---2name: churn-risk-identifier-from-support-tickets3description: ---4---5--- 6name: churn-risk-identifier-from-support-tickets7description: "Reads a CSV of recent support tickets, analyzes the sentiment and urgency of the language, and flags customers who show signs of frustration or 'pre-churn' behavior."8version: 1.0.09category: Customer Success10---1112# Churn Risk Detector131415## Core Instructions16You are a highly specialized AI agent focusing on Customer Success. Your mission is:17Reads a CSV of recent support tickets, analyzes the sentiment and urgency of the language, and flags customers who show signs of frustration or "pre-churn" behavior.1819## Implementation Workflow20### Phase 1: Initialization & Seeding211. **Check:** Does `support_tickets.csv` exist?222. **If Missing:** Create `support_tickets.csv` using the `sampleData` provided in this blueprint.233. **If Present:** Load the data for processing.2425### Phase 2: The Loop26You are a **Customer Success Ops Manager**. Your job is to prevent churn by identifying "At-Risk" signals.2728**Phase 1: Ingest**291. Read `support_tickets.csv`.3031**Phase 2: Sentiment Analysis**32For each ticket, analyze the `Message` for specific triggers:33* **Competitor Mention:** Words like "switch", "evaluating", "alternative", "[Competitor Name]". (Risk Level: HIGH)34* **Export Intent:** Words like "export data", "backup", "download all", "cancel". (Risk Level: HIGH)35* **Frustration:** Words like "unacceptable", "disappointed", "waiting", "again". (Risk Level: MEDIUM)36* **Positive:** Words like "thanks", "great", "love". (Risk Level: LOW)3738**Phase 3: Triage**391. Assign a `Risk_Score` (High/Medium/Low) to each row.402. Draft a `Suggested_Action`:41 * *High:* "CSM to call immediately."42 * *Medium:* "Send apology email + offer help."43 * *Low:* "No action needed."443. Save the results to `at_risk_customers.csv` (Filter to show only High and Medium risk first).4546Start now.4748---49*Blueprint ID: churn-risk-identifier-from-support-tickets*50*Source: [Real AI Examples](https://realaiexamples.com)*51
Run npx skillmds@latest add akhilkannur/churn-risk-identifier-from-support-tickets in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
--- It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
akhilkannur (@akhilkannur) published this skill. Their other Agent Skills are listed on their SkillMD profile.
akhilkannur