Customer Retention Analyst
Analyzes churn or retention data to find the specific segment and likely cause behind customer loss, not just the overall churn rate.
Customer Retention Analyst is a free AI skill for data workflows. Analyzes churn or retention data to find the specific segment and likely cause behind customer loss, not just the overall churn rate. It works with Claude, ChatGPT, Cursor and is ready to use out of the box.
About this skill
Customer Retention Analyst takes churn, usage, or customer data and digs past the headline retention rate to find which segment is actually driving the loss and what pattern precedes it — a usage drop-off, a pricing tier, an onboarding gap, a support issue. It separates confirmed patterns in the data from hypotheses that need further investigation, and ends with a prioritized, testable next step rather than a vague 'improve retention' recommendation.
What it does
Given customer, usage, or churn data and a retention question, the skill segments the data to find where churn concentrates (by cohort, plan tier, usage pattern, acquisition channel, etc.), identifies the behavior or event that most often precedes churn in that segment, separates confirmed patterns from hypotheses with a VERIFY flag, and recommends one specific, testable intervention.
What is included
- Churn segmentation framework (cohort, tier, channel, usage pattern)
- Pre-churn behavior pattern identification
- Confirmed-pattern vs. hypothesis separation with VERIFY flagging
- Prioritized, testable intervention recommendation
- Retention metric definitions cheat sheet (logo churn, revenue churn, NRR)
How to use it
1. Download the SKILL.md file 2. Upload it to Claude, ChatGPT, or Cursor as a project skill or custom instructions 3. Share your churn/usage data along with the retention question you're investigating 4. Receive a segmented analysis, the likely pre-churn pattern, and one testable next step
Examples
Our overall monthly churn is 4%, but I feel like it's worse for some customers than others. Data: signup_date, plan_tier, last_login, churned (yes/no).
Segmentation finding: - Churn concentrates heavily in customers who haven't logged in within 14 days of signup — this group churns at roughly 3x the overall rate - Plan tier shows only a small difference in churn rate; tier is not the primary driver here VERIFY: this dataset doesn't include onboarding completion or support ticket data, which would help confirm whether the 14-day gap is caused by onboarding friction or something else — worth pulling in if available. Recommended test: add a check-in touchpoint (email or in-app) at day 7 for accounts with no login since signup, and measure whether it shifts the 14-day-inactive churn rate over the next full cohort cycle.
FAQ
What is this skill for?
How do I install it?
What if my data is limited, like just signup date and churn status?
Does it calculate standard SaaS metrics like NRR?
How is this different from a general data analysis request?
Will it recommend multiple fixes at once?
Related Skills
Data Analysis Assistant
Turns a raw dataset description or file into a structured analysis: key metrics, trends, anomalies, and plain-language findings.
CSV Data Cleaning & Insights Reporter
Reviews a pasted CSV/table sample, flags data quality issues, proposes cleaning steps, and surfaces the top 3 insights worth investigating.
Data Analysis Workflow Planner
Design a reliable data-analysis workflow from raw files to validated insights, including cleaning, checks, methods, outputs, and reproducibility.