Use when consolidating product usage, health, and sentiment signals for lifecycle programs.
NewMaintained
Automatic
◆Customer Success pack
Last verified 8/23/2026
What it changes
Passed 7 of 22 test cases with the skill, and 15 of 22 without it.
Without skill67%
With skill33%
Checks it passed that the model alone missed
Includes tagging signals or accounts by personas or verticals during the normalization step.
Includes a closed loop step to track outcomes such as expansion booked, churn prevented, or advocacy activated.
1 fixed14 passed either way5 still failing2 broke
Pass-rate lift
-33 pp
Tokens
-12%
Agent turns
0%
Response time
-21%
Model gemini-3.6-flashMeasured 8/23/2026v115 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
A test case the skill fixed. Same model, same prompt, with and without the skill.
Prompt
We are setting up a centralized lifecycle dashboard to monitor churn risks and adoption signals. Could you outline a blueprint covering data sources, identity normalization steps, signal categorization, and automated alert mechanisms to distribute these insights to our cross-functional teams?
What was checked, without and with the skill
Checked
Without skill
With skill
Includes a closed loop step to track outcomes such as expansion booked, churn prevented, or advocacy activated.
Missed
Passed
Includes tagging signals or accounts by personas or verticals during the normalization step.
Missed
Passed
case-01 · gemini-3.6-flash · 8/23/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md25 linessingle file
Customer Insights & Telemetry Skill
When to Use
Building segment-specific lifecycle journeys.
Prioritizing accounts for adoption help, expansion offers, or advocacy invites.
Diagnosing churn/retention risks and surfacing insights to CS + product.
Framework
Signals Stack – product usage, engagement, sentiment, commercial, health composite.
Data Plumbing – define sources (warehouse, product analytics, CS tools) and refresh cadence.
Normalization – align account/user IDs, tag personas/verticals.