Post-mortem analysis when a client churns. Takes client history, engagement data, support tickets, usage logs, and exit feedback to produce a comprehensive churn autopsy with root cause classification, timeline of decline, and preventive measures.
SkillScore73Maintained
Automatic
◆Customer Success pack
Last verified 8/24/2026
What it changes
Passed 15 of 21 test cases with the skill, and 11 of 21 without it.
Without skill55%
With skill73%
Checks it passed that the model alone missed
Specifies the output filename churn-autopsy.md.
Requires including lessons learned to convert account loss into organizational learning.
Specifies creating the output file named churn-autopsy.md in the current working directory.
and 1 more in the full report
4 fixed12 passed either way6 still failing0 broke
Pass-rate lift
+18 pp
Tokens
-3%
Agent turns
0%
Response time
-21%
Model gemini-3.6-flashMeasured 8/24/2026v116 of 22 cases passed with skill · 21 comparable
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 4
Prompt
What exact filename must be produced at the end of a forensic account loss investigation?
What was checked, without and with the skill
Checked
Without skill
With skill
Specifies the output filename churn-autopsy.md.
Missed
Passed
case-18 · gemini-3.6-flash · 8/24/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md21 lines6 files
Churn Autopsy
Dissect a client departure with forensic rigor and produce churn-autopsy.md: a historical record and retention playbook that turns a loss into organizational learning.
Contents
references/inputs.md -- required and optional data to gather before analysis
references/analysis-framework.md -- the six-phase forensic method
references/root-cause-taxonomy.md -- root cause categories and subcategories
references/output-template.md -- full churn-autopsy.md report structure
references/standards.md -- objectivity, rigor, sensitivity, incomplete-data, and operating rules
Workflow
Collect. Gather all available inputs per references/inputs.md. Read provided files directly; query connected CRM and analytics MCP tools for account, usage, and support data. Note any gaps.
Organize. Build the full chronological timeline from first touch to cancellation before attempting analysis.
Analyze. Apply the six phases in references/analysis-framework.md systematically, without skipping: baseline, timeline of decline, root cause classification, missed warning signs, counterfactual analysis, lessons learned.
Classify. Assign one primary root cause and any contributing causes using references/root-cause-taxonomy.md.
Draft. Write the report in the structure defined in references/output-template.md.
Challenge. Review every conclusion against references/standards.md; attempt to disprove each finding before keeping it.
Finalize. Produce churn-autopsy.md with all sections complete in the current working directory or a user-specified location.