churn-autopsy — Claude Code skill: what it does, how to install
churn-autopsy — a skill for post-mortem analysis of client churn. Collects interaction history, support tickets, usage logs and exit feedback, then builds a timeline of decline and identifies root causes.
MIT 244 installs ★ 440 updated 2026-10-20
npx skills add OneWave-AI/claude-skills --skill churn-autopsy -a claude-codeWhat churn-autopsy does
churn-autopsy runs a six-phase investigation: it builds a timeline from first contact to cancellation, classifies the root cause using a built-in taxonomy, spots missed warning signs and suggests preventive measures. The skill reads project files and can query data from connected CRM and analytics MCP servers.
Output goes to churn-autopsy.md — a report with sections for baseline state, timeline of decline, root cause, missed warnings, counterfactual analysis and lessons learned. Without connected MCP tools for CRM and analytics access, part of the data will need manual collection.
The skill operates through built-in Read, Write, Edit, Glob, Grep, Bash, WebFetch and WebSearch tools. Before starting analysis it checks data availability and logs gaps; before finalising the report it reviews every conclusion against objectivity standards.
What it helps with
- dissect client departure reasons from CRM data, logs and tickets
- trace the timeline of engagement drop before churn
- spot missed warning signals in interaction history
- classify churn root cause using a standard taxonomy
- record retention lessons in a structured report
Example prompts for the agent
- Analyse Beta Inc churn from
clients/beta-inc/history.jsonand tickets insupport/beta-2024-q1/ - Build a departure timeline from CRM data and write the report to
reports/churn/ - Investigate subscription cancellation from
exit-survey.jsonandusage-logs.csv
How to install churn-autopsy
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill churn-autopsy -a claude-code2Manually: put the files in place
~/.claude/skills/churn-autopsy/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/churn-autopsy/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill churn-autopsy -a codex2Manually: put the files in place
.agents/skills/churn-autopsy/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill churn-autopsy -a cursor2Manually: put the files in place
.cursor/skills/churn-autopsy/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install OneWave-AI/claude-skills churn-autopsy2Manually: put the files in place
.github/skills/churn-autopsy/SKILL.md1Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill churn-autopsy -a gemini-cli2Platform CLI
gemini skills install https://github.com/OneWave-AI/claude-skills --path churn-autopsyManually: put the files in place
.devin/skills/churn-autopsy/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add OneWave-AI/claude-skills --skill churn-autopsy -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about churn-autopsy
How to install churn-autopsy in Claude Code?
Run npx skills add OneWave-AI/claude-skills --skill churn-autopsy -a claude-code; the skill installs to ~/.claude/skills/churn-autopsy/SKILL.md.
What does churn-autopsy do?
It performs post-mortem analysis of client churn: gathers interaction history, support tickets and logs, builds a timeline of activity decline, identifies the root cause via taxonomy and writes a report with preventive measures to churn-autopsy.md.
What data does churn-autopsy need?
It requires client history, engagement data, support tickets, usage logs and exit feedback. The skill reads files and queries connected MCP tools for CRM and analytics; if MCP is unavailable, part of the data is collected manually.
Source text
SKILL.md · MIT
--- name: churn-autopsy description: 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. tools: Read, Write, Edit, Glob, Grep, Bash, WebFetch, WebSearch model: inherit --- # 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 1. **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. 2. **Organize.** Build the full chronological timeline from first touch to cancellation before attempting analysis. 3. **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. 4. **Classify.** Assign one primary root cause and any contributing causes using `references/root-cause-taxonomy.md`. 5. **Draft.** Write the report in the structure defined in `references/output-template.md`. 6. **Challenge.** Review every conclusion against `references/standards.md`; attempt to disprove each finding before keeping it. 7. **Finalize.** Produce `churn-autopsy.md` with all sections complete in the current working directory or a user-specified location.
© OneWave-AI · MIT · OneWave-AI/claude-skills