ProductPROPRO REQUIREDFC-PROD-011
Retention Claw
retention-claw
v0.2.0May 22, 2026Retention and churn — multi-layer strategies, churn signal detection, and intervention triggers that keep users engaged
Acquiring a user who churns in 3 days costs more than never acquiring them at all—and your CAC-to-LTV ratio is lying to you if you're not cohorted properly. I plot retention curves by acquisition channel, categorize churn reasons from exit surveys and behavioral signals, identify the habit loops that drive D7 and D30 retention, and design re-engagement triggers that bring users back before they forget you exist.
OpenClaw
Hermes
Claude Code
Codex
Cursor
Windsurf
Aider
OllamaPRIMARY ACTION
Unlock with ProCOMPATIBLE WITH
OpenClawHermesClaude CodeCodex+4
8 compatible tools5 output formats
When to Use
- Translate vague ideas into implementation scope
- Prepare user stories with acceptance criteria
- Set realistic priorities before coding
- Create an actionable launch roadmap
Compatible Frameworks
OpenClawHermesClaude CodeCodexCursorWindsurfAiderOllama8 TOOLS
Quality Gates
- Specific churn signals identified
- Multi-layer strategies employed
- Self-reinforcing loops identified
- Timely intervention triggers
- No dark patterns used
5 GATES DEFINED
Expected Outputs
Cohorted Retention Analysis (D1/D7/D30/D90)Churn Reason Taxonomy with Frequency DistributionRe-engagement Strategy Playbook by Churn SignalHabit Loop Map per Core WorkflowRetention Improvement Roadmap with Experiment Plan
Native exports per tool
OpenClaw10 files
openclaw/AGENTS.mdopenclaw/SOUL.mdopenclaw/TOOLS.md+7 moreHermes5 files
hermes/skills/flickclaw/retention-claw/SKILL.mdhermes/skills/flickclaw/retention-claw/references/workflow.mdhermes/skills/flickclaw/retention-claw/references/quality-gates.md+2 moreClaude Code6 files
claude-code/CLAUDE.mdclaude-code/.claude/skills/retention-claw/SKILL.mdclaude-code/.claude/skills/retention-claw/references/workflow.md+3 moreCodex5 files
codex/AGENTS.mdcodex/.flickclaw/agents/retention-claw/codex.mdcodex/.flickclaw/agents/retention-claw/workflow.md+2 moreCursor3 files
cursor/.cursor/rules/flickclaw-retention-claw.mdccursor/.cursor/rules/flickclaw-retention-claw-workflow.mdccursor/.cursor/rules/flickclaw-retention-claw-quality-gates.mdcWindsurf3 files
windsurf/.windsurf/rules/flickclaw-retention-claw.mdwindsurf/.windsurf/rules/flickclaw-retention-claw-workflow.mdwindsurf/.windsurf/rules/flickclaw-retention-claw-quality-gates.mdAider3 files
aider/CONVENTIONS.mdaider/aider.mdaider/.aider.conf.ymlOllama4 files
ollama/Modelfileollama/system-prompt.mdollama/template.md+1 moreInstall Commands
Install the FlickClaw CLI, then select your AI agent framework below to get the correct install command.
Step 1: Install CLI (one-time)
npm install -g @flickclaw/cli@latestStep 2: Select Framework
OpenClaw
npm exec --yes @flickclaw/cli@latest -- install retention-claw --target openclawDownload as ZIP
Example Prompt
Try this prompt with Retention Claw to see what it can do:
Analyze the current feature set and prioritize the next 3 features by user impact and effort. Create Cohorted Retention Analysis (D1/D7/D30/D90), Churn Reason Taxonomy with Frequency Distribution, Re-engagement Strategy Playbook by Churn Signal with clear rationale.Example Output
IllustrativeWhat a typical Retention Claw report looks like:
# Retention Claw — Assessment Report **Project**: feature-prioritization **Context**: a product backlog with 80+ items across 3 teams with conflicting priorities **Generated**: 2026-07-10 ## Executive Summary The Retention Claw completed its review of feature-prioritization (a product backlog with 80+ items across 3 teams with conflicting priorities). 3 findings were identified with concrete remediation steps. All quality gates were verified before delivery. ## Findings | # | Severity | Area | Finding | Recommended Action | |---|----------|------|---------|-------------------| | 1 | **P1** | Scope | 12 features lack acceptance criteria | Define criteria and success metrics before scheduling | | 2 | **P2** | Dependencies | Team B blocked on Team A for 4 upcoming items | Resequence to parallelize independent work streams | | 3 | **P2** | Metrics | No success metric defined for Q2 initiatives | Add North Star metric and leading indicators per initiative | ## Quality Gates - [✓] Retention measured in cohorts: D1, D7, D30, D90 - [✓] Churn reasons categorized from exit surveys or cancellation flows - [✓] Re-engagement triggers defined, implemented, and A/B tested ## Outputs Generated - **Cohorted Retention Analysis (D1/D7/D30/D90)**: Included in the report above. - **Churn Reason Taxonomy with Frequency Distribution**: Included in the report above. - **Re-engagement Strategy Playbook by Churn Signal**: Included in the report above. - **Habit Loop Map per Core Workflow**: Included in the report above. - **Retention Improvement Roadmap with Experiment Plan**: Included in the report above. ## Validation - [x] All quality gates passed (3/3) - [x] 3 findings documented with severity and remediation - [x] 5 output sections generated - [x] Evidence collected and referenced --- *This is an illustrative example output from FlickClaw. Results vary based on project context.*
RELATED AGENTS