This walks you through Dave McClure's AARRR framework with actual formulas and conversion tracking between each stage: Acquisition, Activation, Retention, Revenue, and Referral. You feed it your funnel numbers and it builds a dashboard showing where users drop off, calculates metrics like viral coefficient and LTV:CAC, and scores experiments using ICE framework (Impact, Confidence, Ease). The examples are detailed, showing complete funnel visualizations and stage-by-stage breakdowns with specific percentages. Most useful when you need to explain growth problems to investors or figure out which part of your funnel is actually broken. It's opinionated about what healthy benchmarks look like, which is either helpful or annoying depending on your product.

skills.sh installs
219
GitHub stars
150
last updated
Aug 21, 2026

Install

$ npx -y skills add guia-matthieu/clawfu-skills --skill aarrr-metrics --agent claude-code

Installs into .claude/skills of the current project.

Files

AARRR Pirate Metrics

Apply Dave McClure's AARRR framework to measure and optimize growth through the five stages: Acquisition, Activation, Retention, Revenue, and Referral.

When to Use This Skill

  • Building growth dashboards
  • Identifying funnel bottlenecks
  • Prioritizing growth experiments
  • Reporting to investors
  • Diagnosing growth problems

Methodology Foundation

Based on Dave McClure's AARRR framework (500 Startups), providing:

  • Stage-specific metrics definition
  • Funnel conversion analysis
  • Prioritization framework
  • Experiment design guidance

What Claude Does vs What You Decide

Claude DoesYou Decide
Defines metrics per stageSpecific definitions for your product
Identifies bottlenecksExperiment priorities
Suggests experimentsResource allocation
Creates dashboardsTool selection
Benchmarks performanceAcceptable thresholds

Instructions

Step 1: Define Each Stage

AARRR Stages:

Sponsors

Details

Repository
github.com/guia-matthieu/clawfu-skills
First seen
Jun 3, 2026

More from guia-matthieu/clawfu-skills

All 96

Recommended

1juliusbrussee avatarcavemanjuliusbrussee/cavemanUltra-compressed communication mode. Cuts output tokens 65% (measured) by speaking like caveman while keeping full technical accuracy. Supports intensity levels618.3Kskills.sh installs
2mattpocock avatargrill-memattpocock/skillsA relentless interview to sharpen a plan or design.1.5Mskills.sh installs
3shadcn avatarimproveshadcn/improveSurvey any codebase as a senior advisor and produce prioritized, self-contained implementation plans for OTHER models/agents to execute. Strictly read-only on s40Kskills.sh installs
4obra avatarsystematic-debuggingobra/superpowersUse when encountering any bug, test failure, or unexpected behavior, before proposing fixes326.7Kskills.sh installs
5forrestchang avatarkarpathy-guidelinesforrestchang/andrej-karpathy-skillsBehavioral guidelines to reduce common LLM coding mistakes through explicit assumptions, simplicity, and verifiable success criteria.17.9Kskills.sh installs
6vercel-labs avatarfind-skillsvercel-labs/skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express int4.3Mskills.sh installs