Token导航 LogoToken导航

Agent Skill · 研究检索

aarrr-metrics(aarrr 指标)

aarrr-metrics 用于查找、检索和筛选相关信息,适合在 Codex、Claude、Cursor、Gemini CLI 中需要根据关键词、任务场景或来源线索快速定位候选结果时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

aarrr-metrics 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为只读;许可证信息还不明确,第三方扫描已通过,按安装量在研究检索类的 73,675 个 Skill 里排第 34,961。

总安装 2,162周安装 91GitHub Stars 85下载 757核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:aarrr-metrics(aarrr 指标)
来源仓库:https://github.com/guia-matthieu/clawfu-skills
仓库路径:skills/aarrr-metrics
安装命令:
npx skills add https://github.com/guia-matthieu/clawfu-skills --skill aarrr-metrics
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/guia-matthieu/clawfu-skills --skill aarrr-metrics

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

aarrr-metrics 基于 AARRR 海盗指标框架,用于分析和优化产品增长漏斗。适用于构建增长看板、识别转化瓶颈和制定实验优先级等场景。通过定义各阶段关键指标、分析漏斗转化率和建议实验方向来支持决策。安装需通过 npx 从指定 GitHub 仓库添加,使用前请确认环境权限与依赖配置。

注意该技能依赖外部数据源,需确保网络连通性及目标平台对 MCP 工具的支持状态。

来源仓库内路径:skills/aarrr-metrics

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/guia-matthieu/clawfu-skills --skill aarrr-metr…;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它标注为只读,先用只读任务试一次,确认行为符合预期再扩大使用范围。

常见问题

6 条

aarrr-metrics 怎么安装?

在终端执行 npx skills add https://github.com/guia-matthieu/clawfu-skills --skill aarrr-metrics。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

aarrr-metrics 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

aarrr-metrics 需要什么权限?

权限级别是只读。该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

aarrr-metrics 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

aarrr-metrics 用的人多吗?

公开数据是累计安装 2,162 次,近一周安装 91 次,下载 757 次,GitHub 85 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

aarrr-metrics 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。
  • 第三方扫描已通过,常见的高风险行为没有命中。
  • 标注为只读权限,试用阶段不容易误改本地文件。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。
  • 只想先试试效果、不希望它改动本地文件的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
aarrr-metrics

aarrr 指标 · 本页

2,16285只读未明确通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

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:

StageQuestionFocus
AcquisitionHow do users find you?Traffic, channels
ActivationDo they have a great first experience?Onboarding, aha moment
RetentionDo they come back?Engagement, habit
RevenueDo they pay?Conversion, monetization
ReferralDo they tell others?Virality, NPS

Step 2: Set Stage-Specific Metrics

Metrics Framework:

StagePrimary MetricSupporting Metrics
AcquisitionCAC, Unique visitorsChannel mix, CTR, CPM
ActivationActivation rateTime to activate, drop-off points
RetentionD7/D30 retentionDAU/MAU, churn rate
RevenueLTV, ARPUConversion rate, ACV
ReferralViral coefficientNPS, referral rate

Step 3: Map Your Funnel

Funnel Template:

Acquisition → Activation → Retention → Revenue → Referral
   100%    →    30%     →    15%    →    5%   →    1%

Calculate conversion rates between each stage.

Step 4: Identify Bottlenecks

Bottleneck Analysis:

Drop-offDiagnosis
Acquisition → ActivationPoor onboarding or wrong traffic
Activation → RetentionNot finding core value
Retention → RevenuePricing or value misalignment
Revenue → ReferralNot delighting paying users

Step 5: Prioritize Experiments

ICE Framework:

  • Impact: How much will it move the metric?
  • Confidence: How sure are we?
  • Ease: How easy to implement?

Examples

Example 1: Complete AARRR Dashboard

Input:

Build an AARRR dashboard for a B2B SaaS product.
Monthly visitors: 50,000
Signups: 3,000
Activated users: 900
Paying customers: 150
Referrals generating signups: 45

Output:

## AARRR Dashboard: B2B SaaS

### Funnel Overview

┌──────────────────────────────────────────────────────────────┐ │ AARRR FUNNEL │ ├──────────────────────────────────────────────────────────────┤ │ │ │ ACQUISITION ACTIVATION RETENTION REVENUE REF │ │ 50,000 3,000 900 150 45 │ │ 100% 6% 30% 17% 30% │ │ │ │ ████████████ ████████ ████ ██ █ │ │ │ │ Visitors → Signups → Activated → Paid → Referral │ │ (-94%) (-70%) (-83%) (-70%) │ │ ⚠️ ⚠️ ✅ ⚠️ │ │ │ └──────────────────────────────────────────────────────────────┘

---

### Stage-by-Stage Analysis

#### 1. ACQUISITION

**Metrics:**
| Metric | Value | Benchmark | Status |
|--------|-------|-----------|--------|
| Monthly visitors | 50,000 | - | Baseline |
| Visitor → Signup | 6% | 2-5% | ✅ Good |
| CAC | $45 | <$50 | ✅ Good |
| Signups | 3,000 | - | - |

**Channel Breakdown:**
| Channel | Visitors | Signups | Conv % | CAC |
|---------|----------|---------|--------|-----|
| Organic | 20,000 | 1,500 | 7.5% | $0 |
| Paid Search | 15,000 | 900 | 6% | $60 |
| Content | 10,000 | 450 | 4.5% | $20 |
| Social | 5,000 | 150 | 3% | $80 |

**Analysis:** Acquisition is healthy. Organic performing best.
Paid social has high CAC—consider reallocating.

---

#### 2. ACTIVATION ⚠️ BOTTLENECK

**Metrics:**
| Metric | Value | Benchmark | Status |
|--------|-------|-----------|--------|
| Signup → Activated | 30% | 40-60% | ⚠️ Below |
| Time to activate | 3.2 days | <1 day | ⚠️ Slow |
| Activation rate | 900/3,000 | - | - |

**Activation Definition:**
"Activated" = Created first project + invited 1 team member

**Drop-off Analysis:**
| Step | Users | Drop-off |
|------|-------|----------|
| Signup complete | 3,000 | - |
| Email verified | 2,400 | -20% |
| Created project | 1,500 | -38% |
| Invited team | 900 | -40% ⚠️ |

**Primary Bottleneck:** "Invite team member" step losing 40%

**Experiment Ideas:**
| Experiment | Hypothesis | ICE |
|------------|------------|-----|
| Skip team invite in onboarding | Removes friction, activate solo first | 8/8/9 = 8.3 |
| In-app invite prompt (day 2) | Right timing, after value seen | 7/7/8 = 7.3 |
| Email team invite reminder | Low effort, catches drop-offs | 5/6/9 = 6.7 |

---

#### 3. RETENTION

**Metrics:**
| Metric | Value | Benchmark | Status |
|--------|-------|-----------|--------|
| Week 1 retention | 65% | 60%+ | ✅ Good |
| Month 1 retention | 45% | 40%+ | ✅ Good |
| DAU/MAU ratio | 28% | 20%+ | ✅ Good |
| Churn rate | 5%/month | <5% | ✅ OK |

**Retention Curve:**

Day 1: 100% ████████████████████ Day 7: 65% █████████████ Day 14: 52% ██████████ Day 30: 45% █████████ Day 60: 38% ████████ Day 90: 32% ██████

**Analysis:** Retention is solid. Users who activate tend to stick.
This confirms activation is the primary bottleneck.

---

#### 4. REVENUE

**Metrics:**
| Metric | Value | Benchmark | Status |
|--------|-------|-----------|--------|
| Activated → Paid | 17% | 5-15% | ✅ Strong |
| Trial → Paid | 17% | 10-25% | ✅ Good |
| ARPU | $89/mo | - | Baseline |
| LTV | $1,068 | - | 12mo × ARPU |
| LTV:CAC | 24:1 | >3:1 | ✅ Excellent |

**Revenue Breakdown:**
| Plan | Customers | % | MRR |
|------|-----------|---|-----|
| Starter ($29) | 60 | 40% | $1,740 |
| Pro ($89) | 75 | 50% | $6,675 |
| Enterprise ($249) | 15 | 10% | $3,735 |
| **Total** | **150** | - | **$12,150** |

**Analysis:** Strong conversion and healthy LTV:CAC.
Not a bottleneck—maintain current approach.

---

#### 5. REFERRAL ⚠️ OPPORTUNITY

**Metrics:**
| Metric | Value | Benchmark | Status |
|--------|-------|-----------|--------|
| Referral rate | 30% | 20%+ | ✅ Good |
| Viral coefficient | 0.45 | >1 = viral | ⚠️ Below |
| NPS | +32 | >30 | ✅ Good |
| Referral signups | 45 | - | - |

**Calculation:**
- 150 paying customers
- 30% refer (45 referrals)
- Each referral generates 1 signup
- Viral coefficient = 45/150 × (6% activation) = 0.018
- Not organic virality, but healthy referral base

**Experiment Ideas:**
| Experiment | Hypothesis | ICE |
|------------|------------|-----|
| Referral incentive (2-way) | Motivation for both parties | 7/8/7 = 7.3 |
| In-app share prompts | Right moment capture | 6/7/8 = 7.0 |
| Case study program | Social proof + referral | 5/6/6 = 5.7 |

---

### Priority Recommendations

| Priority | Focus | Current | Target | Impact |
|----------|-------|---------|--------|--------|
| 1 | Activation | 30% | 45% | +450 activated/mo |
| 2 | Referral | 30% | 50% | +30 referral signups |
| 3 | Paid channel mix | 6% conv | 8% conv | -$10 CAC |

**90-Day Goal:**
If activation improves 30% → 45%:
- +450 more activated users
- At 17% conversion = +76 new customers
- At $89 ARPU = +$6,800 MRR

---

### Dashboard Template

┌────────────────────────────────────────────────────────────┐ │ AARRR MONTHLY DASHBOARD January 2026 │ ├────────────────────────────────────────────────────────────┤ │ │ │ ACQUISITION ACTIVATION RETENTION │ │ Visitors: 50K Activated: 900 D30: 45% │ │ Signups: 3K Rate: 30% ⚠️ Churn: 5% │ │ CAC: $45 Time: 3.2d DAU/MAU: 28% │ │ │ │ REVENUE REFERRAL OVERALL │ │ Customers: 150 Referrals: 45 MRR: $12.2K │ │ Conv: 17% Rate: 30% LTV:CAC: 24:1 │ │ ARPU: $89 NPS: +32 Health: 🟢 │ │ │ │ BOTTLENECK: Activation (30% vs 45% target) │ │ EXPERIMENT: Skip team invite onboarding │ │ │ └────────────────────────────────────────────────────────────┘

Example 2: Quick Bottleneck Diagnosis

Input:

Diagnose this funnel:
- 100K visitors, 5K signups (5%)
- 4K activated (80%)
- 1K retained at D30 (25%)
- 200 paid (20%)

Output:

## Quick AARRR Diagnosis

### Funnel

| Stage | Users | Conv | Benchmark | Status |
|-------|-------|------|-----------|--------|
| Acquisition | 100K → 5K | 5% | 2-5% | ✅ Good |
| Activation | 5K → 4K | 80% | 40-60% | ✅ Excellent |
| Retention | 4K → 1K | 25% | 40%+ | ❌ Problem |
| Revenue | 1K → 200 | 20% | 5-15% | ✅ Strong |

### Bottleneck: RETENTION

**Problem:** Only 25% retained at D30 (should be 40%+)

**What this means:**
- Great at attracting and activating
- Users try it, find value initially
- But don't form a habit / come back
- Losing 3,000 activated users monthly

**Likely Causes:**
1. Single-use case (solved problem, left)
2. Not enough ongoing value
3. Poor re-engagement
4. Competitor switching

**Recommended Experiments:**
1. User interviews with churned users
2. Email re-engagement sequence
3. Weekly value summary email
4. Add recurring use case

**Impact if fixed:**
If retention → 40%: 1,600 retained → 320 paid
That's +120 customers/month (+60%)

Skill Boundaries

What This Skill Does Well

  • Structuring growth metrics
  • Identifying funnel bottlenecks
  • Prioritizing experiments
  • Creating dashboards

What This Skill Cannot Do

  • Access your actual data
  • Know your specific definitions
  • Run experiments
  • Guarantee results

Iteration Guide

Follow-up Prompts:

  • "Design activation experiments for [problem]"
  • "What metrics matter for [stage]?"
  • "Create a retention analysis framework"
  • "How do we improve [specific conversion]?"

References

  • Dave McClure - Pirate Metrics (500 Startups)
  • Reforge Growth Series
  • Amplitude Product Analytics
  • Mixpanel Growth Framework

Related Skills

  • product-led-growth - PLG motions
  • growth-loops - Sustainable growth
  • startup-metrics - Investor metrics

Skill Metadata

  • Domain: Growth
  • Complexity: Intermediate
  • Mode: cyborg
  • Time to Value: 2-3 hours for full setup
  • Prerequisites: Analytics access, metric definitions

平台分布

Codex

39.72%
按下载量换算301

Claude

28.82%
按下载量换算218

Cursor

18.19%
按下载量换算138

Gemini CLI

10.13%
按下载量换算77

安全审计

Gen Agent Trust Hub

通过

Socket

通过

Snyk

通过

权限和风险

只读

该 Skill 主要提供规则、说明或参考内容,本身偏只读;真正读写文件、联网或执行命令仍取决于宿主 Agent 的任务。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills