Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add konglong87/superPM --skill pm-aarrrgit clone --depth 1 https://github.com/konglong87/superPMWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/konglong87/superpm/pm-aarrr)<a href="https://agentmods.dev/skills/konglong87/superpm/pm-aarrr"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-aarrr/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/konglong87/superpm/pm-aarrr"><img src="https://agentmods.dev/badge/skills/konglong87/superpm/pm-aarrr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00053 | $0.06375 |
| Opus 5 | $0.00026 | $0.03188 |
| Sonnet 5 | $0.00011 | $0.01275 |
| Haiku 4.5 | $0.00005 | $0.00637 |
Grade A, and why
pm-aarrr scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 798 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preamble (run first)
bash "$(dirname "${BASH_SOURCE[0]}")/../../check-update.sh" 2>/dev/null || true
# 创建增长迭代目录
mkdir -p docs/03-增长迭代
# 检查数据指标文档
echo "📊 正在检查数据指标体系..."
if [ -f "docs/02-方案设计/数据指标体系.md" ]; then
echo "✅ 数据指标体系 - 已找到"
else
echo "⏳ 数据指标体系 - 未找到"
fi
echo ""
echo "🎯 AARRR模型介绍:"
echo "A - Acquisition (获取用户)"
echo "A - Activation (激活用户)"
echo "R - Retention (提高留存)"
echo "R - Revenue (增加收入)"
echo "R - Referral (自传播)"
跨 Agent 交互规则
当流程要求与用户交互时:
- 如果当前环境支持 AskUserQuestion,使用 AskUserQuestion(最佳体验)。
- 如果当前环境不支持 AskUserQuestion,必须用普通聊天消息提出同样问题。
- 一次只问一个问题。
- 提问后必须停止当前回合,等待用户回答(STOP and WAIT)。
- 不得在用户回答前生成文档、写入 docs。
- 已有 docs 文件不能替代本轮用户回答。
执行流程
步骤 1: 选择分析重点(主 agent - 用户交互)
使用 AskUserQuestion 询问:
🎯 AARRR增长分析 - 选择分析重点
AARRR模型覆盖用户生命周期的5个环节。请选择您重点关注的环节:
A) 全面分析(分析所有5个环节,并行执行,推荐) B) 获取分析(Acquisition - 用户从哪里来) C) 激活分析(Activation - 用户首次体验是否良好) D) 留存分析(Retention - 用户是否持续使用) E) 变现分析(Revenue - 如何赚钱) F) 传播分析(Referral - 用户是否愿意推荐) G) 瓶颈诊断(找到当前最大的增长瓶颈)
💡 提示:
- 选择"A"可并行分析所有环节,效率提升 5x
- 产品初期 → 关注获取和激活
- 产品成长期 → 关注留存和变现
- 产品成熟期 → 关注变现和传播
用户选择后,记录到变量 AARRR_FOCUS
步骤 2: 收集数据(主 agent)
2.1 读取现有数据指标
尝试读取 docs/02-方案设计/数据指标体系.md
如果不存在,提示用户:
- A) 先执行 /pm-data 建立数据指标体系
- B) 手动输入当前的关键指标数据
- C) 使用行业基准数据进行分析
2.2 构建数据输入
使用 AskUserQuestion 收集关键数据:
📊 数据收集
请提供以下关键指标(如不确定可输入"未知"):
Acquisition (获取用户):
- 新增用户数(近7天):
- 主要渠道:
- 渠道转化率:
Activation (激活用户):
- 注册转化率:
- 首次关键行为完成率:
Retention (留存):
- 次日留存率:
- 7日留存率:
- 30日留存率:
Revenue (变现):
- 付费转化率:
- ARPU (平均每用户收入):
- LTV (用户生命周期价值):
Referral (传播):
- 邀请率:
- K因子 (病毒系数):
将所有数据整理为结构化 JSON,准备传递给 subagent。
步骤 3: 并行派发 subagent 分析(核心优化)
优化说明:
- 主 agent 一次性派发 5 个 subagent
- 每个 subagent 负责 1 个 AARRR 环节的分析
- 分析细节不占用主 agent 上下文
- 所有环节并行执行
3.1 构建 subagent 任务清单
如果用户选择"全面分析":
准备 5 个并行 subagent 任务:
[
{
"task_id": "acquisition_analysis",
"stage": "Acquisition",
"focus": "用户获取渠道、成本、效率",
"input_data": {
"新增用户数": "1000",
"主要渠道": ["搜索", "社交媒体", "推荐"],
"渠道转化率": "5%",
"CAC": "50元"
}
},
{
"task_id": "activation_analysis",
"stage": "Activation",
"focus": "用户首次体验、核心功能触达",
"input_data": {
"注册转化率": "40%",
"首次关键行为完成率": "30%",
"onboarding完成率": "60%"
}
},
{
"task_id": "retention_analysis",
"stage": "Retention",
"focus": "用户留存、活跃度、召回",
"input_data": {
"次日留存率": "40%",
"7日留存率": "20%",
"30日留存率": "10%"
}
},
{
"task_id": "revenue_analysis",
"stage": "Revenue",
"focus": "变现能力、付费转化、收入增长",
"input_data": {
"付费转化率": "5%",
"ARPU": "20元",
"LTV": "200元"
}
},
{
"task_id": "referral_analysis",
"stage": "Referral",
"focus": "用户传播、病毒系数、推荐机制",
"input_data": {
"邀请率": "10%",
"K因子": "0.8"
}
}
]
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 798 lines · 53 tokens per session scan A 961ec6d4ea93
pm-aarrr is a skill published in the GitHub repository konglong87/superPM (64 stars, last pushed 5d ago), licensed MIT. It adds 53 tokens to every session and 6,375 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
multi-search
A web-search helper that chooses among DuckDuckGo, Tavily, Bing API, and Bing scraping based on the available network.
freeride
Manages free AI models from OpenRouter for OpenClaw. Automatically ranks models by quality, configures fallbacks for rate-limit handling, and updates openclaw.json. Use when the user mentions free AI, OpenRouter, model switching, rate limits, or wants to reduce AI costs.
deepsafe-scan
Preflight security scanner for AI coding agents — scans deployment config, skills/MCP servers, memory/sessions, and AI agent config files (hooks injection) for secrets, PII, prompt injection, and dangerous patterns. Runs 4 model behavior probes (persuasion, sandbagging, deception, hallucination). Supports LLM-enhanced…
mapick
Mapick — Skill recommendation & privacy protection for OpenClaw. Scans your local skills, suggests what you're missing, and keeps other skills from seeing your sensitive data.
douyin-upload-mcp-skill
A guide for publishing videos and image-and-text posts through Douyin's creator website. Douyin is a Chinese social-media platform, and the guide uses its creator platform and available MCP tools.
team-tasks
Coordinate multi-agent development pipelines using shared JSON task files. Use when dispatching work across dev team agents (code-agent, test-agent, docs-agent, monitor-bot), tracking pipeline progress, or running sequential/parallel workflows. Covers project init, task assignment, status tracking, agent dispatch via…