复制安装命令
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
GitHub stars License: CC BY-NC-SA 4.0 PRs Welcome Version Claude Code Plugin Skills
用 Codex 或 Claude 安装复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它先审查 Skill 页面再帮你安装。
复制前请先查看来源、License 和安全提示。
来源文件:README.md
╔════════════════════════════════════════════════════════════════════╗
║ ║
║ ██████╗ ███╗ ███╗ ███████╗██╗ ██╗██╗██╗ ██╗ ███████╗
║ ██╔══██╗████╗ ████║ ██╔════╝██║ ██╔╝██║██║ ██║ ██╔════╝
║ ██████╔╝██╔████╔██║ ███████╗█████╔╝ ██║██║ ██║ ███████╗
║ ██╔═══╝ ██║╚██╔╝██║ ╚════██║██╔═██╗ ██║██║ ██║ ╚════██║
║ ██║ ██║ ╚═╝ ██║ ███████║██║ ██╗██║███████╗███████╗███████║
║ ╚═╝ ╚═╝ ╚═╝ ╚══════╝╚═╝ ╚═╝╚═╝╚══════╝╚══════╝╚══════╝
║ ║
║ 70 battle-tested skills + 6 command workflows ║
║ Claude Code • Cursor • Codex • n8n • OpenClaw • and more ... ║
║ ║
║ v0.83 • July 17, 2026 • CC BY-NC-SA 4.0 ║
╚════════════════════════════════════════════════════════════════════╝
70 battle-tested PM frameworks, ready for Claude, Codex, ChatGPT, and any agent that can read structured knowledge.
Generic AI output is a PM's worst enemy. When you tell your agent "write a PRD" without shared context, you get a generic document that no stakeholder trusts and no engineer can act on.
This library gives both you and your AI agent the same professional foundation: the why behind each framework, the failure modes to avoid, and the judgment to apply them correctly. You stop repeating yourself. Your agent stops guessing. The work gets better.
The goal is dual — functional and pedagogic in equal measure. Skills equip agents to do PM work at a professional level, and they teach the human PM the reasoning behind each framework — so you can explain it, adapt it, and pass it on. Neither is a byproduct of the other.
Navigate by what you're actually trying to accomplish:
Framing and strategy
Stakeholder alignment
Customer discovery and research
Prioritization and roadmapping
Writing PM deliverables
Validation and experimentation
Finance and growth
Market and competitive intelligence
Career and leadership transitions
AI product work
Choose your setup:
| I use... | Get this | Notes |
|---|---|---|
| Claude Desktop or Claude Web | pm-skills-starter-pack.zip | Unzip, then upload the individual skill ZIPs to Claude Skills |
| Claude Code | Plugin marketplace | claude /plugin marketplace add deanpeters/Product-Manager-Skills |
| Codex | pm-skills-codex.zip | Installs .agents/skills and AGENTS.md |
| Not sure | pm-skills-starter-pack.zip | Start here |
All downloads: GitHub Releases
Each pack below is a ZIP of upload-ready skill ZIPs — unzip, then upload individuals to Claude Skills:
| Pack | Download | What's inside |
|---|---|---|
| Starter | pm-skills-starter-pack.zip | Core skills across all categories |
| Discovery | 02-discovery-pack.zip | Research, interviewing, synthesis |
| Strategy | 03-strategy-pack.zip | Positioning, roadmapping, prioritization |
| Delivery | 04-delivery-pack.zip | PRDs, stories, epics |
| AI PM | 05-ai-pm-pack.zip | Context engineering, orchestration, readiness |
| Market Intel | 06-market-intel-pack.zip | The full Market Intelligence Suite: disciplines, investigation chain, frameworks, monitors |
| All skills | 99-all-skills-pack.zip | All 70 skills |
Not ready to wire skills into your agent setup? Run the local playground first and kick the tires in your browser.
pip install -r app/requirements.txt
streamlit run app/main.py
What you can do:
Multi-provider support: Anthropic, OpenAI, Ollama. API keys via environment variables only (no in-app key entry).
Docs: app/STREAMLIT_INTERFACE.md · app/.env.example
Feedback welcome via GitHub Issues or LinkedIn.
Skills are organized in three tiers that build on each other:
┌────────────────────────────────────────────────────────┐
│ WORKFLOW SKILLS (19) │
│ Complete end-to-end PM processes (days to weeks) │
│ Example: run a full discovery cycle or write a PRD │
└────────────────────────────────────────────────────────┘
↓ orchestrates
┌────────────────────────────────────────────────────────┐
│ INTERACTIVE SKILLS (27) │
│ Guided discovery — 3-5 questions, then recommendations│
│ Example: "Which prioritization framework fits here?" │
└────────────────────────────────────────────────────────┘
↓ uses
┌────────────────────────────────────────────────────────┐
│ COMPONENT SKILLS (24) │
│ Templates for specific PM deliverables (30-90 min) │
│ Example: write a user story with acceptance criteria │
└────────────────────────────────────────────────────────┘
Interactive skills use an Adaptive Decision Ladder. Instead of dumping a framework at you, an interactive skill asks 3-5 targeted questions about your specific context, then offers numbered recommendations — each with a clear "use this when" rationale. You pick a path. The skill executes it and explains the why as it goes. If you want to just learn the framework without doing the work, you can ask that too — the skill coaches you either way. This is ABC — Always Be Coaching — in practice.
Full catalog: catalog/INDEX.md — all 70 skills with descriptions, or browse skills/ directly.
Every SKILL.md follows the same structure:
| Section | What it contains |
|---|---|
| Frontmatter | name, description, type, intent, best_for, scenarios |
| Purpose | What this skill does and when to reach for it |
| Input | What you can bring (with example invocations) — inline input is used, not re-asked, and arriving empty-handed is fine: the skill walks you through it |
| Key Concepts | Frameworks, definitions, anti-patterns — with vocabulary explained |
| Application | Step-by-step instructions an agent (or human) can follow |
| Examples | Real-world cases showing both good and bad versions |
| Common Pitfalls | Named failure modes with consequences and corrections |
| References | Related skills and external frameworks |
The best_for frontmatter field lists 3-5 specific scenarios where the skill is most useful — helpful for quickly scanning whether a skill fits your situation.
Why no $ARGUMENTS templating? Other skill libraries use Claude Code's $ARGUMENTS substitution for input. We deliberately don't: it only expands in Claude Code (it renders as literal syntax in Claude Desktop/Web, Codex, and the Streamlit playground), and it teaches the human reader nothing. Instead, every skill has a plain-language ## Input section that works on every runtime — and makes clear you can show up with full context, partial context, or nothing at all and be guided through the rest. Full rationale in CONTRIBUTING.md.
Claude Code · Claude Desktop · Claude Web · OpenAI Codex · ChatGPT · Cursor · Windsurf · n8n · LangFlow · CrewAI · Gemini · any agent that reads structured markdown
See docs/Platform Guides for PMs.md for platform-specific setup.
| Document | Purpose |
|---|---|
| Using PM Skills 101 | Beginner-friendly orientation — setup without technical overload |
| Platform Guides for PMs | Tool-by-tool setup chooser for every supported platform |
| Using PM Skills with Claude | Claude Code + GitHub ZIP upload for Claude Desktop/Web |
| Using PM Skills with Codex | Local workspace + GitHub-connected Codex on ChatGPT |
| Using PM Skills with ChatGPT | GitHub app, Custom GPT Knowledge, and Project-based usage |
| Using PM Skills with Slash Commands 101 | Turn skills into reusable slash commands like /pm-story |
| Add-a-Skill Utility Guide | End-to-end guide for generating and validating new skills |
| Market Intelligence Suite Summary | The 14-skill competitive/market research suite: disciplines, chain, and which skill to run when |
| Building PM Skills | How raw PM content gets distilled into agent-ready skills |
| START_HERE.md | 60-second onboarding for local repo users |
v0.83 — July 17, 2026 · The Market Intelligence Suite
autonomous-investigation — the protocol for research that proceeds without you. Question budgets, a search-plan gate, Fact / Inference / Assumption labels on every claim, do-not-invent lists, and stable diffable schemas, so investigations can run on a schedule and you can diff this quarter against lasttam-sam-som-calculator (three entry modes, including autonomous bottom-up research) and company-intel (Executive Signal Refresh rerun pattern — Then/Now diffs and Dropped Language: what leaders stop saying is often the strongest signal)v0.82 — July 8, 2026
incoming-request-advisor (Interactive) — drop in a Slack ping, email, mandate, or escalation and get a structured breakdown that separates the literal ask from the real job-to-be-done, reads sender power and stake, and points you toward a reply. Ships with a copy/paste template so you can run it by hand too/dist — no terminal, no Releases tab. Read the plain-language README, scan the CATALOG, and download any skill or pack straight from the repo. Built for PMs who just want the skillsv0.81 — July 4, 2026
## Input section: what to bring, what happens to context you supply up front (it's used, not re-asked), and reassurance that arriving empty-handed is fine — the guided flow covers the restargument-hint autocomplete for Claude Code users; deliberately no $ARGUMENTS templating — it breaks on every other runtime and teaches the reader nothing (why)$ARGUMENTS in the bodyagent-orchestration-advisor (Interactive) — the multi-agent workflow design skill was referenced everywhere but only existed on an orphaned commit; recovered from git history and brought up to current standardsv0.80 — June 19, 2026
stakeholder-identification (Component) — comprehensive stakeholder brainstorm using allies/audiences/influencers, R/P/D marking, equity lens, and bias check; narrows to priority targetsstakeholder-mapping (Component) — two complementary grids (Power × Interest + Impact × Power); comparing outputs reveals who you're under-engaging relative to how much the product affects themstakeholder-engagement-advisor (Interactive) — per-stakeholder engagement planning via Adaptive Decision Ladder: three questions on profile, power/impact, and context deliver tailored message framing, medium, cadence, and a named next actionAll three adapted from the MITRE Innovation Toolkit via the companion repo MITRE ITK Skills — worth a bookmark if you work in discovery, facilitation, or cross-functional product strategy.
v0.79 — May 15, 2026
organic-growth-advisor — McKinsey Growth Pyramid triage for new segments, geographies, channels, or productspm-skill-creator — interactive skill for designing repo-compliant skills via guided conversation.claude-plugin/plugin.json that silently blocked Claude Code skill discoveryPM_MAX_INPUT) and path traversal protection to helper scriptsFound a gap? Have a PM framework worth formalizing? The bar is pedagogic — skills must teach the why, not just the how.
See CONTRIBUTING.md for guidelines, or open an issue to start a conversation.
CC BY-NC-SA 4.0 — non-commercial use with share-alike.
Everything in this repository — every skill, template, and doc — is licensed CC BY-NC-SA 4.0. There is no mix of licenses here.
Some skills note in their Provenance sections that they were adapted from product-manager-prompts, Dean's earlier prompt library. That repo has the same author, so there is no license conflict: a license grants permissions to other people, and a copyright holder is free to adapt and relicense their own work. Those Provenance lines are lineage — a breadcrumb back to where an idea started — not a license dependency. No third-party MIT-licensed text is incorporated anywhere in this library.
In plain terms:
The companion prompt library, product-manager-prompts, carries the same CC BY-NC-SA 4.0 license as of its v2.3.0, with its own plain-language permissions (stricter on commercial use) — see its LICENSING.md, which governs that repo.
name: saas-revenue-growth-metrics
argument-hint: "[metrics or question]"
description: Calculate SaaS revenue, retention, and growth metrics. Use when diagnosing momentum, churn, expansion, or product-market-fit signals.
intent: >-
Master revenue and retention metrics to understand SaaS business momentum, evaluate product-market fit, and make data-driven decisions about growth investments. Use this to calculate key metrics, interpret trends, identify problems early, and communicate business health to stakeholders.
type: component
theme: finance-metrics
best_for:
- "Understanding your key revenue and retention metrics"
- "Calculating MRR, ARR, churn, and NRR correctly"
- "Building a metrics dashboard for your SaaS product"
scenarios:
- "I need to calculate and interpret our MRR, churn rate, and NRR for a board deck"
- "Help me understand the difference between gross and net revenue retention and how to improve it"
estimated_time: "10-15 min"Master revenue and retention metrics to understand SaaS business momentum, evaluate product-market fit, and make data-driven decisions about growth investments. Use this to calculate key metrics, interpret trends, identify problems early, and communicate business health to stakeholders.
This is not a business intelligence tool—it's a framework for PMs to understand which metrics matter, how to calculate them correctly, and what actions to take based on the numbers.
Works best with: The question you're answering (is growth healthy? is churn a fire?) or the metrics you want interpreted. Also useful: Your numbers — MRR/ARR, growth rate, GRR/NRR, expansion, cohort data — partial data is workable.
Anything supplied with the invocation itself — text after the skill name, a pasted context dump, or an appended ARGUMENTS: line — counts as answers already given. Use it and skip whatever it covers; don't re-ask.
Arriving empty-handed? That works too. Use it as a reference: read the metric sections relevant to your diagnosis.
Example invocation: Interpret these: $4M ARR, 8% MoM growth, GRR 88%, NRR 103% — is the growth masking a churn problem?
The "top-line" metrics that measure how much money the business generates.
Revenue — Total money earned from selling products/services before expenses. The "top line" of the income statement.
ARPU (Average Revenue Per User) — Average revenue generated per individual user.
Total Revenue / Total UsersARPA (Average Revenue Per Account) — Average revenue generated per customer account.
MRR / Active AccountsARPA/ARPU Analysis — Using both metrics together to understand monetization.
ACV (Annual Contract Value) — Annualized recurring revenue per contract (excludes one-time fees).
Annual Recurring Revenue per Contract (don't include setup fees, professional services)MRR/ARR (Monthly/Annual Recurring Revenue) — Predictable recurring revenue normalized to monthly or annual.
MRR = Sum of all recurring subscription revenue per month; ARR = MRR × 12Gross vs. Net Revenue — Gross revenue before vs. net revenue after discounts, refunds, credits.
Net Revenue = Gross Revenue - Discounts - Refunds - CreditsMetrics that measure how well you keep and grow existing customers.
Churn Rate — Percentage of customers who cancel in a period.
Customers Lost in Period / Starting CustomersNRR (Net Revenue Retention) — Revenue retention from existing customers including expansion and contraction.
(Starting ARR + Expansion - Churn - Contraction) / Starting ARR × 100Expansion Revenue — Additional revenue from existing customers (upsells, cross-sells, usage growth).
Sum of upsells + cross-sells + usage increases from existing customersQuick Ratio (SaaS) — Revenue gains vs. revenue losses.
(New MRR + Expansion MRR) / (Churned MRR + Contraction MRR)Revenue Mix Analysis — Breakdown of revenue by product, segment, or channel.
Product/Segment Revenue / Total Revenue × 100Cohort Analysis — Group customers by join date and track behavior over time.
Use these when:
Don't use these when:
Use the templates in template.md to calculate your core revenue metrics.
Revenue = Sum of all customer payments in period
Example:
Quality checks:
ARPU = Total Revenue / Total Users
Example:
Quality checks:
ARPA = MRR / Active Accounts
Example:
Quality checks:
ARPA = MRR / Active Accounts
ARPU = MRR / Total Users
Average Seats per Account = ARPA / ARPU
Example:
Quality checks:
ACV = Annual Recurring Revenue per Contract
(Exclude one-time fees like setup, professional services)
Example:
Quality checks:
MRR = Sum of all recurring monthly subscriptions
ARR = MRR × 12
Track components:
- New MRR (from new customers)
- Expansion MRR (from upsells/cross-sells)
- Churned MRR (from lost customers)
- Contraction MRR (from downgrades)
Example:
Quality checks:
Net Revenue = Gross Revenue - Discounts - Refunds - Credits
Example:
Quality checks:
Logo Churn Rate = Customers Lost / Starting Customers × 100
Revenue Churn Rate = MRR Lost / Starting MRR × 100
Example (Logo Churn):
Example (Revenue Churn):
Quality checks:
Convert monthly to annual:
Annual Churn = 1 - (1 - Monthly Churn)^12NRR = (Starting ARR + Expansion - Churn - Contraction) / Starting ARR × 100
Example:
Quality checks:
Expansion Revenue = Upsells + Cross-sells + Usage Growth (from existing customers)
Example:
Quality checks:
Quick Ratio = (New MRR + Expansion MRR) / (Churned MRR + Contraction MRR)
Example:
Quality checks:
Product/Segment % = Product/Segment Revenue / Total Revenue × 100
Example:
Quality checks:
Group customers by when they joined and track metrics over time.
Example:
| Cohort | Month 0 | Month 1 | Month 2 | Month 3 | Month 6 |
|---|---|---|---|---|---|
| Jan 2024 | 100% | 95% | 92% | 90% | 85% |
| Feb 2024 | 100% | 94% | 90% | 87% | 80% |
| Mar 2024 | 100% | 92% | 86% | 82% | - |
Quality checks:
Before reporting metrics, validate:
Revenue metrics:
Retention metrics:
Analysis:
See examples/ folder for detailed scenarios. Mini examples below:
Company: Mid-market project management SaaS
Revenue Metrics:
Retention Metrics:
Analysis:
Action: Scale acquisition. Unit economics are strong.
Company: SMB marketing automation SaaS
Revenue Metrics:
Retention Metrics:
Cohort Analysis:
| Cohort | Month 6 Retention |
|---|---|
| 6 months ago | 75% |
| 3 months ago | 65% |
| Current | 58% |
Analysis:
Action: STOP scaling acquisition. Fix retention first. Investigate:
Company: Multi-product SaaS platform
Blended Metrics Look Great:
But Revenue Mix Analysis Shows:
| Product | Revenue | % of Total | Growth | Churn | NRR |
|---|---|---|---|---|---|
| Legacy Product | $2M | 67% | -5% MoM | 8% | 75% |
| New Product | $1M | 33% | +80% MoM | 1% | 150% |
Analysis:
Action: Accelerate migration from legacy to new product. Plan for legacy product sunset.
Symptom: "We grew revenue 50% this year, we're crushing it!"
Consequence: Revenue is the top line, not bottom line. You might be growing at a loss, destroying margins, or scaling unprofitable products.
Fix: Always pair revenue metrics with margin metrics (see saas-economics-efficiency-metrics). $1M revenue at 80% margin >> $2M revenue at 20% margin.
Symptom: "ARPU increased 30%!" (but customer count dropped 40%)
Consequence: ARPU rose because you lost all your small customers, not because you improved monetization.
Fix: Analyze ARPU by cohort and segment. True ARPU improvement = same customers paying more, not losing cheap customers.
Symptom: "Blended churn is stable at 3%"
Consequence: Blended metrics can hide that new cohorts churn at 6% while old cohorts churn at 1%. Product-market fit is degrading.
Fix: Always analyze retention by cohort. If newer cohorts perform worse, stop scaling and fix the product.
Symptom: "Logo churn is only 2%, we're great!"
Consequence: You might be losing 2% of customers but 10% of revenue if you're churning large customers.
Fix: Track both logo churn AND revenue churn. If revenue churn > logo churn, you're losing high-value customers.
Symptom: "We lost 50 customers this month" (no context on who)
Consequence: Losing 50 small customers ($10/month) is different from losing 50 enterprise customers ($10K/month).
Fix: Segment churn analysis by customer size, cohort, and reason. Weight by revenue impact, not just logo count.
Symptom: "3% monthly churn is fine, that's only 36% annually"
Consequence: Churn compounds. 3% monthly = 31% annual churn, not 36%. Math: 1 - (1 - 0.03)^12 = 31%.
Fix: Use the correct formula when converting monthly to annual churn. Don't just multiply by 12.
Symptom: "Gross revenue is up 20%!" (but discounts/refunds doubled)
Consequence: Net revenue might be flat or shrinking. Discounts hide pricing power problems; refunds hide product quality issues.
Fix: Always track gross AND net revenue. If discounts >20% or refunds >10%, investigate why.
Symptom: "NRR is 105%, we're expanding!"
Consequence: NRR can be >100% just from very low churn, without meaningful expansion. True expansion-driven NRR is >120%.
Fix: Break down NRR into components: expansion MRR vs. churned/contracted MRR. Aim for expansion-driven NRR, not just low churn.
Symptom: "We're at $10M ARR!" (but $5M is from one customer)
Consequence: Losing that one customer cuts revenue in half. Roadmap becomes hostage to one customer's requests.
Fix: Track revenue concentration. Ideal: Top customer <10% of revenue, Top 10 customers <40%. Diversify early.
Symptom: "Our ARPU is $100" (average of $10 SMB and $1,000 enterprise)
Consequence: Blended ARPU hides segment economics. Can't make smart acquisition or product decisions.
Fix: Calculate ARPU/ARPA by segment (SMB, mid-market, enterprise). Optimize each segment independently.
saas-economics-efficiency-metrics — Unit economics (CAC, LTV, margins, burn rate)finance-metrics-quickref — Fast lookup for all metricsfeature-investment-advisor — Uses revenue metrics to evaluate feature ROIfinance-based-pricing-advisor — Uses ARPU/ARPA to evaluate pricing changesbusiness-health-diagnostic — Uses revenue/retention metrics to diagnose business healthresearch/finance/Finance for Product Managers.mdresearch/finance/Finance_QuickRef.mdresearch/finance/Finance_Metrics_Additions_Reference.md
评论 (0)
暂无评论,成为第一个评论者吧!