PM Skills Marketplace: The AI Operating System for Better Product Decisions
69 PM skills and 42 chained workflows across 9 plugins. Claude Code, Cowork, and more. From discovery to strategy, execution, launch, growth, and shipping AI-built code.
Designed for Claude Code and Cowork. Skills compatible with other AI assistants.
Start Here
New idea? → /discover
Need strategic clarity? → /strategy
Writing a PRD? → /write-prd
Planning a launch? → /plan-launch
Defining metrics? → /north-star
If this project helps you, ⭐ the repo.
Why PM Skills Marketplace?
Generic AI gives you text. PM Skills Marketplace gives you structure.
Each skill encodes a proven PM framework — discovery, assumption mapping, prioritization, strategy — and walks you through it step by step. You get the rigor of Teresa Torres, Marty Cagan, and Alberto Savoia built into your daily workflow, not sitting on a bookshelf.
The result: better product decisions, not just faster documents.
How It Works (Skills, Commands, Plugins)
Skills are the building blocks of the marketplace. Each skill gives Claude domain knowledge, analytical frameworks, or a guided workflow for a specific PM task. Some skills also work as reusable foundations that multiple commands share.
Skills are loaded automatically when relevant to the conversation — no explicit invocation needed. If needed (e.g., prioritizing skills over general knowledge), you can force loading skills with /plugin-name:skill-name or /skill-name (Claude will add the prefix).
Commands are user-triggered workflows invoked with /command-name. They chain one or more skills into an end-to-end process. For example, /discover chains four skills together: brainstorm-ideas → identify-assumptions → prioritize-assumptions → brainstorm-experiments.
Plugins group related skills and commands into installable packages. Each plugin covers a PM domain — discovery, strategy, execution, and so on. Installing the marketplace gives you all 9 plugins at once.
Commands use skills. Some skills serve multiple commands. Some skills (like prioritization-frameworks or opportunity-solution-tree) are standalone references that Claude draws on whenever relevant — no command needed.
Commands are designed to flow into each other, matching the PM workflow. After any command completes, it suggests relevant next commands — just follow the prompts.
Installation
Claude Cowork (recommended for non-developers)
- Open Customize (bottom-left)
- Go to Browse plugins → Personal → +
- Select Add marketplace from GitHub
- Enter:
phuryn/pm-skills
All 9 plugins install automatically. You get both commands (/discover, /strategy, etc.) and skills.
Claude Code (CLI)
# Step 1: Add the marketplace claude plugin marketplace add phuryn/pm-skills # Step 2: Install individual plugins claude plugin install pm-toolkit@pm-skills claude plugin install pm-product-strategy@pm-skills claude plugin install pm-product-discovery@pm-skills claude plugin install pm-market-research@pm-skills claude plugin install pm-data-analytics@pm-skills claude plugin install pm-marketing-growth@pm-skills claude plugin install pm-go-to-market@pm-skills claude plugin install pm-execution@pm-skills claude plugin install pm-ai-shipping@pm-skills
Codex CLI (OpenAI)
Codex reads the same plugin marketplace file as Claude Code, so you can install PM Skills natively — no conversion or file-copying needed:
# Step 1: Add the marketplace codex plugin marketplace add phuryn/pm-skills # Step 2: Install the plugins you want codex plugin add pm-toolkit@pm-skills codex plugin add pm-product-strategy@pm-skills codex plugin add pm-product-discovery@pm-skills codex plugin add pm-market-research@pm-skills codex plugin add pm-data-analytics@pm-skills codex plugin add pm-marketing-growth@pm-skills codex plugin add pm-go-to-market@pm-skills codex plugin add pm-execution@pm-skills codex plugin add pm-ai-shipping@pm-skills
What you get: every skill (the PM frameworks), available to Codex and invocable by name. Install whole plugins rather than cherry-picking individual skills — a workflow usually relies on several skills that ship together.
What's different from Claude Code: the /slash commands (/discover, /write-prd, …) install but don't run as Codex slash commands — Codex plugins don't expose commands. To run a workflow, just describe the steps in plain language, for example:
Run product discovery on [your idea]: brainstorm options, map assumptions, prioritize the risky ones, then design experiments — pause between each step.
Optional — let Codex turn the workflows into skills. Because the command files ship inside each installed plugin, you can ask Codex to convert the ones you use most:
Read the command files in the pm-execution plugin and create equivalent Codex skills for the workflows I use most often.
This is a best-effort, model-driven conversion (some Claude-specific command syntax won't translate), but it's a quick way to get the guided workflows on Codex without leaving the CLI.
Other AI assistants (skills only)
The skills/*/SKILL.md files follow the universal skill format and work with any tool that reads it. Commands (/slash-commands) are Claude-specific.
| Tool | How to use | What works |
|---|---|---|
| Gemini CLI | Copy skill folders to .gemini/skills/ |
Skills only |
| OpenCode | Copy skill folders to .opencode/skills/ |
Skills only |
| Cursor | Copy skill folders to .cursor/skills/ |
Skills only |
| Kiro | Copy skill folders to .kiro/skills/ |
Skills only |
# Example: copy all skills for OpenCode (project-level) for plugin in pm-*/; do mkdir -p .opencode/skills/ cp -r "$plugin/skills/"* .opencode/skills/ 2>/dev/null done # Example: copy all skills for Gemini CLI (global) for plugin in pm-*/; do cp -r "$plugin/skills/"* ~/.gemini/skills/ 2>/dev/null done
Available Plugins
1. pm-product-discovery — Ideation, experiments, assumption testing, OSTs, interviews (13 skills, 5 commands)
Skills (13):
brainstorm-ideas-existing— Multi-perspective ideation for existing products (PM, Designer, Engineer)brainstorm-ideas-new— Ideation for new products in initial discoverybrainstorm-experiments-existing— Design experiments to test assumptions for existing productsbrainstorm-experiments-new— Design lean startup pretotypes for new products (Alberto Savoia)identify-assumptions-existing— Identify risky assumptions across Value, Usability, Viability, and Feasibilityidentify-assumptions-new— Identify risky assumptions across 8 risk categories including Go-to-Market, Strategy, and Teamprioritize-assumptions— Prioritize assumptions using an Impact × Risk matrix with experiment suggestionsprioritize-features— Prioritize a feature backlog based on impact, effort, risk, and strategic alignmentanalyze-feature-requests— Analyze and categorize customer feature requests by theme and strategic fitopportunity-solution-tree— Build an Opportunity Solution Tree (Teresa Torres) — outcome → opportunities → solutions → experimentsinterview-script— Create a structured customer interview script with JTBD probing questionssummarize-interview— Summarize an interview transcript into JTBD, satisfaction signals, and action itemsmetrics-dashboard— Design a product metrics dashboard with North Star, input metrics, and alert thresholds
Commands (5):
/discover— Full discovery cycle: ideation → assumption mapping → prioritization → experiment design/brainstorm— Multi-perspective ideation (ideas|experiments×existing|new)/triage-requests— Analyze and prioritize a batch of feature requests/interview— Prepare an interview script or summarize a transcript (prep|summarize)/setup-metrics— Design a product metrics dashboard
Examples:
Skills:
What are the riskiest assumptions for our AI writing assistant idea?Help me build an Opportunity Solution Tree for improving user activationPrioritize these 12 feature requests from our enterprise customers [attach CSV]
Commands:
/discover AI-powered meeting summarizer for remote teams/brainstorm experiments existing — We need to reduce churn in our onboarding flow/interview prep — We're interviewing enterprise buyers about their procurement workflow
2. pm-product-strategy — Vision, business models, pricing, competitive landscape (12 skills, 5 commands)
Product strategy, vision, business models, pricing, and macro environment analysis. Covers the full strategic toolkit from vision crafting through competitive landscape scanning.
Skills (12):
product-strategy— Comprehensive 9-section Product Strategy Canvas (vision → defensibility)startup-canvas— Startup Canvas combining Product Strategy (9 sections) + Business Model — an alternative to BMC and Lean Canvas for new productsproduct-vision— Craft an inspiring, achievable, and emotional product visionvalue-proposition— 6-part JTBD value proposition (Who, Why, What before, How, What after, Alternatives)lean-canvas— Lean Canvas business model for startups and new productsbusiness-model— Business Model Canvas with all 9 building blocksmonetization-strategy— Brainstorm 3–5 monetization strategies with validation experimentspricing-strategy— Pricing models, competitive analysis, willingness-to-pay, and price elasticityswot-analysis— SWOT analysis with actionable recommendationspestle-analysis— Macro environment: Political, Economic, Social, Technological, Legal, Environmentalporters-five-forces— Competitive forces analysis (rivalry, suppliers, buyers, substitutes, new entrants)ansoff-matrix— Growth strategy mapping across markets and products
Commands (5):
/strategy— Create a complete 9-section Product Strategy Canvas/business-model— Explore business models (lean|full|startup|value-prop|all)/value-proposition— Design a value proposition using the 6-part JTBD template/market-scan— Macro environment analysis combining SWOT + PESTLE + Porter's + Ansoff/pricing— Design a pricing strategy with competitive analysis and experiments
Examples:
Skills:
Compare Lean Canvas vs Business Model Canvas vs Startup Canvas for my marketplace startupDesign a value proposition for our AI writing assistant targeting non-native English speakersRun a Porter's Five Forces analysis for the project management SaaS market
Commands:
/strategy B2B project management tool for agencies/business-model startup — AI writing tool for non-native English speakers/value-proposition SaaS onboarding tool for enterprise customers
3. pm-execution — PRDs, OKRs, roadmaps, sprints, retros, release notes, stakeholder management (16 skills, 11 commands)
Day-to-day product management: PRDs, OKRs, roadmaps, sprints, retrospectives, release notes, pre-mortems, stakeholder management, user stories, and prioritization frameworks.
Skills (16):
create-prd— Lean 8-section PRD template (a fuller spec on request)brainstorm-okrs— Team-level OKRs aligned with company objectivesoutcome-roadmap— Transform a feature list into an outcome-focused roadmapsprint-plan— Sprint planning with capacity estimation, story selection, and risk identificationretro— Structured sprint retrospective facilitationrelease-notes— User-facing release notes from tickets, PRDs, or changelogspre-mortem— Risk analysis with Tigers/Paper Tigers/Elephants classificationstakeholder-map— Power × Interest grid with tailored communication plansummarize-meeting— Meeting transcript → decisions + action itemsuser-stories— User stories following the 3 C's and INVEST criteriajob-stories— Job stories: When [situation], I want to [motivation], so I can [outcome]wwas— Product backlog items in Why-What-Acceptance formattest-scenarios— Test scenarios: happy paths, edge cases, error handlingdummy-dataset— Realistic dummy datasets as CSV, JSON, SQL, or Pythonprioritization-frameworks— Reference guide to 9 prioritization frameworks (Opportunity Score, ICE, RICE, MoSCoW, Kano, etc.)strategy-red-team— Adversarial stress-test of a plan: surface load-bearing assumptions, name what would make each one fail, and rank by cheapest test
Commands (11):
/write-prd— Create a PRD from a feature idea or problem statement/plan-okrs— Brainstorm team-level OKRs/transform-roadmap— Convert a feature-based roadmap into outcome-focused/sprint— Sprint lifecycle (plan|retro|release)/pre-mortem— Pre-mortem risk analysis on a PRD or launch plan/red-team-prd— Adversarially stress-test a PRD, roadmap, or strategy and rank the riskiest assumptions by cheapest test/meeting-notes— Summarize a meeting transcript into structured notes/stakeholder-map— Map stakeholders and create a communication plan/write-stories— Break features into backlog items (user|job|wwa)/test-scenarios— Generate test scenarios from user stories/generate-data— Create realistic dummy datasets
Examples:
Skills:
Which prioritization framework should I use for a 50-item backlog?Map our stakeholders for the platform migration projectWhat's the difference between Opportunity Score, ICE, and RICE?
Commands:
/write-prd Smart notification system that reduces alert fatigue/sprint retro — Here are the notes from our last sprint/write-stories job — Break down the "team dashboard" feature into job stories
4. pm-market-research — Personas, segmentation, journey maps, market sizing, competitor analysis (7 skills, 3 commands)
User research and competitive analysis: personas, segmentation, journey maps, market sizing, competitor analysis, and feedback analysis.
Skills (7):
user-personas— Create refined user personas from research datamarket-segments— Identify 3–5 customer segments with demographics, JTBD, and product fituser-segmentation— Segment users from feedback data based on behavior, JTBD, and needscustomer-journey-map— End-to-end journey map with stages, touchpoints, emotions, and pain pointsmarket-sizing— TAM, SAM, SOM with top-down and bottom-up approachescompetitor-analysis— Competitor strengths, weaknesses, and differentiation opportunitiessentiment-analysis— Sentiment analysis and theme extraction from user feedback
Commands (3):
/research-users— Build personas, segment users, and map the customer journey/competitive-analysis— Analyze the competitive landscape/analyze-feedback— Sentiment analysis and segment insights from user feedback
Examples:
Skills:
Estimate TAM/SAM/SOM for an AI code review tool in the US marketCreate a customer journey map for our e-commerce checkout flowSegment these survey respondents by behavior and needs [attach CSV]
Commands:
/research-users We have interview data from 12 users of our fitness app/competitive-analysis Figma competitors in the design tool space/analyze-feedback Here's 200 NPS responses from Q4 [attach file]
5. pm-data-analytics — SQL generation, cohort analysis, A/B test analysis (3 skills, 3 commands)
Data analytics for PMs: SQL query generation, cohort analysis, and A/B test analysis.
Skills (3):
sql-queries— Generate SQL from natural language (BigQuery, PostgreSQL, MySQL)cohort-analysis— Retention curves, feature adoption, and engagement trends by cohortab-test-analysis— Statistical significance, sample size validation, and ship/extend/stop recommendations
Commands (3):
/write-query— Generate SQL queries from natural language/analyze-cohorts— Cohort analysis on user engagement data/analyze-test— Analyze A/B test results
Examples:
Skills:
How large a sample do I need for 95% confidence with a 2% MDE?What retention metrics should I track for a subscription app?
Commands:
/write-query Show me monthly active users by country for Q4 2025 (BigQuery)/analyze-test Here are the results from our checkout flow A/B test [attach CSV]/analyze-cohorts Weekly retention for users who signed up in January vs February
6. pm-go-to-market — Beachhead segments, ICPs, messaging, growth loops, GTM motions, battlecards (6 skills, 3 commands)
Go-to-market strategy: beachhead segments, ideal customer profiles, messaging, growth loops, GTM motions, and competitive battlecards.
Skills (6):
gtm-strategy— Full GTM strategy: channels, messaging, success metrics, and launch planbeachhead-segment— Identify the first beachhead market segmentideal-customer-profile— ICP with demographics, behaviors, JTBD, and needsgrowth-loops— Design sustainable growth loops (flywheels)gtm-motions— Evaluate GTM motions and tools (product-led, sales-led, etc.)competitive-battlecard— Sales-ready battlecard with objection handling and win strategies
Commands (3):
/plan-launch— Full GTM strategy from beachhead to launch plan/growth-strategy— Design growth loops and evaluate GTM motions/battlecard— Create a competitive battlecard
Examples:
Skills:
What's the best beachhead segment for a developer productivity tool?Design a growth loop for a B2B SaaS with a freemium tierDefine our ICP for an AI-powered HR screening platform
Commands:
/plan-launch AI code review tool targeting mid-size engineering teams/battlecard Our CRM vs Salesforce for the SMB market/growth-strategy Two-sided marketplace for connecting freelancers with startups
7. pm-marketing-growth — Marketing ideas, positioning, value props, naming, North Star metrics (5 skills, 2 commands)
Product marketing and growth: marketing ideas, positioning, value proposition statements, product naming, and North Star metrics.
Skills (5):
marketing-ideas— Creative, cost-effective marketing ideas with channels and messagingpositioning-ideas— Product positioning differentiated from competitorsvalue-prop-statements— Value proposition statements for marketing, sales, and onboardingproduct-name— Product name brainstorming aligned to brand values and audiencenorth-star-metric— North Star Metric + input metrics with business game classification
Commands (2):
/market-product— Brainstorm marketing ideas, positioning, value props, and product names/north-star— Define your North Star Metric and supporting input metrics
Examples:
Skills:
Brainstorm 5 positioning angles that differentiate us from NotionWhat's a good North Star Metric for a two-sided marketplace?Generate value prop statements for our sales team's pitch deck
Commands:
/market-product B2B analytics dashboard for e-commerce managers/north-star Two-sided marketplace connecting freelancers with clients
8. pm-toolkit — Resume review, legal documents, proofreading (4 skills, 5 commands)
PM utilities beyond core product work: resume review, legal documents, and proofreading.
Skills (4):
review-resume— PM resume review and tailoring against 10 best practices (XYZ+S formula, keywords, structure)draft-nda— Non-Disclosure Agreement with jurisdiction-appropriate clausesprivacy-policy— Privacy policy covering GDPR/CCPA compliancegrammar-check— Grammar, logic, and flow checking with targeted fixes
Commands (5):
/review-resume— Comprehensive PM resume review/tailor-resume— Tailor a resume to a specific job description/draft-nda— Draft an NDA/privacy-policy— Draft a privacy policy/proofread— Check grammar, logic, and flow
Examples:
Skills:
Review my PM resume against best practices [attach PDF]Check this product announcement for grammar and clarity
Commands:
/review-resume [attach your PM resume]/tailor-resume [attach resume + paste job description]/proofread Here's the draft of our Q1 investor update
9. pm-ai-shipping — AI Shipping Kit: document a vibe-coded app, review it for correctness, security and performance defects, map test coverage, compile a shipping packet (3 skills, 5 commands)
For PMs and founders accountable for AI-built code. AI agents write code fast but leave no record of intent — what the system should do, who may do what, where the secrets live, which rules are actually verified. This kit restores reviewability: it documents the system, then audits the gap between what the docs say and what the code actually does — the class of bug generic scanners miss.
Skills (2):
shipping-artifacts— The durable documentation set that makes an AI-built app reviewable: a core every app needs (architecture, user/permission flows, permissions, variables/secrets, test-coverage map) plus conditional docs added only when they apply (emails, cron, SEO, embedded agents/automation). Defines what each doc must capture and how a reviewer uses itintended-vs-implemented— The method for finding the gap between what a system is documented to do and what the code actually does, with cited evidence on both sides
Commands (5):
/ship-check— Turn a vibe-coded repo into a reviewer-ready shipping packet: document, wire agent context, run security and performance audits, map test coverage, and compile the results/document-app— Reverse-engineer a codebase into the system documents reviewers and auditors need — a core set (architecture, flows, permissions, variables) plus conditional docs (emails, cron, SEO, automation) when they apply;checkwrites nothing and reports where existing docs and code disagree/derive-tests— Turn documented intent into a test-coverage map: inventory the tests that exist today, separate them from proposed tests and unverified gaps, and recommend a gate that follows the repo's stated gate policy (a green-before-merge CI gate where it states none);checkwrites nothing and reports where the map is stale/security-audit-static— Static security audit: map trust boundaries, cross-reference documented intent, self-refute every finding, and report only evidence-backed risks; a git range orchangesaudits only a change/performance-audit-static— Static performance audit: find N+1 queries and request waterfalls, over-fetching, missing indexes, and caching opportunities, ranked by effort and impact; a git range orchangesaudits only a change
Examples:
Skills:
What documentation does my Supabase app need before someone can review it?Where does what this code does diverge from what the docs say it should do?
Commands:
/ship-check the payments service/document-app — Reverse-engineer the system docs for this repo/derive-tests — Which documented rules have no test yet?/security-audit-static src/api
About
This marketplace evolves with product practice and AI capabilities.
Selected skills based on the work of:
- Teresa Torres — Continuous Discovery Habits
- Marty Cagan — INSPIRED and TRANSFORMED
- Alberto Savoia — The Right It
- Dan Olsen — The Lean Product Playbook
- Roger L. Martin — Playing to Win
- Ash Maurya — Running Lean
- Strategyzer — Business Model Generation and Value Proposition Design
- Christina Wodtke — Radical Focus
- Anthony W. Ulwick — Jobs to Be Done
- Alistair Croll & Benjamin Yoskovitz — Lean Analytics
- Sean Ellis — Hacking Growth
- Maja Voje — Go-To-Market Strategist
Curated by Paweł Huryn from The Product Compass Newsletter.
Compose with PM Brain
PM Brain a second brain for product managers. Plain markdown files in a folder on your laptop. Claude reads them before answering, writes to them after, sweeps them every Friday. No vector DB. No cloud. No agent memory tricks.
Contributing
See CONTRIBUTING.md.
Known Issue on Windows
If your Cowork is unstable and can't start a VM (claude-code/issues/27010), try:
$action = New-ScheduledTaskAction -Execute "powershell.exe" -Argument "-WindowStyle Hidden -Command `"if ((Get-Service CoworkVMService).Status -ne 'Running') { Start-Service CoworkVMService }`"" $trigger = New-ScheduledTaskTrigger -RepetitionInterval (New-TimeSpan -Minutes 1) -Once -At (Get-Date) $settings = New-ScheduledTaskSettingsSet -AllowStartIfOnBatteries -DontStopIfGoingOnBatteries Register-ScheduledTask -TaskName "CoworkVMServiceMonitor" ` -Action $action ` -Trigger $trigger ` -Settings $settings ` -RunLevel Highest ` -User "SYSTEM"
It solves 90% of the issues on Windows. The remaining 10%: open services.msc > start "Claude" service manually
License
MIT — see LICENSE.