New advertisers: 50% off your first month with code FIRSTMONTHSee slots

Find the right PM skill for the situation on your desk, by lifecycle phase.

GitHub stars
8.1K
View on GitHub

Add marketplace

/plugin marketplace add deanpeters/Product-Manager-Skills

Run it inside Claude Code once, then install the plugin below.

Install

/plugin install pm-skills-navigator@pm-skills

Run it inside Claude Code after adding the marketplace.

Files

Discovered from source

PM Skills Navigator

Purpose

Get from "here's what's on my desk" to "here's the skill to open first, and why", in about five minutes. The library has dozens of skills. Most PMs don't need a catalog; they need a place to start and a sense of what comes next.

The navigator works by finding where the work is in the product lifecycle, because the most common mistake in product work is doing a later job before an earlier one is finished: writing the PRD for a problem nobody has validated, or prioritizing solutions before the outcome is named. The phase tells you which skills are premature.

It recommends a route, not a mandate. Every skill it points to runs on its own.

Input

Works best with: The situation on your desk, in a sentence or two: what's happening, and what you're supposed to produce or decide.

Also useful: What you already know for sure versus what you're assuming, who's asking, and how much time you have.

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. The first question asks what's on your desk, and the rest are answerable from what you already know. "I don't know" is a valid answer and becomes a labeled assumption in the route.

Example invocations:

  • Our dispatchers don't use the route optimizer and my VP wants a redesign. Where do I start?
  • I just joined a product team and don't know which of these skills matters for me.

Key Concepts

The Arc

Product work tends to unfold in an order. The library groups its skills by that order:

Phase (bundle)The questionYou're here when...You can leave when...
DetermineWhat outcome are we after, and what is the market doing?You can't state the outcome in a measurable sentence, or the market has movedYou have a measurable outcome and a view of the market and the customer
DiscoverWhat is the real problem?You have an outcome but the problem is a guess or a stakeholder's opinionYou have a problem statement backed by evidence from customers
DefineIs this solution worth building, and how do we position it?You have a problem but the solution is untestedYou have a tested bet worth building and can say who it's for and why you win
DevelopHow do we turn it into buildable work?The solution is chosen but isn't ready for a team (no PRD, stories, order)A team can start, and knows what they're building and in what order
DeliverHow do we price it, take it to market, measure it, and retire it well?It's built, or it's agingIt's priced and launched, and you can tell whether it worked, or it has been retired cleanly
DriveHow do I work with people and grow?The question is about a stakeholder, an incoming request, or your own careerIt's handled. This phase runs under all the others

The same arc shows up in software delivery (plan, analyze, design, build, deploy) and in other product frameworks. That's the point: it isn't a house opinion, it's how work earns the right to move forward.

The Phase Is Set by Evidence, Not by Where You Wish You Were

A team that says "we're in Develop" because a PRD is due, with an unvalidated problem underneath, is actually in Discover. Ask what's validated and what's assumed, and place the work at the earliest phase whose exit condition isn't met. Calling it later doesn't make it later.

A Cycle, Not a Line

Work loops back (a failed test sends you to Discover again) and runs concurrently (launch prep starts while you build). So the navigator:

  • Names two phases when the work straddles them, and puts the one carrying the highest unresolved risk first.
  • Treats Drive as orthogonal. A question about a stakeholder or your own career gets routed to Drive whatever phase the product is in.
  • Never blocks. If you want a later-phase skill, it says what you're skipping and what that risk is, then helps you anyway. Your call.

Motions: The Smaller Groups Inside a Bundle

Each bundle has motions, which are specific jobs. The map below is the full list. A motion marked Coming has no skill yet. The navigator says so instead of forcing a poor fit.

Anti-Patterns (what this is NOT)

  • Not a pipeline. It suggests an order; it doesn't require one. Skip, reorder, or stop after one.
  • Not a gate. It never refuses to help with a later-phase skill.
  • Not a replacement for the skills. It points; the skills do the work.
  • Not a catalog. For a flat list, see catalog/skills-by-bundle.md.

Facilitation Source of Truth

Use workshop-facilitation as the interaction protocol. Give the heads-up at the start (four questions, about five to ten minutes) and let the user dump context to skip ahead.

Default entry mode: Guided · set in pm-skills.config.yaml (library-wide default or a per-skill override); the user's own choice in the session always wins. On the first turn, offer all three modes, then open in the default without waiting for a pick: Guided asks the first question, Context dump invites the paste, Best guess asks for a one-sentence minimum and drafts with every assumption labeled.


The Map

This block is generated from pm-skills.config.yaml. Don't edit it here; run python3 scripts/check-bundles.py --write-navigator.

Determine (Context): Set outcomes and read the terrain: strategy, finance, market, customers.

Discover (Discover + Investigate): Find and frame the real problem.

Define (Discover + Define): Shape a solution worth building and test the bet.

Develop (Create): Turn the chosen solution into buildable work.

Deliver (Deliver): Take it to market, measure it, and retire it well.

Drive (Runs under all five phases): Drive your career and your stakeholders.

Core (shared helpers that ship with every bundle): workshop-facilitation, pm-skills-navigator, autonomous-investigation, pm-skill-creator, skill-authoring-workflow


Application

This skill asks up to 4 adaptive questions, then recommends a route with reasons.


Question 1 of 4: What's on your desk?

Agent asks:

"What's the situation? Tell me what's happening and what you're expected to produce or decide. One or two sentences is plenty."

Listen for the job-to-be-done behind the request. "Write a PRD" is a deliverable; the situation underneath (a stakeholder asked for a feature, or discovery found a pattern) decides which phase it belongs to. If the answer is about people (a stakeholder, a request, your career), note it: that's Drive, and it can skip Question 2.


Question 2 of 4: What's validated, and what's assumed?

Agent asks:

"Let's find where this really stands. Which of these is true today?

  1. We have a measurable outcome we're aiming at (not just a feature)
  2. We've talked to customers and can state the problem with evidence
  3. We've tested a solution and it held up
  4. None of those yet, or I'm not sure

Pick any that apply."

Place the work at the earliest phase whose exit condition is unmet:

They saidEarliest unmetPhase
4 (none)The outcomeDetermine
1 onlyThe problemDiscover
1 and 2, not 3The solution testDefine
1, 2, and 3Buildable work, then marketDevelop, then Deliver

If their situation sounds later than their answers (a PRD is due but they picked 4), say so gently: the PRD is premature, here's the evidence gap, and here's the smaller job that unblocks it.


Question 3 of 4: What do you need to walk away with?

Agent asks:

"What would make this session worth it?

  1. A decision (which option, build or not, which framework)
  2. An understanding (what's going on, what customers need, what the market is doing)
  3. A document (a PRD, stories, a positioning statement, a plan)
  4. Alignment (getting people on board, handling a request, planning a conversation)"

Use the answer to pick the motion and the skill type. A decision usually means an interactive advisor. An understanding usually means a workflow or an investigation. A document means a component skill. Alignment means a Drive skill, whatever the phase.


Question 4 of 4: How much time do you have?

Agent asks:

"Roughly how long can you give this: under an hour, a few hours, or days?"

Use it to size the route, and honor an override either way. Under an hour means one skill, the quick one. A few hours means two or three in order. Days means the workflow version where one exists. Name what a shorter route leaves uncovered.


Final Step: Recommend the route

Deliver this structure:

## Your Route: [Situation in a few words]

**Where the work is:** [Phase] (and [second phase] if it straddles) — because [what's validated vs assumed]
**Bundle / motion:** [Bundle] → [Motion]

### Start here
1. [`skill`](../skill/SKILL.md): [why this one first, one line]
2. [`skill`](../skill/SKILL.md): [what it adds]
3. [`skill`](../skill/SKILL.md): [optional; what it adds]

**What you're skipping, if anything:** [the earlier-phase job you aren't doing, and the risk]
**Gap, if any:** [a need with no skill yet, and the closest alternative]

### Paste this first
> [A real first prompt using their own details]

### Assumptions I made
- [Anything answered "I don't know"]

Then offer numbered next steps:

"Where next?

  1. Run the first skill now, with the prompt above
  2. See the rest of this phase, or the phase before or after it
  3. Check what you're skipping, and go back for it first
  4. Navigate a different problem

Pick a number, combine them, or tell me what you'd rather do."


Examples

Example A: SaaS, the PRD is premature

Fieldlight (field service software). The PM's VP wants a redesign of the route optimizer because dispatchers "don't use it."

Q1. "Dispatchers don't use the route optimizer. My VP wants it redesigned. I'm supposed to write the PRD."

Q2. Which is true: outcome, problem, tested solution? → "Honestly, none. The VP has an outcome in mind, but nobody has asked a dispatcher why."

Q3. What do you walk away with? → "A document, the PRD."

Q4. Time? → "A couple of hours."

Route: Phase Discover (and Develop, where the request is pointing). The PRD is premature: the problem is an opinion, not a finding.

  1. problem-framing-canvas: state the problem before the solution
  2. discovery-interview-prep: plan five dispatcher conversations
  3. prd-development: once the problem is evidenced

What you're skipping: nothing yet; you're not skipping, you're sequencing. Paste this first: "Frame this problem: dispatchers 'don't use' the route optimizer, and my VP wants it redesigned."

The coaching beat: the PRD was the right deliverable and the wrong next step. Naming it that way keeps the PM from feeling blocked.

Example B: Industrial, the work straddles two phases

Northfield Automation (industrial retrofit controls). NFA-200 sales have been flat for six quarters. A distributor asks for a variant; engineering says it's a 14-month cycle.

Q1. "NFA-200 is flat. A big distributor wants a variant. Sales is half-promising it."

Q2. → "We have an outcome (hold margin). We don't know if it's the product or the channel."

Q3. → "A decision: variant or not?"

Q4. → "A week, but it's a big call."

Route: Phase Deliver (an aging product) and Define (the variant is an untested bet). Highest unresolved risk first: Deliver, because nobody has established whether the product is declining or badly distributed.

  1. lifecycle-play-advisor: is this extend, replace, retire, or nothing yet?
  2. incoming-request-advisor: decode what the distributor is asking before replying
  3. pol-probe-advisor: if "extend" wins, test the variant cheaply

What you're skipping: a 14-month build commitment on an untested variant. Paste this first: "Help me decide what to do with NFA-200: sales flat six quarters, a distributor wants a variant."

The coaching beat: two phases named on purpose. Straddling is normal; what matters is which risk to retire first.


Common Pitfalls

Pitfall 1: Placing the Work Where the Deliverable Is

Symptom: "A PRD is due, so we're in Develop." Consequence: A polished spec for an unvalidated problem. Looks like progress, builds the wrong thing well. Fix: Place by evidence: the earliest phase whose exit condition is unmet.

Pitfall 2: Treating the Route as a Pipeline

Symptom: Running all three recommended skills in order because they were listed. Consequence: Process theater. The route is a suggestion; the first skill may be all you need. Fix: Stop when the question is answered. Every skill runs alone.

Pitfall 3: Forcing a Fit on a Gap

Symptom: Recommending a loosely related skill for a need the library doesn't cover yet. Consequence: The PM trusts a template that doesn't fit, and the library loses credibility. Fix: Say "no skill for this yet" and name the closest honest alternative with its limits.

Pitfall 4: Blocking the Skip

Symptom: Refusing to help with a later-phase skill until an earlier one is done. Consequence: Contradicts a cycle that really is concurrent, and the PM stops asking. Fix: Name what's being skipped and the risk, then help anyway.

Pitfall 5: Routing a People Problem Through the Product Arc

Symptom: Sending a stakeholder conflict to Discover. Consequence: Customer research for a problem that's about a person. Fix: Drive runs under every phase. Route people questions there directly.


References

Related Skills

These stand on their own; none is a prerequisite for this skill, and this skill isn't a prerequisite for them.

External Frameworks

  • Software development life cycle (plan, analyze, design, build, deploy): the same arc in engineering
  • Productside Blueprint: the product lifecycle the phase names are aligned with

Provenance

  • Distilled from practitioner experience teaching the product lifecycle and routing PMs to the right tool for the phase they are actually in.

From the deanpeters/Product-Manager-Skills README

Product Manager Skills

Ready-made PM skills for your AI assistant. A skill is a short instruction file that teaches an AI how to do one PM job the way a pro would, such as writing a PRD or mapping stakeholders, so you stop re-explaining your process every time.

Try it in five minutes

  1. Download the starter pack and unzip it.
  2. In Claude, open Settings → Capabilities → Skills and upload one skill ZIP from inside the folder. Using Claude Code, Codex or something else? Jump to Get Started.
  3. Start a chat and paste this, swapping in your own details:
Which of these skills fits what's on my desk this week? Here's the situation: [one or two sentences].

You should see Claude name the skill it is using and start asking you questions. Arriving empty-handed is fine: the skills ask for what they need.


GitHub stars GitHub forks GitHub watchers Contributors PRs Welcome

Version Skills Last commit Claude Code Plugin

╔════════════════════════════════════════════════════════════════════╗
║                                                                    ║
║   ██████╗ ███╗   ███╗    ███████╗██╗  ██╗██╗██╗     ██╗     ███████╗
║   ██╔══██╗████╗ ████║    ██╔════╝██║ ██╔╝██║██║     ██║     ██╔════╝
║   ██████╔╝██╔████╔██║    ███████╗█████╔╝ ██║██║     ██║     ███████╗
║   ██╔═══╝ ██║╚██╔╝██║    ╚════██║██╔═██╗ ██║██║     ██║     ╚════██║
║   ██║     ██║ ╚═╝ ██║    ███████║██║  ██╗██║███████╗███████╗███████║
║   ╚═╝     ╚═╝     ╚═╝    ╚══════╝╚═╝  ╚═╝╚═╝╚══════╝╚══════╝╚══════╝
║                                                                    ║
║   95 battle-tested skills + 6 command workflows                    ║
║   Claude Code • Cursor • Codex  • n8n • OpenClaw • and more ...    ║
║                                                                    ║
║   v0.86 • November 13, 2026 • CC BY-NC-SA 4.0                      ║
╚════════════════════════════════════════════════════════════════════╝

95 battle-tested PM frameworks, ready for Claude, Codex, ChatGPT, and any agent that can read structured knowledge.


Why This Exists

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.


Get Started

Choose your setup:

I use...Get thisNotes
Claude Desktop or Claude Webpm-skills-starter-pack.zipUnzip, then upload the individual skill ZIPs to Claude Skills
Claude CodePlugin marketplace/plugin marketplace add deanpeters/Product-Manager-Skills, then /plugin install product-manager-skills@pm-skills for everything, or one lifecycle bundle at a time (see Browse by lifecycle)
Codexpm-skills-codex.zipInstalls .agents/skills and AGENTS.md
OpenCodeCopy skills/* to ~/.config/opencode/skills/ (or reuse the Codex ZIP)OpenCode reads our SKILL.md format as-is. See the install guide
Not surepm-skills-starter-pack.zipStart here

All downloads: GitHub Releases

Start here by situation

Don't know where to begin? Find the line that sounds like your week. Each route is a suggested order, not a pipeline — every skill runs on its own, so skip ahead, reorder, or stop after one. The first prompt is real: paste it, swap in your details, and go.

If this is you...Try, in this orderTimePaste this first
"I have an idea and I don't know if it's real."problem-framing-canvas → discovery-interview-prep → pol-probe-advisor~1–1.5 hrFrame this problem: field sales reps 'don't use the CRM' and leadership wants gamification.
"A request or mandate just landed on my desk."incoming-request-advisor → stakeholder-mapping → prioritization-advisor~1 hrMy VP DM'd me: "Any chance the dashboard redesign lands next sprint? Board's asking." Analyze this before I reply.
"I need to understand the market, fast."market-landscape-scan → competitive-research-snapshot → swot-analysis~1–2 hrRun a market landscape scan on [your market], and tell me the decision it should support.
"We keep getting compared and losing."positioning-workshop → roadmap-planning (going bigger: product-strategy-session, a 2–4 week workflow)~2–3 hrRun a positioning workshop for our API monitoring tool — we keep getting compared to Datadog and losing.
"Time to write it down."prd-development → epic-breakdown-advisor → user-story~1.5–3 hrBuild a PRD for self-serve workspace provisioning — here are my discovery notes and the OKR it ladders to.
"Our product is getting old."lifecycle-play-advisor → eol-readiness-advisor → eol-process~30–50 min to a decisionHelp me decide what to do with [product]. Here's what makes me think it's fading: [signals].
"I'm stepping up a level."director-readiness-advisor or vp-cpo-readiness-advisor — pick by where you're headed~10–20 minI'm 60 days into a Director role and my old peers now report to me — it's awkward and I'm still doing PM work. Coach me.
"I'm new here, or not sure."The Starter pack — six skills across the craft—Install it, then ask: Which of these skills fits what's on my desk this week?

Why these orders (so you can break them on purpose):

  • Idea → problem → people → probe. Name the problem before you ask anyone about it, and ask people before you build anything. The probe comes last because it's the most expensive of the three.
  • Request → decode → map → decide. Understand what's really being asked before replying, know who else is in the room, then ask where it fits. Prioritizing first is how a loud VP becomes your roadmap.
  • Market → competitors → SWOT. Evidence first, framework last. SWOT on top of no research is opinion with a 2×2 around it.
  • Positioning → roadmap. Decide who you're for and why you win before choosing what to build. The strategy session is the full-length version when the question is bigger than a quarter.
  • PRD → epics → stories. The why first, then slices, then the smallest writeable pieces. Writing stories first is how a backlog loses its reason.
  • Aging → play → readiness → process. The first skill may say "nothing yet" — extending or harvesting is a legitimate answer, and starting here does not commit you to a sunset.

Browse by lifecycle

Product work unfolds in an order: set the outcome before you investigate, investigate before you define, define before you build. The library follows that arc in five bundles, with a sixth that runs underneath all of them. It's a cycle, not a pipeline, so you will loop back, and every skill still runs on its own.

BundleThe question it answersStart withClaude Code install
DetermineWhat are we trying to achieve, and what is the market doing?product-strategy-session, market-landscape-scan, business-health-diagnostic/plugin install pm-determine@pm-skills
DiscoverWhat is the real problem?problem-framing-canvas, discovery-interview-prep/plugin install pm-discover@pm-skills
DefineIs this solution worth building, and how do we position it?pol-probe-advisor, positioning-statement/plugin install pm-define@pm-skills
DevelopHow do we turn the chosen solution into buildable work?prd-development, user-story, prioritization-advisor/plugin install pm-develop@pm-skills
DeliverHow do we price it, take it to market, and retire it well?finance-based-pricing-advisor, lifecycle-play-advisor/plugin install pm-deliver@pm-skills
DriveHow do I work with stakeholders and grow my career?stakeholder-mapping, director-readiness-advisor/plugin install pm-drive@pm-skills

Not sure which bundle? Ask the pm-skills-navigator: describe what's on your desk, and in about five minutes it tells you where the work really is and which skill to open first.

Every bundle includes a few shared helper skills (the facilitation rulebook and the navigator among them), so each works installed alone. The full list, grouped by bundle and by the smaller "motions" inside each, is in catalog/skills-by-bundle.md.

Why this order? Skipping ahead is how teams build the right thing for the wrong problem. Naming the outcome first gives discovery a target, and discovery gives definition something real to test.

On Claude Desktop or Web? Download the bundle pack that matches your phase, or grab single skills from the download shelf.

Lifecycle bundle packs for Claude Desktop / Web

Each pack is a ZIP of upload-ready skill ZIPs. Unzip it, then upload the skills to Claude Skills:

PackDownloadWhat's inside
Starterpm-skills-starter-pack.zipSix core skills across the craft. The best first download
Determinepm-determine-pack.zipStrategy, finance, market intelligence, customer context (24 skills)
Discoverpm-discover-pack.zipInterviews, surveys, usage data, synthesis, assumptions, problem framing, opportunity trees, journey maps (12 skills)
Definepm-define-pack.zipHypotheses, probes, experiments, positioning (9 skills)
Developpm-develop-pack.zipPRDs, stories, prioritization, roadmaps, sprint and release rituals, AI agents (16 skills)
Deliverpm-deliver-pack.zipLaunch plans, messaging, sales enablement, pricing, channels, post-launch metrics, activation and retention, and the end-of-life suite (18 skills)
Drivepm-drive-pack.zipStakeholders, decision rights, influence, and career transitions (11 skills)
All skills99-all-skills-pack.zipAll 95 skills

The older themed packs (02-discovery through 07-lifecycle-eol) were retired in v0.86. Every skill in them lives in a lifecycle pack above.

Install guides


Try It First — Streamlit (beta)

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:

  • Learn — browse setup and integration paths without leaving the app
  • Find My Skill — describe your situation in plain English and get recommended skills
  • Run Skills — run a skill with your own scenario once you know what you want

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.


What You Can Get Done

Navigate by what you're actually trying to accomplish:

Framing and strategy

  • problem-framing-canvas — MITRE's Look Inward / Look Outward / Reframe sequence; stops teams from solving the wrong problem
  • positioning-statement — Geoffrey Moore's template for defining who you serve, what you solve, and how you're different
  • product-strategy-session — full strategy arc: positioning → problem framing → solution exploration → roadmap (2-4 weeks)

Stakeholder alignment

  • stakeholder-identification — map every stakeholder before engaging anyone: broad brainstorm → allies/audiences/influencers → R/P/D marking → equity lens → narrow to priority targets
  • stakeholder-mapping — run two complementary grids (Power × Interest for engagement strategy; Impact × Power for whose voice to elevate) and compare to find the gaps
  • stakeholder-engagement-advisor — per-stakeholder engagement planning: diagnoses their profile and context, then delivers tailored message framing, medium, cadence, and a named next action

Customer discovery and research

Prioritization and roadmapping

  • prioritization-advisor — asks 3-5 questions about your context, then recommends RICE, ICE, Kano, or the right alternative
  • epic-breakdown-advisor — splits large epics using Richard Lawrence's 9 patterns
  • roadmap-planning — gather inputs → define epics → prioritize → sequence → communicate (1-2 weeks)

Writing PM deliverables

  • user-story — Mike Cohn format + Gherkin acceptance criteria, with anti-patterns
  • prd-development — structured PRD: problem → personas → solution → metrics → stories (2-4 days)
  • press-release — Amazon Working Backwards: clarify product vision before writing a line of spec

Validation and experimentation

  • pol-probe-advisor — recommends which prototype type to run based on your hypothesis and risk level
  • pol-probe — template for documenting lightweight validation experiments before building

Finance and growth

  • business-health-diagnostic — diagnoses SaaS health across growth, retention, efficiency, and capital using your real metrics
  • organic-growth-advisor — McKinsey Growth Pyramid triage: diagnoses whether your constraint is in new segments, geographies, channels, or products
  • feature-investment-advisor — build / don't build recommendation using revenue impact, cost, ROI, and strategic value

Market and competitive intelligence

Aging products: extend, replace, or retire

  • lifecycle-play-advisor — start here when a product stops growing: seven transition questions establish the stage, then it picks the play — extend, replace, or retire — and tells you when the honest answer is "nothing yet"
  • product-lifecycle-plays — the framework behind that call: the PLC strategy grid, the seven replacement hazards, and a risk register whose last column asks what is Plan B?
  • eol-process — the whole sunset in six phases, decide → align → plan → prepare → announce → close, including the post-EOL review everyone skips
  • The EOL chain: eol-readiness-advisor → eol-stakeholder-sequence → eol-checklist → eol-internal-enablement → eol-message — every one runs standalone, sized Light/Standard/Heavy by you

Career and leadership transitions

AI product work


95 Skills, 3 Types

Skills are organized in three tiers that build on each other:

┌────────────────────────────────────────────────────────┐
│  WORKFLOW SKILLS (25)                                  │
│  Complete end-to-end PM processes (days to weeks)      │
│  Example: run a full discovery cycle or write a PRD    │
└────────────────────────────────────────────────────────┘
                       ↓ orchestrates
┌────────────────────────────────────────────────────────┐
│  INTERACTIVE SKILLS (34)                               │
│  Guided discovery — 3-5 questions, then recommendations│
│  Example: "Which prioritization framework fits here?"  │
└────────────────────────────────────────────────────────┘
                       ↓ uses
┌────────────────────────────────────────────────────────┐
│  COMPONENT SKILLS (36)                                 │
│  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: by type or by lifecycle bundle, all 95 skills with descriptions, or browse skills/ directly.


How a Skill File Works

Every SKILL.md follows the same structure:

SectionWhat it contains
Frontmattername, description, type, intent, best_for, scenarios
PurposeWhat this skill does and when to reach for it
InputWhat 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 ConceptsFrameworks, definitions, anti-patterns — with vocabulary explained
ApplicationStep-by-step instructions an agent (or human) can follow
ExamplesReal-world cases showing both good and bad versions
Common PitfallsNamed failure modes with consequences and corrections
ReferencesRelated 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.

Guided Context Capture. Every interactive skill gathers context the same way. You can go one question at a time, paste what you know, or say "best guess." A pasted dump gets read back to you as Known / Assumed / Missing / Conflicting before any question is asked. You get a recap before anything is generated. Decisions come as a ranked ladder (Recommended first, real alternatives with tradeoffs), and you make the call. The skill never re-asks what you already said or passes a guess off as a fact. Guided is the default opening; change it library-wide or per skill in pm-skills.config.yaml. How it works and why: docs/guided-context-capture.md.


Works With

Claude Code · Claude Desktop · Claude Web · OpenAI Codex · ChatGPT · Cursor · Windsurf · n8n · LangFlow · CrewAI · Gemini · OpenCode · any agent that reads structured markdown

See docs/Platform Guides for PMs.md for platform-specific setup.


Docs

DocumentPurpose
Using PM Skills 101Beginner-friendly orientation — setup without technical overload
Platform Guides for PMsTool-by-tool setup chooser for every supported platform
Using PM Skills with ClaudeClaude Code + GitHub ZIP upload for Claude Desktop/Web
Using PM Skills with CodexLocal workspace + GitHub-connected Codex on ChatGPT
Using PM Skills with ChatGPTGitHub app, Custom GPT Knowledge, and Project-based usage
Using PM Skills with Slash Commands 101Turn skills into reusable slash commands like /pm-story
Add-a-Skill Utility GuideEnd-to-end guide for generating and validating new skills
Market Intelligence Suite SummaryThe 14-skill competitive/market research suite: disciplines, chain, and which skill to run when
Lifecycle & EOL Suite SummaryThe 8-skill lifecycle/sunset suite: the three plays, the EOL chain, and right-sizing
Building PM SkillsHow raw PM content gets distilled into agent-ready skills
START_HERE.md60-second onboarding for local repo users

What's New

v0.86 — November 13, 2026 · The Everyday Work of Product, Now on the Map

v0.85 — November 13, 2026 · Lifecycle Bundles, a Navigator, and the Go-to-Market Gap Filled

v0.84 — August 10, 2026 · The Lifecycle & End-of-Life Suite

  • 7 new skills + 1 upgrade for the part of product management nobody trains you on: what to do with a product that has stopped growing, and how to retire one without losing the customer
  • Start upstream of the kill decision. lifecycle-play-advisor and product-lifecycle-plays diagnose where a product actually sits using seven transition questions, then pick between the three plays — extend, replace, or retire. Includes the seven replacement hazards and a risk register whose contingency column asks the question everyone skips: what is Plan B?
  • The EOL chain: eol-readiness-advisor (go/no-go, and it will tell you to hold) → eol-stakeholder-sequence (Legal before Finance before Sales — get the order wrong and you find the landmines after the announcement) → eol-checklist (phase-gated, an owner on every item) → eol-internal-enablement (your teams ready before customers hear) → eol-message (upgraded: three transition paths including the honest no-replacement case) → eol-process (the whole thing, six phases, including the post-EOL review everybody skips)
  • Right-sizing is a dial you set, not a verdict handed to you. Every skill offers Light / Standard / Heavy, defaults to Standard, and names what a lighter choice leaves uncovered. A feature deprecation should never get a flagship playbook — that's how teams learn to ignore EOL process on the sunset that actually matters
  • No tight coupling. Every skill runs standalone; the workflow is a recommended route through independent stops, not a pipeline. Enter wherever you actually are — including mid-sunset, with a diagnostic that maps symptoms ("Support is drowning") to the phase that got skipped
  • Library now at 77 skills · full story in the release note

v0.83 — July 17, 2026 · The Market Intelligence Suite

v0.82 — July 8, 2026

  • Added 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
  • New: a browsable download shelf at /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 skills
  • Library now at 56 skills

v0.81 — July 4, 2026

  • Every skill now has a required ## 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 rest
  • Added argument-hint autocomplete for Claude Code users; deliberately no $ARGUMENTS templating — it breaks on every other runtime and teaches the reader nothing (why)
  • Validator now enforces the convention: skills fail without an Input section or with bare $ARGUMENTS in the body
  • Streamlit playground shows each skill's "What to bring (all optional)" before you start a session
  • Restored agent-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 standards

v0.80 — June 19, 2026

  • Added stakeholder-identification (Component) — comprehensive stakeholder brainstorm using allies/audiences/influencers, R/P/D marking, equity lens, and bias check; narrows to priority targets
  • Added stakeholder-mapping (Component) — two complementary grids (Power × Interest + Impact × Power); comparing outputs reveals who you're under-engaging relative to how much the product affects them
  • Added stakeholder-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 action

All 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

  • Added organic-growth-advisor — McKinsey Growth Pyramid triage for new segments, geographies, channels, or products
  • Added pm-skill-creator — interactive skill for designing repo-compliant skills via guided conversation
  • Fixed missing .claude-plugin/plugin.json that silently blocked Claude Code skill discovery
  • Added configurable input length guard (PM_MAX_INPUT) and path traversal protection to helper scripts

→ Full changelog


Contributing

Found 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.


License

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:

  • ✅ Use these skills in your day job — at a for-profit company, with your team, in your agents. That's what they're for.
  • ✅ Adapt and remix them — share what you build under this same license, with credit.
  • ✅ Teach with them — workshops, brown bags, mentoring, sending the ladder down.
  • ❌ Don't sell them — no repackaging the skills themselves into a paid product, course, or service without expressed written permission.
  • 📄 Need something citable for your legal team? See LICENSING.md: internal use at a for-profit company is fine, and what you produce using the skills is yours.
  • 🤔 Not sure your use qualifies? Open an issue and ask. If you're using these in the spirit they were built — to get better at the craft and help others do the same — the answer is almost certainly yes.

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.


Questions

Details

Marketplace
deanpeters/Product-Manager-Skills
Source
skills/pm-skills-navigator
Category
Meta

More from deanpeters/Product-Manager-Skills

All 102

Similar to pm-skills-navigator

More Development Tools