Skip to content
pm-skills

PM Skills

68 best-practice product management skills for AI agents.

PM Skills teaches AI assistants how to produce professional PM artifacts - PRDs, user stories, acceptance criteria, experiment designs, sprint outputs, and more. One command, consistent output, every time.

The Triple Diamond

Section titled “The Triple Diamond”

Skills are organized across 6 phases of the Triple Diamond framework - three diamonds covering the problem space, the solution space, and the learning space.

graph LR
    subgraph "Problem Space"
        D1["Discover<br/>5 skills"] --> D2["Define<br/>5 skills"]
    end
    subgraph "Solution Space"
        D3["Develop<br/>4 skills"] --> D4["Deliver<br/>6 skills"]
    end
    subgraph "Learning Space"
        D5["Measure<br/>6 skills"] --> D6["Iterate<br/>4 skills"]
    end
    D2 --> D3
    D4 --> D5
    D6 -.->|"next cycle"| D1

    classDef discover fill:#e7f5ff,stroke:#1971c2,color:#0c2d5e,stroke-width:2px
    classDef define fill:#e6fcf5,stroke:#0ca678,color:#0a4f3c,stroke-width:2px
    classDef develop fill:#f3e8ff,stroke:#7048e8,color:#3a1d8a,stroke-width:2px
    classDef deliver fill:#fff4e1,stroke:#d9480f,color:#5e2200,stroke-width:2px
    classDef measure fill:#fff9db,stroke:#e8a317,color:#5e3e00,stroke-width:2px
    classDef iterate fill:#ffe9ec,stroke:#c2255c,color:#5c0a25,stroke-width:2px

    class D1 discover
    class D2 define
    class D3 develop
    class D4 deliver
    class D5 measure
    class D6 iterate

Learn about the Triple Diamond

The Skills

Section titled “The Skills”

Discover (5 skills)

Research, competitive analysis, stakeholder mapping.

Browse Discover

Define (5 skills)

Problem framing, hypotheses, opportunity trees, JTBD.

Browse Define

Develop (4 skills)

Solution briefs, ADRs, design rationale, spikes.

Browse Develop

Deliver (6 skills)

PRDs, user stories, acceptance criteria, edge cases, launch, release notes.

Browse Deliver

Measure (6 skills)

Experiments, instrumentation, dashboards, results, OKR grading.

Browse Measure

Iterate (4 skills)

Retrospectives, lessons, refinement, pivot decisions.

Browse Iterate

Foundation (11 skills)

Cross-cutting skills: persona, OKR writer, lean canvas, meeting lifecycle, stakeholder update, stakeholder briefings, prioritized action plan, build risk review.

Browse Foundation

Utility (12 skills)

Create, validate, iterate skills, build and run multi-skill workflows, generate diagrams and presentations, and update the library.

Browse Utility

Tool (15 skills)

Canonical sprint methodologies: Foundation Sprint (7) + Design Sprint (7) + tool-note-and-vote.

Browse Tool

Skills by Phase

Section titled “Skills by Phase”

Each box below is a skill you invoke by name. The six phases trace a product from first research through to post-launch learning, so you can pick the one that matches where your work is right now.

block-beta
    columns 6

    block:discover["Discover"]:1
        d1["discover-competitive-analysis"]
        d2["discover-interview-synthesis"]
        d3["discover-stakeholder-summary"]
        d4["discover-journey-map"]
        d5["discover-market-sizing"]
    end

    block:define["Define"]:1
        f1["define-problem-statement"]
        f2["define-hypothesis"]
        f3["define-opportunity-tree"]
        f4["define-jtbd-canvas"]
        f5["define-prioritization-framework"]
    end

    block:develop["Develop"]:1
        v1["develop-solution-brief"]
        v2["develop-spike-summary"]
        v3["develop-adr"]
        v4["develop-design-rationale"]
    end

    block:deliver["Deliver"]:1
        l1["deliver-prd"]
        l2["deliver-user-stories"]
        l3["deliver-acceptance-criteria"]
        l4["deliver-edge-cases"]
        l5["deliver-launch-checklist"]
        l6["deliver-release-notes"]
    end

    block:measure["Measure"]:1
        m1["measure-experiment-design"]
        m2["measure-instrumentation-spec"]
        m3["measure-dashboard-requirements"]
        m4["measure-experiment-results"]
        m5["measure-okr-grader"]
        m6["measure-survey-analysis"]
    end

    block:iterate["Iterate"]:1
        i1["iterate-retrospective"]
        i2["iterate-lessons-log"]
        i3["iterate-refinement-notes"]
        i4["iterate-pivot-decision"]
    end

    discover --> define --> develop --> deliver --> measure --> iterate

    style discover fill:#e7f5ff,stroke:#1971c2,color:#0c2d5e,stroke-width:2px
    style define fill:#e6fcf5,stroke:#0ca678,color:#0a4f3c,stroke-width:2px
    style develop fill:#f3e8ff,stroke:#7048e8,color:#3a1d8a,stroke-width:2px
    style deliver fill:#fff4e1,stroke:#d9480f,color:#5e2200,stroke-width:2px
    style measure fill:#fff9db,stroke:#e8a317,color:#5e3e00,stroke-width:2px
    style iterate fill:#ffe9ec,stroke:#c2255c,color:#5c0a25,stroke-width:2px

Beyond the six phases, three cross-cutting families support the work at every stage:

  • Foundation (11) - reusable building blocks for any initiative: foundation-persona, foundation-lean-canvas, foundation-okr-writer, foundation-stakeholder-update, foundation-stakeholder-briefings, foundation-prioritized-action-plan, foundation-build-risk-review, and the four meeting skills (agenda, brief, recap, and cross-meeting synthesis).
  • Workshop tools (15) - run a facilitated session with your agent: the 7-skill Foundation Sprint family for 2-day strategic alignment, the 7-skill Design Sprint family for a 5-day prototype-and-test cycle, and the standalone tool-note-and-vote decision mechanic.
  • Utility (12) - meta-tooling that builds, validates, and maintains the library itself, plus utility-pm-workflow-builder for authoring new workflows, utility-pm-workflow-orchestrator for governed multi-skill runs, and the sub-agents that handle adversarial review, catalog auditing, changelog curation, and release orchestration.

The Skill Lifecycle

Section titled “The Skill Lifecycle”

Three utility skills form a self-reinforcing quality loop for managing the skill library itself:

flowchart LR
    Create["utility-pm-skill-builder<br/>Create"] --> Validate["utility-pm-skill-validate<br/>Validate"]
    Validate --> Decision{Findings?}
    Decision -- "PASS" --> Ship["Ship"]
    Decision -- "WARN / FAIL" --> Iterate["utility-pm-skill-iterate<br/>Iterate"]
    Iterate --> Validate

Create a new skill with guided gap analysis and classification. Validate it against structural conventions and quality criteria. Iterate to fix findings from the validation report or apply feedback. Repeat until passing, then ship.

The lifecycle tools are what keep the library consistent as it grows - the validator catches drift, and the iterator applies fixes with version tracking and change summaries.

Learn more about the lifecycle · PM-Skill versioning

Quick Start

Section titled “Quick Start”

Claude Code - install from the plugin marketplace:

Terminal window
/plugin marketplace add product-on-purpose/agent-plugins
/plugin install pm-skills@product-on-purpose

Any other agent - add via the open skills CLI, or clone the repo:

Terminal window
npx skills add product-on-purpose/pm-skills
# or: git clone https://github.com/product-on-purpose/pm-skills.git

Then invoke any skill by name:

deliver-prd "Search feature for e-commerce platform"
define-hypothesis "Will one-page checkout increase conversion?"
deliver-acceptance-criteria "User can reset password via email"

Full setup guide · Find the right skill · Recipes

See It In Action

Section titled “See It In Action”

Follow three fictional companies through the complete product lifecycle - from discovery research to pivot decisions - with real prompts and full outputs.

Storevine - B2B Ecommerce

Building email marketing for 15K merchants. Organized prompts.

Follow the journey

Brainshelf - Consumer PKM

Building a morning digest for 22K users. Casual prompts.

Follow the journey

Workbench - Enterprise Collaboration

Building document templates for 500 enterprises. Structured prompts.

Follow the journey

Works Everywhere

Section titled “Works Everywhere”
PlatformMethod
Claude CodeSlash commands (deliver-prd, define-hypothesis, etc.)
GitHub CopilotAGENTS.md auto-discovery
Cursor / WindsurfAGENTS.md or MCP server
Claude.ai / DesktopZIP upload or MCP
Any MCP clientpm-skills-mcp

Workflows

Section titled “Workflows”

12 guided multi-skill workflows for common PM processes. Each chains skills in a recommended sequence with handoff guidance.

WorkflowBest forSkills
Feature KickoffNew featuresproblem-statement, hypothesis, prd, user-stories, launch-checklist
Lean StartupRapid validationhypothesis, experiment-design, experiment-results, pivot-decision
Triple DiamondMajor initiativesAll 30 phase skills across 6 phases
Customer DiscoveryResearch to probleminterview-synthesis, jtbd-canvas, opportunity-tree, problem-statement
Sprint Planning (agile)Agile sprint-ready storiesrefinement-notes, user-stories, edge-cases
Product StrategyStrategic framingcompetitive-analysis, stakeholder-summary, opportunity-tree, solution-brief, adr
Post-Launch LearningShip to learninstrumentation-spec, dashboard-requirements, experiment-results, retrospective, lessons-log
Stakeholder AlignmentLeadership buy-instakeholder-summary, problem-statement, solution-brief, launch-checklist
Technical DiscoveryFeasibilityspike-summary, adr, design-rationale
Foundation Sprint2-day strategic alignment7 tool-foundation-sprint-* skills producing a testable Founding Hypothesis
Design Sprint5-day prototype + test7 tool-design-sprint-* skills producing a Decider’s build/iterate/pivot/stop call
Foundation to DesignEnd-to-end FS + DS arcBoth families chained with a narrative handoff conversation

All workflows

Recent Releases

Section titled “Recent Releases”
VersionDateHighlights
v2.26.02026-06-10Authoring + quality: /chain runs any ad-hoc skill sequence with go/no-go checkpoints, the new utility-pm-workflow-builder promotes proven chains into durable workflows, and all 26 original-generation skills gained “When NOT to Use” boundaries. Catalog grows 65 to 66.
v2.25.22026-06-10Maintenance patch: a single manifest now declares every release-gate validator, with an enforcing CI parity referee so the bash, PowerShell, and CI inventories cannot drift. Closes the 2026-06-06 audit.
v2.25.12026-06-06Maintenance patch: docs site moves to the family site/ layout (Pattern S), a generated CI-gated resource index, root-link repair with an enforcing guard, and an em-dash-scar cleanup.
v2.25.02026-06-03The plugin’s first hooks: opt-in house-rule guardrails and a confident-only phase router, plus an advisory output-quality CI tier. No new skills.
v2.24.02026-06-01utility-pm-workflow-orchestrator runs a prioritized action plan through its recommended pm-skills with go/no-go checkpoints. Ships EXPERIMENTAL. Catalog grows 64 to 65.
v2.23.02026-05-31foundation-prioritized-action-plan turns rough notes, transcripts, or a vague ask into one prioritized action plan with honest confidence levels. Catalog grows 63 to 64.
v2.22.02026-05-30One menu entry per skill: the 63 duplicate command wrappers are gone, so each capability shows once. Native Codex support added via a .codex-plugin manifest. All 65 skills unchanged.
v2.21.02026-05-26Marketplace launch: pm-skills now installs from the product-on-purpose plugin marketplace. The previous install path keeps working, so existing setups need no change.
v2.20.02026-05-25Each workshop methodology is now a single command: /workflow-foundation-sprint, /workflow-design-sprint, and /workflow-foundation-to-design chain their per-day skills end to end.
v2.19.02026-05-23Pre-promotion hardening: new validators catch stale counts, dead links, and references to skills that do not exist before they can ship. Nothing you use behaves differently.

All releases · Full changelog

Section titled “Links”