phuryn/pm-skills

A/B Test Analysis evaluates A/B test results with statistical significance, sample size validation, confidence intervals, and ship/extend/stop recommendations. Use when interpreting split test data, checking if a test reached significance, or deciding whether to ship a variant.

Beachhead Segment identifies the first beachhead market segment for a product launch by evaluating segments against burning pain, willingness to pay, winnable market share, and referral potential. Use it when choosing a first market, targeting an initial customer segment, or planning market entry strategy.

Brainstorm Team OKRs generates three alternative OKR sets aligned with company strategy, each with a qualitative objective and three measurable key results. Use when setting quarterly OKRs, aligning team goals with company strategy, drafting objectives, or learning how to write effective OKRs.

Cohort Analysis helps analyze user engagement and retention patterns by cohort to identify trends in user behavior, feature adoption, and long-term engagement. Use it when studying retention curves, feature adoption over time, churn patterns, or engagement trends.

Competitive Battlecard creates sales-ready battlecards comparing your product against a specific competitor, including positioning, feature comparison, objection handling, and win/loss patterns. Use it when preparing sales teams, creating competitive materials, or answering 'why not competitor X?'

Create PRD guides an agent through writing a Product Requirements Document using an 8-section template covering problem, objectives, segments, value propositions, solution, and release planning. Use it when drafting a PRD, documenting product requirements, preparing a feature spec, or reviewing an existing PRD.

Dummy Dataset Generation creates realistic dummy datasets for testing with customizable columns, constraints, and output formats such as CSV, JSON, SQL, or Python scripts. Use it when you need sample data for development, demos, or populating test environments.

GTM Motions evaluates seven go-to-market approaches—inbound, outbound, paid digital, community, partner, ABM, and PLG—and recommends the best motion stack and tools for a product. Use it when selecting marketing channels, comparing inbound vs outbound, or planning cross-channel campaigns.

Growth Loops identifies and evaluates five loop types (viral, usage, collaboration, user-generated, referral) to design sustainable product-led growth. Use it when building growth mechanisms, reducing paid acquisition, or analyzing competitor strategies.

Intended vs Implemented compares documented requirements against actual code to find security and correctness gaps that generic scanners miss, citing both documentation and implementation evidence for each finding. Use it when auditing AI-built code, access control, or whether a codebase matches its own documentation.

Job Stories creates job stories using the 'When [situation], I want to [motivation], so I can [outcome]' format with detailed acceptance criteria. Use when writing job stories, creating JTBD-style backlog items, or expressing user situations and motivations.

Outcome Roadmap transforms an output-focused roadmap into an outcome-focused one that communicates strategic intent, rewriting initiatives as outcome statements reflecting user and business impacts. Use when shifting to outcome roadmaps or making a roadmap more strategic.

Pre-Mortem runs a pre-mortem risk analysis on a PRD or launch plan, imagining launch failure to surface hidden concerns. It categorizes risks as Tigers, Paper Tigers, and Elephants, classifies launch-blocking, fast-follow, or track items, and produces mitigation action plans.

Prioritization Frameworks is a reference guide to 9 prioritization frameworks—including RICE, ICE, Kano, MoSCoW, and Opportunity Score—with formulas, when-to-use guidance, and templates. Use it to select a prioritization method or compare frameworks.

Release Notes turns tickets, PRDs, or changelogs into polished, user-facing release summaries organized by category. Use when writing release notes, creating changelogs, announcing product updates, or summarizing what shipped.

SQL Queries generates SQL statements from natural language descriptions and supports BigQuery, PostgreSQL, MySQL, and other dialects. It reads database schemas from uploaded diagrams or documentation so you can write SQL, build data reports, explore databases, or translate business questions into queries.

Shipping Artifacts defines the durable documentation set that makes an AI-built app reviewable before shipping: architecture, user/permission flows, variables/secrets, and a test-coverage map, plus conditional docs for emails, cron, SEO, and embedded agents. Use when documenting a codebase for handoff, mapping trust boundaries, planning test coverage, or preparing for security or performance

Sprint Planning estimates team capacity, selects and sequences stories, maps dependencies, and identifies risks. Use it to prepare for sprint planning, balance scope against velocity, and define a clear sprint goal.

Sprint Retrospective Facilitator guides a structured sprint retrospective, identifying what went well, what didn't, and prioritized action items with owners and deadlines. Use it when running a retrospective, reflecting on a sprint, or turning team feedback into actionable improvements.

Stakeholder Map builds a power/interest grid of stakeholders and generates a tailored communication plan for each quadrant. Use it to manage stakeholders, align cross-functional teams, or prepare for a launch.

Strategy Red Team attacks the load-bearing assumptions in a PRD, roadmap, or strategy before reality does. It steelmans each claim, ranks failure modes by impact × likelihood × cheapness-to-test, and returns the cheapest test and kill criteria. Use when stress-testing a plan or preparing a doc for executive review.

Summarize Meeting turns transcripts into structured meeting notes with date, participants, topic, key decisions, summary points, and action items. Use it to process meeting recordings, create minutes, or recap discussions.

Test Scenarios creates comprehensive test scenarios from user stories, including test objectives, starting conditions, user roles, step-by-step actions, and expected outcomes. Use it when writing QA test cases, creating test plans, defining acceptance tests, or validating feature implementations.

User Stories breaks down features into user stories following the 3 C's and INVEST criteria, with descriptions, design links, and acceptance criteria. Use when writing user stories, creating backlog items, or defining acceptance criteria.

Why What Acceptance creates product backlog items in Why-What-Acceptance format, producing independent, valuable, testable items with strategic context. Use it when writing structured backlog items, breaking features into work items, or communicating strategic intent to teams.