Get briefed — loads your full memory, pulls live state from all connected tools, surfaces risks, staleness, upcoming milestones, and gives you a prioritized briefing so you're never starting blank

Run a competitive intelligence analysis — landscape mapping, battlecards, 7 Powers moat comparison, positioning gaps, and monitoring plan

Design an AI-powered feature end-to-end — model selection, prompt architecture, eval framework, failure modes, cost modeling, and improvement flywheel

Run a full discovery cycle — problem framing, JTBD demand-side analysis, assumption mapping, opportunity sizing, and OST mapping — from a rough idea to validated opportunity

Set up PM Copilot — a guided wizard that builds your persistent memory profile so every future session is grounded in your product context

Plan a full go-to-market launch — positioning, messaging hierarchy, ICP definition, launch timeline, rollback plan, and post-launch measurement

Plan the upcoming sprint — epic breakdown, user story decomposition, RICE prioritization, dependency check, and capacity allocation

Run a post-ship retrospective — measure outcomes vs. predictions, extract lessons, update memory, and feed insights back into the PM system

Build or review your roadmap — OKR alignment, Now/Next/Later structuring, dependency mapping, and stakeholder views, pulling live Linear/Jira state

Structure OKRs — define objectives, write measurable key results, align to strategy, stress-test for quality, and cascade across teams

Set up your metrics framework — North Star selection, funnel definition, dashboard structuring, and A/B test design for your key bets

Generate tailored stakeholder updates by audience — pulls live tracker state from Linear/Jira, formats by audience (exec / engineering / customer) using Pyramid Principle

Run a full strategic review — competitive positioning, 7 Powers moat assessment, strategy stack audit, and pre-mortem on current bets

Synthesize user research into OST opportunity areas — ingests interview transcripts, survey data, or Notion docs; extracts themes, persona signals, and evidence map

Triage a batch of user feedback — cluster themes, score by frequency × severity × strategic fit, route top issues to roadmap or experiments

Generate your weekly PM digest — pulls roadmap state, open risks, metrics movement, stakeholder actions, and upcoming milestones into one actionable summary

Write a complete PRD from an idea — JTBD analysis, user stories, success metrics, and a prototype-ready spec appendix, all wired to your memory

Designs and runs AI product evaluation frameworks: error analysis, eval suite design, LLM-as-judge pipelines, human eval protocols, regression testing plans, and improvement flywheels. Use this agent when the user is building an AI-powered feature and needs to define how to measure quality, catch regressions, or systematically improve model outputs. <example> Context: User shipped an AI feature and is seeing quality complaints but can't quantify them. user: "Our AI summaries are getting complaints. Help me build an eval framework." assistant: "I'll design an eval suite: error taxonomy, LLM-as-judge pipeline, and regression tests..." <commentary> Multi-step AI evaluation requiring error categorization (open coding → axial coding), eval suite design with golden datasets, and LLM-as-judge rubric construction. The ai-evaluator agent handles this specialized work in isolation. </commentary> </example> <example> Context: User is about to change their AI model or prompt and needs to ensure quality doesn't regress. user: "We're switching from GPT-4 to Claude for our chatbot. Design regression tests." assistant: "I'll build a regression testing plan with golden sets and quality gates..." <commentary> Regression testing design requiring golden dataset construction, pass/fail criteria, and automated comparison pipeline. Specialized quantitative work that benefits from focused context. </commentary> </example>

Runs deep product discovery research: problem framing, JTBD demand-side analysis, assumption mapping, opportunity sizing, and opportunity-solution tree mapping. Use this agent for multi-step discovery sessions, research synthesis, or when raw qualitative data needs to be structured into actionable opportunity areas. <example> Context: User wants to explore a problem space before committing to a solution direction. user: "I'm hearing complaints about our onboarding flow. Run discovery on this." assistant: "I'll run a full discovery analysis on your onboarding experience..." <commentary> Multi-step discovery requiring problem framing, JTBD analysis, assumption mapping, and opportunity-solution tree construction. The discovery-researcher agent handles this heavy research in isolation and returns structured findings. </commentary> </example> <example> Context: User has raw interview transcripts and needs synthesis into opportunity areas. user: "I did 8 user interviews about our billing flow. Synthesize the findings." assistant: "I'll analyze the transcripts and synthesize into opportunity areas..." <commentary> High-volume qualitative data synthesis that benefits from isolated context. The agent applies continuous discovery and JTBD frameworks to extract themes, switching triggers, and unmet needs from raw research data. </commentary> </example>

Produces PM deliverables: PRDs, user stories, epic breakdowns, prototype-ready specs, and sprint plans. Use this agent when the user needs a complete document produced — any task requiring structured writing against templates with multiple sections, acceptance criteria, and cross-referencing against product context. <example> Context: User has validated an opportunity and needs to turn it into a shippable PRD. user: "Write a PRD for the new collaborative editing feature." assistant: "I'll produce a complete PRD using your template and product context..." <commentary> Full PRD authoring requiring template application, persona cross-referencing, success metrics definition, and user story decomposition. The document-writer agent handles this multi-section production in isolation. </commentary> </example> <example> Context: User needs to break a large initiative into shippable increments. user: "Break down our payments migration into epics with user stories." assistant: "I'll decompose the initiative into sequenced epics with stories..." <commentary> Epic breakdown and user story decomposition requiring dependency mapping, acceptance criteria, and INVEST validation. Heavy structured output that benefits from isolated context. </commentary> </example>

Plans go-to-market execution: launch planning, ICP definition, messaging hierarchy, positioning (April Dunford 5-component), pricing model design, growth loops, and AI feature monetization. Use this agent when the user needs to plan how to bring a product or feature to market — any task requiring multi-constraint GTM planning that balances positioning, pricing, and channels. <example> Context: User is launching a new feature and needs a full GTM plan. user: "We're shipping AI-powered search next month. Plan the go-to-market." assistant: "I'll build a full GTM plan: positioning, messaging, ICP, and launch timeline..." <commentary> Full GTM planning requiring ICP definition, April Dunford positioning exercise, messaging hierarchy, launch timeline, and measurement plan. The gtm-planner agent handles this multi-constraint planning in isolation. </commentary> </example> <example> Context: User needs to evaluate or redesign their pricing model. user: "We're losing deals on pricing. Help me rethink our pricing tiers." assistant: "I'll analyze your pricing against value metrics and competitive anchors..." <commentary> Pricing analysis requiring value metric identification, tier design, willingness-to-pay estimation, and competitive benchmarking. Multi-dimensional planning work. </commentary> </example>

Runs market and user research analysis: persona development, journey mapping, TAM/SAM/SOM sizing, competitor battlecards, feedback triage, and attitudinal segmentation. Use this agent when the user needs to understand their market, users, or competitive landscape — any task requiring structured analysis of external signals and user behavior data. <example> Context: User is entering a new market and needs to understand the landscape. user: "We're expanding into SMB. Build me personas and size the market." assistant: "I'll run market research: persona development and TAM sizing for SMB..." <commentary> Multi-step market analysis requiring persona construction from behavioral data, TAM/SAM/SOM estimation, and competitive context. The market-researcher agent handles this research-heavy work in isolation. </commentary> </example> <example> Context: User has a pile of customer feedback and needs it structured into themes. user: "We have 200 Intercom tickets about our API. Triage and prioritize them." assistant: "I'll triage the feedback, cluster themes, and score by impact..." <commentary> High-volume feedback triage requiring theme clustering, frequency/severity/fit scoring, and routing recommendations. The agent processes the volume in isolation and returns a prioritized summary. </commentary> </example>

Handles quantitative PM work: North Star metric selection, funnel analysis, cohort analysis, A/B test design, dashboard structuring, and SQL generation. Use this agent when the user needs to define, measure, or analyze product metrics — any task requiring statistical reasoning, metric framework design, or data-informed decision support. <example> Context: User is setting up their metrics framework from scratch. user: "Help me pick a North Star metric and build a measurement framework." assistant: "I'll analyze your product to select a North Star and design the framework..." <commentary> Multi-step metrics work requiring North Star selection criteria, funnel definition, and dashboard structuring. The metrics-analyst agent runs the full framework design in isolation. </commentary> </example> <example> Context: User wants to design an A/B test for a specific feature change. user: "Design an A/B test for our new checkout flow. We get 5k daily transactions." assistant: "I'll design a rigorous test with hypothesis, sample size, and analysis plan..." <commentary> A/B test design requiring hypothesis formulation, sample size calculation, guardrail metric selection, and analysis plan. Quantitative work that benefits from focused context. </commentary> </example>

Produces audience-tailored stakeholder communications: executive summaries, engineering briefs, launch announcements, risk escalations, and weekly digests. Use this agent when the user needs to communicate the same information to different audiences, or when a communication requires careful tone calibration for a specific stakeholder group. <example> Context: User needs to communicate a launch to three different audiences simultaneously. user: "We're shipping the new dashboard next week. Write updates for exec, eng, and customers." assistant: "I'll produce three audience-tailored updates for the dashboard launch..." <commentary> Multi-audience communication requiring Pyramid Principle for execs, context-first for engineering, and narrative for customers. The stakeholder-communicator agent handles tone calibration across all three in isolation. </commentary> </example> <example> Context: User needs to escalate a risk to leadership with options and a recommendation. user: "Our data migration is at risk of slipping 3 weeks. Help me escalate this." assistant: "I'll draft a clear, action-oriented risk escalation for leadership..." <commentary> Risk escalation requiring calm framing, options table, impact assessment, and a clear recommendation. The agent balances urgency with professionalism. </commentary> </example>

Runs strategic analysis frameworks: competitive positioning, 7 Powers moat assessment, strategy stack audits, pre-mortems, and beachhead market selection. Use this agent when the user needs to evaluate strategic direction, stress-test a bet, or compare positioning options — any task requiring multi-framework strategic reasoning in isolation. <example> Context: User is considering entering a new market segment and needs strategic validation. user: "We're thinking about going upmarket to enterprise. Run a strategy review." assistant: "I'll run a full strategic analysis on the enterprise move..." <commentary> Multi-framework strategic analysis requiring 7 Powers moat check, beachhead evaluation, competitive positioning, and pre-mortem. The strategy-analyst agent runs these in sequence and returns a scored assessment. </commentary> </example> <example> Context: User needs to stress-test an upcoming initiative before committing resources. user: "We're about to bet big on AI search. What could go wrong?" assistant: "I'll run a pre-mortem and strategic risk assessment..." <commentary> Pre-mortem combined with competitive and moat analysis. The agent applies multiple strategic lenses to surface risks the team hasn't considered. </commentary> </example>

Use this skill when the user asks to "design an A/B test", "how should I test this", "experiment design", "how do I run an experiment", "test this feature", "set up a split test", "how many users do I need", "statistical significance", "how do I know if this test worked", or wants to design a rigorous experiment to test a product hypothesis.

Use this skill when the user asks specifically about "how to monetize AI features", "should AI be a separate tier", "pricing for AI capabilities", "how to charge for AI", "AI add-on vs. bundle", "AI feature pricing strategy", or is adding AI capabilities to an existing product and wants to decide how to monetize them. This is a specialized version of pricing-review focused on AI feature economics.

Use this skill when the user asks about "altitude and horizon framework", "Shreyas Doshi altitude", "working at the right level", "am I too in the weeds", "I'm too tactical", "how do I work at the right altitude", "horizon thinking for PMs", or wants to evaluate whether they're operating at the right level of abstraction for their role and stage.

Use this skill when the user asks to "map assumptions", "identify assumptions", "what are we assuming", "assumption audit", "what could go wrong with this idea", "test our assumptions", "what do we need to validate", "identify our riskiest assumption", or when reviewing an idea or PRD and wants to surface hidden bets before building. Do NOT use this skill for general risk analysis — that is part of the pre-mortem skill.

Use this skill when the user asks about "attitudinal segmentation", "segmenting by attitude", "AI embracer vs skeptic", "how to segment our users beyond demographics", "psychographic segmentation", "behavioral segmentation", "how users feel about AI", or wants to go beyond demographic user segments to understand attitudinal and behavioral differences that affect product and marketing decisions.

Use this skill when the user asks to "tailor this for different audiences", "write this for an exec vs. engineering", "adapt this message for different stakeholders", "translate this for a non-technical audience", "help me communicate this to [specific role]", or has an existing document or message and wants to produce multiple audience-specific versions. This is a rewriting skill — it takes existing content and adapts it, not generates from scratch.

Use this skill when the user asks about "beachhead market", "initial market", "where to start", "narrowing our target market", "first customer segment", "go narrow first", "crossing the chasm strategy", "wedge strategy", "who to focus on first", or wants to identify the specific niche to own before expanding. Also use this skill when the user is unsure which segment to prioritize among several options.

Use this skill when the user asks "how do I become a senior PM", "what does senior PM actually mean", "I want to get promoted to senior", "what's the difference between PM and senior PM", "I've been a PM for 2–3 years and want to grow", "my manager says I need to work more strategically", "I'm stuck at PM level", or wants to understand the specific behaviors and skills that separate a PM from a Senior PM. Do NOT use this skill for VP or CPO-level career questions — use solo-to-cpo for that.

Use this skill when the user asks about "cohort analysis", "retention cohorts", "how to read cohort data", "analyze my retention", "what does my cohort data say", "cohort retention curves", "D7/D30 retention", "how to improve cohort retention", or has cohort data they want to interpret and act on.

Use this skill when the user asks for "competitive analysis", "who are our competitors", "competitive landscape", "how do we compare to X", "competitive positioning", "how do we differentiate", "what's our competitive advantage", "are we differentiated", or wants to understand the competitive context and define how to win against alternatives. Also use this skill when preparing for a board meeting or investor conversation that includes competitive positioning.

Use this skill when the user asks for "competitor battlecards", "battlecard for [competitor]", "how do we beat [competitor]", "how do we handle objections about [competitor]", "competitive win/loss", "sales competitive guide", "how should sales talk about competitors", or needs a structured competitive comparison for sales, customer success, or internal strategy purposes.

Use this skill when the user asks to "synthesize interview notes", "analyze my user interviews", "what patterns are in my interviews", "help me with continuous discovery", "find the themes in these interviews", "what did I learn from these calls", "turn these interview notes into opportunities", or pastes or shares raw interview transcripts or notes from user conversations. This skill focuses on the interview synthesis step of continuous discovery, not general feedback analysis — use feedback-triage for support tickets or NPS data.

Use this skill when the user asks to "design a metrics dashboard", "what should be on my PM dashboard", "structure our analytics dashboard", "what metrics to track", "what should I put on a product dashboard", "build a metrics framework", or wants to design a coherent set of metrics and dashboard layout that drives good product decisions without creating information overload.

Use this skill when the user asks to "write an engineering brief", "brief the engineering team", "write a technical spec handoff", "summarize this PRD for engineers", "engineering kickoff doc", "write a spec for the dev team", "help me communicate this feature to engineering", or needs to translate a product decision or PRD into an engineering-ready communication that gives engineers the context to make good technical decisions.

Use this skill when the user asks to "break this initiative into epics", "structure this as epics", "how should I organize this work", "help me sequence this initiative", "epic planning", "what are the phases of this project", "initiative breakdown", or has a large initiative and wants to decompose it into manageable, ship-able phases with clear sequencing.

Use this skill when the user asks to "analyze AI errors", "error analysis for our AI feature", "open coding", "axial coding", "analyze model failures", "categorize AI mistakes", "find patterns in bad AI outputs", "what's wrong with our AI", or has a set of bad AI outputs and wants to understand what's failing and why. This is the first step in the AI eval methodology from Hamel Husain and Shreya Shankar.

Use this skill when the user asks to "design an eval suite", "build evals for my AI feature", "create an evaluation framework", "how do I evaluate my AI", "what evals should I run", "build an eval system", or wants to create a systematic evaluation framework for an AI-powered product feature. Typically run after error-analysis has identified the failure categories to prioritize.

Use this skill when the user asks to "write an exec summary", "summarize this for leadership", "write a summary for the CEO", "board update summary", "executive brief", "leadership update", "write this for C-level", or needs to communicate a complex situation, decision, or initiative status to senior leadership in a concise, structured format. Do NOT use this skill for full stakeholder updates with multiple audience versions — use stakeholder/audience-tailoring for that.

Use this skill when the user asks to "triage feedback", "analyze support tickets", "cluster feedback", "analyze NPS responses", "what are users complaining about", "find pain points in this feedback", "synthesize this customer feedback", or pastes a batch of raw feedback, tickets, or interview notes. This skill is for structured feedback triage and scoring. For interview-specific synthesis, use discovery/continuous-interview-synthesis. For full research synthesis with OST mapping, use /synthesize-research.

Use this skill when the user has a Figma design and wants to turn it into a working prototype, asks "how do I turn my Figma into a prototype", "Figma to code", "take this design and make it interactive", or wants to use AI coding tools to implement a design that already exists in Figma.

Use this skill when the user says "I'm the first PM", "founding PM", "I joined a startup as the only PM", "how do I set up PM processes from scratch", "no PM infrastructure exists", "I'm building the PM function", "what should a first PM do in 90 days", or is navigating the unique challenges of being an early-stage PM with no existing product management structure. Do NOT use this skill for general career progression — use solo-to-cpo for that.

Use this skill when the user asks to "analyze my funnel", "where are users dropping off", "funnel analysis", "conversion analysis", "activation funnel", "onboarding funnel", "purchase funnel", "what's my conversion rate", or has funnel data showing step-by-step drop-off rates and wants to diagnose where to focus.

Use this skill when the user speaks informally about their product work — voice-to-text style updates, venting about a stakeholder conversation, sharing what happened in a meeting, or saying things like "you won't believe what just happened", "quick update", "just got off a call", "heads up", "FYI", "thought you should know", or any unstructured narrative about work events. Also use when the user shares something that sounds like product context but without a clear request. Do NOT use this skill when the user is asking a specific PM question or requesting a deliverable — use the appropriate skill for that instead.

Use this skill when the user asks about "growth loops", "viral loops", "product-led growth", "PLG", "how does our product grow itself", "referral mechanics", "word of mouth", "how to build growth into the product", "organic growth", or wants to identify and design the mechanisms through which the product acquires more users through its own usage.

Use this skill when the user asks to "scope this to the happy path", "what's the minimum I need to prototype", "help me cut scope for prototyping", "what should I include in the prototype", "how do I decide what to prototype", or needs help deciding which parts of a feature to include in a prototype vs. which to defer. Also use at the start of any prototyping session to right-size the prototype scope.

Use this skill when the user asks to "design a human evaluation", "human eval process", "annotation guidelines", "how to set up human review of AI outputs", "how to get humans to evaluate AI quality", "build a labeling process", "create annotation criteria", or wants to set up a structured process for humans to evaluate AI output quality.

Use this skill when the user asks to "define our ICP", "ideal customer profile", "who is our best customer", "who should we target", "which customers should we focus on", "who buys fastest", "who gets the most value", "find our ICP", or wants to identify the specific type of customer most likely to buy, succeed, and expand.

Use this skill when the user asks about "continuous improvement for AI", "AI quality flywheel", "how do we keep improving our AI feature", "closing the eval feedback loop", "systematic AI improvement process", or wants to build a repeating process that continuously improves AI product quality over time rather than doing one-off fixes.

Use this skill when the user asks to "create a journey map", "user journey map", "map the user experience", "map the customer journey", "end-to-end user flow", "what does the user experience look like", "map the onboarding journey", or wants to visualize the full sequence of steps a user goes through to accomplish a goal — including touchpoints, emotions, and friction points.

Use this skill when the user asks about "jobs to be done", "JTBD", "what job are users hiring us for", "demand-side thinking", "what progress are users trying to make", "why do users switch to our product", "what are users really trying to accomplish", "forces of progress", "push pull analysis", or wants to understand user motivation beyond surface-level feature requests. Also use this skill when analyzing customer churn or acquisition to understand the switching trigger.

Use this skill when the user asks to "write a launch announcement", "announce this feature", "write a launch email", "product announcement", "release notes", "launch blog post", "feature announcement to customers", "write the Slack announcement for this launch", or is preparing to communicate a new feature or product to users, customers, or the public.

Use this skill when the user asks to "plan a launch", "create a launch plan", "how do I launch this feature", "launch checklist", "go-to-market plan for this feature", "launch timeline", "prepare for launch", or needs a structured plan for taking a feature or product from "ready to ship" to "in users' hands with people knowing about it".

Use this skill when the user asks to "set up LLM as a judge", "write an LLM judge prompt", "automate quality evaluation", "use Claude to evaluate outputs", "build an automated eval", "LLM-based evaluation", or wants to create a scalable automated evaluation system where one LLM grades the outputs of another LLM.

Use this skill when the user asks to "update my PM Copilot memory", "save this to my profile", "remember that", "update my context", "update my product context", "save this decision", "add this to my memory", "track this risk", "mark this risk as resolved", "add a lesson learned", "save these stakeholder notes", or any explicit request to persist information to the memory profile. Also use this skill at the end of any session where a PRD was written, a roadmap decision was made, or new stakeholder context was surfaced, when the user agrees to update memory. Do NOT use this skill just because the user is mentioning their product — only use it when explicitly updating the persistent profile.

Use this skill when the user asks to "write our messaging", "create a messaging framework", "what should our tagline be", "value proposition", "messaging hierarchy", "how do we talk about our product", "craft our positioning statement", "what's our one-liner", or needs to develop the core language that communicates product value to different audiences.

Use this skill when the user asks about "NLX design", "natural language experience", "conversational UX", "how to design an AI interaction", "conversation design", "how the AI should talk to users", "design the conversation flow", "AI UX design", or wants to design the natural language interaction patterns for an AI-powered feature. This is the UX design skill for conversational and AI-first interfaces.

Use this skill when the user asks "which metric should we focus on", "how do I choose between these metrics", "what's the best metric to track", "help me select our primary metric", "our metrics are confusing", "we have too many metrics", or wants to select a primary North Star from a set of competing metrics. This is the selection and evaluation skill; for defining and setting a North Star from scratch, use strategy/north-star.

Use this skill when the user asks about "north star metric", "what should our north star be", "define our north star", "key metric", "one metric that matters", "choosing our success metric", "how do we define success", "our product metric", or wants to select or evaluate a single metric that best represents value delivered. Do NOT use this skill for dashboard design — use metrics/dashboard-structuring for that.

Use this skill when the user asks to "write OKRs", "structure our OKRs", "help with quarterly goals", "OKR review", "are our OKRs good", "how do I write key results", "our objectives and key results", "check our OKRs", or wants to create, review, or improve their OKR structure. Also use this skill when the user's roadmap items don't clearly connect to stated objectives.

Use this skill when the user says "set up PM Copilot", "run onboarding", "I'm new here", "help me get started", "initialize my profile", "set up my context", "configure PM Copilot", or when `memory/user-profile.md` exists but has no content filled in (all fields are still placeholder comments). Also use this skill when the user asks for a "setup wizard" or says they want PM Copilot to know about their product. Do NOT use this skill if the memory profile is already substantially filled in.

Use this skill when the user asks to "size this opportunity", "how big is this problem", "opportunity sizing", "how many users are affected", "estimate the impact", "what's the ROI", "is this worth building", "how do I prioritize this against other opportunities", or wants to quantify the potential value of solving a specific problem. Do NOT use this skill for full market sizing (TAM/SAM/SOM) — use the market-users/tam-sizing skill for that.

Use this skill when the user asks about "opportunity solution tree", "OST", "Teresa Torres framework", "build my OST", "map opportunities to solutions", "how should we structure our discovery", "connect outcomes to opportunities", "continuous discovery framework", or wants to visually structure the relationship between outcomes, opportunities, and solutions. Also use this skill when a user has a list of ideas and wants to organize them against user outcomes.

Use this skill when the user asks to "create user personas", "develop personas", "write a persona", "define our users", "user profile", "who is our user", "help me define the target user", "create a user archetype", or wants to build or update structured user persona definitions grounded in research or known user characteristics.

Use this skill when the user asks to "apply April Dunford's framework", "five component positioning", "obviously awesome positioning", "dunford positioning", "help me with positioning", "full positioning exercise", "positioning workshop", or wants to go through the complete April Dunford positioning process from scratch. For a shorter competitive positioning analysis, use strategy/competitive-positioning instead.

Use this skill when the user asks to "write a PRD", "write a spec", "product requirements document", "generate a PRD", "turn this into a spec", "create product requirements", "write acceptance criteria", or explicitly asks for a PRD or product specification. This skill writes a full PRD. For a chained workflow with JTBD analysis, OST framing, and prototype-ready spec, use the /write-prd command instead. Do NOT use this skill if the user only wants to evaluate an idea strategically — use strategy-stack or the pre-mortem skill for that.

Use this skill when the user asks for a "pre-mortem", "failure analysis", "what could go wrong", "risks for this initiative", "stress test this plan", "anticipate failure", "what are we missing", or wants to proactively identify the ways a plan or initiative could fail before investing in it. Also use this skill before major launches or roadmap decisions. Do NOT use this skill for post-launch retrospectives — use lessons-learned capture for that.

Use this skill when the user asks to "review our pricing", "help me think through pricing", "should we change our price", "pricing strategy", "how should we price this", "pricing tiers", "is our pricing right", "freemium vs. paid", or wants to evaluate or design their product's pricing model.

Use this skill when the user asks to "frame a problem", "define the problem", "write a problem statement", "articulate the user problem", "what problem are we solving", "help me think through the problem", "is this the right problem to solve", "clarify the problem", or when a user presents an idea and needs help distinguishing the problem from the solution. Do NOT use this skill if the user is ready to write a full PRD — use the execution/prd-authoring skill or /write-prd command instead.

Use this skill when the user is confused about why their execution feels chaotic, when work isn't connecting to outcomes, when they ask "why does everything feel urgent but nothing moves the needle", when they ask about "Shreyas Doshi's framework", "3 levels of product work", "how to think about product strategy vs execution", or when they want to diagnose whether a problem is a strategy problem or an execution problem.

Use this skill when the user asks to "generate a prototype prompt", "write a prompt for v0", "create a Bolt prompt", "write a Lovable prompt", "generate a prompt for Cursor", or needs just the prompt text to paste into an AI coding tool — without the full vibe-coding coaching. This is the prompt generation skill; for guidance on using AI coding tools, use prototyping/vibe-coding.

Use this skill when the user asks to "create a prototype spec", "write a prompt for v0", "write a vibe-coding prompt", "turn this PRD into a prototype prompt", "create a Bolt prompt", "help me prototype this", "write a spec for Lovable", or wants to convert a PRD or feature description into a self-contained prompt that can be dropped directly into v0, Bolt, Lovable, or another AI coding tool. Also auto-invoked at the end of /write-prd to generate the prototype appendix.

Use this skill when the user asks to "prevent regressions in AI quality", "regression testing for AI", "how do I know if a prompt change broke something", "before/after evaluation for model changes", "catch quality regressions", or wants to set up a process that catches when a model update, prompt change, or system change has degraded AI output quality compared to before.

Use this skill when the user asks to "escalate a risk", "write a risk escalation", "how do I tell leadership about this problem", "write a blocker update", "how do I escalate this issue", "draft a message about this risk", "communicate this blocker", or needs to surface a significant risk, blocker, or problem to leadership in a way that drives action rather than panic.

Use this skill when the user asks about "7 powers", "Hamilton Helmer", "competitive moats", "how do we build a moat", "sustainable competitive advantage", "defensibility", "what makes us hard to copy", "long-term defensibility", or wants to evaluate which structural competitive advantages apply to their product and how to build them deliberately.

Use this skill when the user asks about "career path to CPO", "how do I become a CPO", "PM career progression", "path from PM to VP Product", "PM career growth", "how do I grow as a PM", "what does the PM career ladder look like", "solo PM to product leader", or wants to understand and plan their PM career trajectory from individual contributor to product leadership.

Use this skill when the user asks to "prioritize the sprint", "what should we build this sprint", "help me sequence the backlog", "sprint planning", "how to prioritize these items", "what should go first", "rank these tickets", "is this item worth doing this sprint", or wants to make sequencing decisions for the upcoming sprint or iteration.

Use this skill when the user asks to "write a SQL query", "help me query this data", "how do I get this metric from the database", "generate SQL for", "query for retention", "SQL to find churned users", "write a query for my analytics", or needs SQL to answer a specific product analytics question. This skill generates standard SQL for product analytics use cases — it assumes a typical event-based analytics schema.

Use this skill when the user asks to "review our strategy", "do we have a coherent strategy", "is our strategy working", "strategic review", "strategy audit", "is our roadmap strategic", "does our strategy make sense", "connecting vision to roadmap", or wants a holistic assessment of whether their product strategy is coherent and differentiated. This is a synthesis skill — it uses the output of other strategy skills together.

Use this skill when the user asks to "run a switch interview", "interview someone who switched to us", "interview someone who churned", "understand why users switch", "create interview guide for JTBD", "write an interview script for churn analysis", "how to interview users about their switching decision", or wants to design or debrief an interview specifically about the moment a user changed tools or workflows.

Use this skill when the user asks about "TAM", "total addressable market", "market size", "how big is this market", "SAM", "SOM", "market sizing", "how large is our opportunity", "market opportunity analysis", or needs to produce a defensible market size estimate for a pitch deck, strategic plan, or investment conversation.

Use this skill when the user asks about "working with engineers as a PM", "how technical should a PM be", "I feel out of my depth with engineers", "how to earn engineering trust", "how to read code as a PM", "should I learn to code", "bridging the gap with engineering", "technical credibility for PMs", or wants to develop the skills to partner more effectively with engineering teams. Do NOT use this skill for general career progression questions — use solo-to-cpo for that.

Use this skill when the user asks to "write user stories", "decompose this into user stories", "break this into stories", "write acceptance criteria for this feature", "turn this PRD into stories", "create a story map", "help me write stories for sprint planning", or has a feature or PRD and wants to decompose it into shippable units for engineering. Do NOT use this skill to write a full PRD — use prd-authoring for that.

Use this skill when the user asks to "vibe code this", "build this with AI", "help me use Cursor/v0/Bolt to build this", "vibe coding from my PRD", "how do I code this with AI", "turn this spec into code", or wants guidance on using AI coding tools (Cursor, GitHub Copilot, v0, Bolt, Lovable, Claude Artifacts) to prototype or build a feature from a product spec. This is a coaching skill — it helps the PM get the most out of AI coding tools, not write code directly.

Use this skill when the user asks to "write a product vision", "define our vision", "help me articulate where we're going", "vision statement", "long-term vision", "what should our 3-year vision be", "our product story", or wants to create or refine the aspirational direction for the product. Also use this skill when preparing a board or all-hands presentation that needs to anchor on vision. Do NOT use this skill for OKR setting — use strategy/okr-structuring for that.

Use this skill when the user asks to "write my weekly update", "weekly PM digest", "weekly report", "write my status update", "end of week summary", "weekly standup summary", "write the PM weekly", "update the team this week", or needs to produce a regular cadence update covering what shipped, what's in progress, and what's next.

Read issues, roadmap state, sprint backlog; write tickets; update status

Read Jira board, backlog, sprint state; create and update issues

Read and write spec pages, search knowledge base, pull meeting notes

Pull channel context, read thread sentiment, send stakeholder updates

Read issue backlog, check PR velocity, correlate engineering output with roadmap