pm-copilot

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

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>

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.

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