Skill Claude Code
Help PMs navigate organization politics, simulate stakeholder/peer feedback when people aren't in the room, and run politics checks on plans and communication.
not rated 234
changed 10d ago A 33 tokens
Agent Claude Code
Mid-tier, read-only independent quality check of a drafted PM artifact (PRD, OKRs, roadmap, North Star, opportunity assessment, one-pager, strategy doc). Use before presenting a non-trivial artifact as done, or when the user asks to evaluate one. Independent so the coach isn't grading its own work.
not rated 234
changed today A 69 tokens
Agent Claude Code
Fast-tier, read-only scan of PM Brain context. Use proactively before coaching or drafting when the conversation names a stakeholder, initiative, external org, past decision, or company topic — returns a short summary of what the repo already knows plus any contradictions with logged decisions. Keeps the main coaching…
not rated 234 today A 66 tokens
Agent Claude Code
Role-plays a named stakeholder from their PM Brain avatar to pressure-test a plan, message, or decision. Use for "what would [name] say?", panel reactions, or a politics check before a big conversation. Runs isolated so the simulation stays sharp instead of being softened by the coaching voice.
not rated 234 today A 65 tokens
Skill Claude Code
Ship and spec AI features, LLM products, agents, copilots, and generative UX — including when to use a model vs. rules, prompt and context design, human-in-the-loop, safety guardrails, offline/online evals, golden sets, regression testing for AI, cost/latency budgets, and agent specs structured like PRDs (goals…
not rated 234 today A 170 tokens
brain-review
06Skill Claude Code
Review files or folders in the PM Brain repo for quality, freshness, consistency, and system health. Slash-command style — invoke when the user explicitly asks for a repo review, context health check, or alignment pass on an initiative folder. Not for auto-invocation on casual chat.
not rated 234 today A 60 tokens
braindump
07Skill Claude Code
Coach product sense through unstructured thinking before any framework or template. Use when the user is thinking aloud, stuck, wants to get unstuck, developing product sense, or needs to pressure-test a decision without jumping to docs. Do not suggest templates until the braindump floor is met.
not rated 234 today A 62 tokens
Skill Claude Code
Plan customer discovery, turn interview snapshots into synthesis and evidence-based opportunities, build or update an Opportunity Solution Tree, map jobs and segments, and design RAT tests for the riskiest assumption. Use when the user says "synthesize interviews", "what did we learn from research", "turn notes into…
not rated 234
changed today A 170 tokens
Skill Claude Code
Partner effectively with engineering and design — feasibility and scope negotiation, tech debt tradeoffs, design reviews, discovery with builders, and PRD handoffs that don't get thrown away. Covers what eng needs, what design needs, how to frame debt, and language for hard conversations. Use when the user says "work…
not rated 234 today A 115 tokens
Skill Claude Code
Evaluate quality of a PM artifact or substantive session output using the shared evaluation procedure — gut check, red/green flags, optional full scored review. Use when the user says "evaluate this", "is this good enough", "quality check", "review the PRD/OKR/roadmap we just wrote", or after finishing an artifact.…
not rated 234
changed today A 81 tokens
Skill Claude Code
Design and run product experiments at a practical PM level — A/B tests, hypothesis tests, rollouts, feature flags, and reading results without pretending to be a statistician. Covers hypothesis, primary metric, sample and duration, guardrails, and ship/kill/pivot calls. Use when the user says "A/B test", "experiment…
not rated 234 today A 117 tokens
launch-gtm
12Skill Claude Code
Plan, tighten, or review a product launch and go-to-market motion: rollout phases, beta and GA readiness, sales enablement, marketing launch, and release comms (internal and external). Use when the user says "launch plan", "go-to-market", "GTM", "rollout", "beta launch", "GA", "general availability", "sales…
not rated 234 today A 0 tokens
north-star
13Skill Claude Code
Define, sharpen, or audit a North Star metric and its input metrics tree, and decide which product metrics actually matter (leading vs. lagging, guardrails, vanity vs. actionable, AARRR pirate metrics funnel). Use when the user says "define our north star metric", "what metric should we track", "what should we…
not rated 234
changed today A 130 tokens
okr
14Skill Claude Code
Write, draft, review, or fix OKRs (objectives and key results) for a team, product area, or quarter, and run weekly confidence check-ins, mid-cycle adjustments, and end-of-cycle grading. Use when the user says "write OKRs", "draft our quarterly objectives", "turn our strategy into OKRs", "are these good key results"…
not rated 234
changed today B 123 tokens
Skill Claude Code
Assess whether an idea or initiative is worth pursuing before a PRD, using the Opportunity Assessment framework (objective, target customer, metrics, what we know, research plan, solution ideas, risks). Use when the user asks "is this worth pursuing", "should we build this", "assess this opportunity", "opportunity…
not rated 234
changed today A 124 tokens
prioritize
16Skill Claude Code
Prioritize a backlog, features, initiatives, or bugs, and pick and run the right method (RICE, ICE, Impact–Effort, MoSCoW, Kano, severity × frequency). Use when the user asks "what should we build first", "help me prioritize", "rank these", "MVP scope", "what makes the cut", "sprint or quarterly planning", or is…
not rated 234 today A 103 tokens
roadmap
17Skill Claude Code
Build, restructure, or review a product roadmap, including Now/Next/Later, outcome-based, theme-based, scenario and rolling roadmaps, with confidence levels and time ranges instead of hard dates. Use when the user says "build a roadmap", "now/next/later", "outcome roadmap", "plan the next quarters", "what goes on the…
not rated 234
changed today C 126 tokens
Skill Claude Code
Write, tighten, or review written stakeholder communication: one-pagers, exec summaries, decision docs, status updates, newsletters, sprint summaries and sprint review updates, meeting agendas, escalations, saying no or pushing back on a request, decision records and ADRs. Use when the user says "write a one-pager"…
not rated 234 today A 0 tokens
strategy
19Skill Claude Code
Draft, test, or review a product, team, or company strategy, using the Good Strategy/Bad Strategy kernel (diagnosis, guiding policy, coherent actions), the Playing to Win cascade (where to play, how to win), or a team strategy doc built on pillars and explicit non-goals. Use when the user says "product strategy"…
not rated 234 today A 153 tokens
Skill Claude Code
Plan or close the week using PM cadence rituals, draft the weekly note (YYYY-Www.md), resolve due decisions, and run the Friday drift sweep across decisions, live assumptions, initiatives, and context. Use when the user says "weekly review", "plan my week", "Friday wrap", "drift sweep", or invokes week planning.
not rated 234 today A 72 tokens
write-prd
21Skill Claude Code
Write, draft, tighten, or restructure a PRD, product spec, requirements doc, or feature spec, including JTBD-style PRDs and user stories with Given/When/Then acceptance criteria. Use when the user says "write the PRD", "spec this out", "draft requirements", "turn this into a PRD", or "help me write up what we're…
not rated 234
changed today A 90 tokens
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: