product-manager

Plugin product-manager from marketplace truecast in wastedcode/truecast. Commands read from the repo's manifest — 27 days ago.

Skills (17)

• account-for-distribution

  Use when a build is proposed with no path to reach users — force distribution (channel + activation + retention loop) into the product decision. "Build it and they will come" is a failure mode, not a plan.

• beat-the-frontier

  Use before any substantive product deliverable (PRD, strategy, prioritization, scope call, decision request) and as the last pass before handing it over — your version of the engine's "beat the frontier" loop. Name who does this kind of product work best today, set the bar above them, pre-empt every

• capture-decisions

  Use whenever a load-bearing call is made (or asked again) — record problem, options, what was chosen, why, and what was rejected, so settled questions aren't re-litigated and "why did we do it this way?" always has an answer.

• coherence-over-piecemeal

  Use when scoping any user-facing surface — require a whole-surface design up front; ship in slices, but each slice lands in its final place, nothing bolted on to be re-placed later.

• continuous-discovery

  Use to find real problems and generate options before converging — structure the work as an Opportunity Solution Tree (outcome → opportunities → solutions → tests), talk to users weekly, and produce multiple options, not the first one.

• define-success-metrics

  Use when defining what "success" means for a feature/initiative, when picking a metric, or when a number looks suspiciously good — choose a North Star + guardrails, reject vanity, and defend against Goodhart/gaming.

• eval-driven-ai-product

  Use when the feature is AI/LLM-powered (generation, summarization, classification, agents, RAG) — its acceptance is an EVAL, not "it runs." Define the dataset, graders, thresholds, and failure taxonomy before shipping.

• frame-the-job-jtbd

  Use when scoping or describing a feature — reframe it as the job the user is hiring it for (the outcome in their words), not the feature itself.

• interrogate-the-founder

  Use when a load-bearing fact is unknown — ask the founder the few questions you cannot responsibly default; propose defaults for the reversible ones; fill placeholders, never invent.

• pressure-test-personas

  Use to validate a feature against real users — build a persona dossier and walk that specific person through the journey to find where it breaks for THEM.

• prioritize-tradeoffs

  Use when there's more worth building than time to build it, or two good options compete — make the tradeoff explicit, pick one, and say what you're NOT doing and why.

• problem-first-prd

  Use when writing a spec for a feature or a one-way-door decision — a Working-Backwards PRD whose whole top half is WHY before any WHAT.

• right-size-the-build

  Use when deciding how much process a piece of work needs — match ceremony to stakes; full rigor for one-way doors, a lean path for a contained fix. Cut the ceremony, never the craft.

• run-a-rat

  Use before committing to build anything non-trivial — name the one assumption that, if wrong, kills the idea, and design the cheapest test that could falsify it, run BEFORE the build.

• set-strategy

  Use when asked "what should we build (next / at all)?", when the roadmap is turning into a stakeholder wishlist, or for a build-vs-buy call — set the strategic bet first and derive the work from it, don't collect wishes.

• track-truth-and-done

  Use when reporting status or accepting work — keep the board honest (in-progress only if truly in progress, done only if verified done) and CHECK the definition of done against reality, don't just declare it.

• user-interviews

  Use whenever you need to learn from real users — before/while building, validating a problem, or when stuck. Run Mom-Test interviews (ask about their life and past behavior, not your idea), continuously, and turn them into evidence.

Subagents (1)

• product-manager

  A product manager who keeps you building the right thing — married to the problem, not the solution. Discovery + user interviews + strategy + metrics + painkiller/scope/decision-capture/done-verification craft; delegates delivery.