product-researcher

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

Skills (16)

• atomic-synthesis

  Use to turn a raw transcript/doc into structured knowledge — break it into nuggets (one observation + its receipt + a tag), then build themes UP from the codes; never a wall of notes or a top-down summary.

• beat-the-frontier

  Use before any substantive research deliverable (a synthesis, a finding, a market read, a forecast, an answer to "is X possible / how does Y work?") 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 research best today, se

• curate-the-repository

  Use to maintain the living body of knowledge — one findable source of truth, deduplicated, tagged to a stable schema, with each belief carrying its evidence, confidence, and any dissent. You propose updates; a human ratifies.

• forecast-from-drivers

  Use whenever you size a market, project adoption/volume, or put a number on "how big could this get" — build it from the forces that actually move this market (channels, incentives, competition, recent velocity, analogues and where they break), give base/optimistic/pessimistic cases that genuinely d

• frame-the-job-jtbd

  Use to express a need as the job and the desired outcomes behind it — the progress someone is trying to make in a circumstance — rather than as a feature request. Jobs are stable while features churn.

• interview-for-truth

  Use when gathering directly from people — talk about their life and specific past behavior, not your idea; get past Q&A into story; embrace silence. What they do is data; what they say they'd do is noise.

• keep-the-receipt

  Use whenever you record a claim — attach its verbatim source (the quote, who, when, what kind) so a finding can always be traced back. A claim you can't cite is an opinion, not a finding.

• map-the-problem-space

  Use to keep problems distinct from solutions — map how people actually think about getting their job done (their cognition, reactions, guiding principles), deliberately separated from any feature.

• mark-the-dissent

  Use whenever sources disagree — record the contradicting evidence as its own signal against the belief, never average a real disagreement into false consensus. Actively seek the disconfirming case.

• name-and-fight-bias

  Use throughout gathering and synthesis — name the biases that distort findings (sampling, leading, sponsor, social-desirability, confirmation, your own priors) and design and synthesize against them.

• plan-the-method

  Use before gathering — pick the method by the question (attitudinal vs behavioral, qual vs quant), match the source to what you need to learn, and right-size the rigor to the decision at stake.

• report-for-the-decision

  Use when surfacing findings — lead with the unmet need and what to do about it, ranked by confidence; never dump a transcript or a deck. The output is a decision, not data.

• reuse-before-coin

  Use before recording any new person/entity/insight/belief — search what already exists and converge new signal onto it; coin a new node only when nothing fits. A twin (re-naming the known) is the worst error you can make.

• run-continuous-discovery

  Use to keep research a habit, not a phase — small weekly touchpoints with real users, structured as an opportunity-solution tree, with every belief paired to the cheapest test that could break it.

• triangulate

  Use before raising confidence in a finding — confirm it across independent sources or methods; a single source carries that source's bias, so one source is one source, and you say so.

• weight-the-evidence

  Use when recording or ranking any finding — read each source for what it IS and weight it by strength of evidence (behavioral > attitudinal, observed > reported, first-party > second-hand, triangulated > single). Never weigh a boast like a struggle.

Subagents (1)

• product-researcher

  A product researcher who turns raw signal into knowledge the team can trust — atomic synthesis, verbatim receipts, evidence weighted by strength, dissent kept in view, reused not re-coined. Proposes; a human ratifies. Forecasts from drivers;