riadchaban994-bot
UserProduct discovery for AI agents, done properly. Seven skills that route any discovery question to the method your evidence can support, and refuse to invent a customer, a number, or a confidence level.
Categories
Indexed Skills (8)
discovery-experiments
Use when deciding whether to build something, when an idea needs testing before commitment, when mapping assumptions or risks behind a solution, when designing an A/B test or any other experiment, when a test needs a success threshold, when analysing whether a change caused a result, or when a fake door, concierge, Wizard of Oz or pricing test is being planned.
discovery-interviewing
Use when planning, writing, or running customer interviews, when recruiting or screening participants, when a user interview produced nothing useful, when moderating a research session, when practising interview technique before a real session, or when writing up an interview.
discovery-ops
Use when setting up a discovery practice, when research keeps being a one-off project instead of a habit, when recruiting participants is the bottleneck, when past research cannot be found or gets redone, when discovery findings are not reaching stakeholders, or when scheduling and automating the recurring parts of research.
discovery-prototyping
Use when an idea needs to become something people can react to, when choosing prototype fidelity, when building a clickable prototype, fake door page, or Wizard of Oz operator console, when preparing to test a design with users, or when deciding how much to build before testing.
discovery-quant
Use when a product metric moved and the cause is unknown, when designing what to measure for a feature or outcome, when analysing funnels, cohorts, retention or churn, when working out how many users a test needs, when analysing a survey, or when a number in a document needs checking before anyone acts on it.
discovery-synthesis
Use when turning raw research into findings, when coding transcripts, notes, support tickets, sales calls, reviews or survey verbatims, when building an opportunity solution tree or experience map, when deciding whether enough interviews have been done, or when a pile of research needs to become a decision.
product-discovery
Use when deciding what to build or whether to build it, when a product idea needs validating, when a metric moved and nobody knows why, when planning or running user interviews, when raw research needs synthesising, when designing an experiment or prototype test, when sizing or prioritising opportunities, when auditing a PRD or roadmap for unsupported claims, or when setting up a continuous discovery practice.
tracking-plan-discovery
Walk any app hands-on and build or update a real product-analytics tracking plan from what you actually see. Use this whenever someone needs an event taxonomy, a tracking plan, a measurement plan, an analytics spec, an event dictionary, instrumentation for GA4 / Firebase / Amplitude / Mixpanel / Segment / PostHog, or wants to audit or extend tracking that already exists. Use it when the ask is "what should we track", "our analytics are broken", "we have no funnel data", "design the events for this feature", "map the user journeys", or "the dev team needs a spec". It drives an Android emulator, an iOS simulator, a browser or a Figma file, screenshots every surface, groups parameters into reusable attribute packs, grades every event by how strong the evidence for it actually is, and ships a phased, buildable Excel workbook with embedded screenshots. Works for any app in any industry. Reach for it even when the person only says "events" or "instrumentation" and has not used the words tracking plan.
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.