Product Discovery

What this skill helps you do

Runs structured product discovery to identify high-value opportunities and de-risk product bets before committing delivery resources. Facilitates Opportunity Solution Tree (OST) building from measurable outcomes through opportunities, solutions, and experiments tied to evidence sources. Maps assumptions across desirability, viability, feasibility, and usability with risk/certainty scoring, prioritizing high-risk/low-certainty items for early testing. Provides problem validation techniques (interviews, journey mapping) and solution validation methods (prototypes, concept tests, fake-door experiments). For ecommerce operators, this validates which new products, features, or store improvements to build before investing development or supplier resources.

Install and get started

Copy the full instructions into your AI tool. Test one low-risk example before connecting real store data.

Original Skill instructions

You are a product discovery facilitator. De-risk product bets: 1) Define one measurable outcome with baseline and target. 2) Build an Opportunity Solution Tree: Outcome → Opportunities (user evidence, not opinions) → Solutions → Experiments. Require ≥3 distinct opportunities before converging, ≥2 experiments per top opportunity. 3) Map assumptions across desirability, viability, feasibility, usability — score by risk/certainty; test high-risk/low-certainty first. Use assumption_mapper.py for scoring. 4) Validate problems via interviews and behavior analysis; validate solutions via prototypes, concept tests, fake-door experiments. 5) Plan 10-day sprint with daily evidence reviews. End with: proceed, pivot, or stop. Tie every branch to evidence.

Useful tasks

• Validate whether a new product category is worth adding to your store before sourcing
• Map and test assumptions about customer pain points before building features
• Run a 10-day discovery sprint for a new checkout flow or UX improvement
• Prioritize your product roadmap using evidence-based opportunity scoring
• Test solution concepts with prototypes before committing to supplier resources

How to use it

• Identify at least 3 distinct opportunities before converging on any solution
• Run at least 2 experiments per top opportunity to avoid false positives
• Use the assumption_mapper.py script to automate risk/certainty scoring from CSVs
• Tie every OST branch to a specific evidence source — ban internal opinions
• High-risk + low-certainty assumptions get tested first; do not lead with safe bets

More skills for this workflow

• Market Research

  Triangulated TAM/SAM/SOM sizing, survey sampling with per-segment floors, Kotler scoring.

• Competitive Teardown

  12-dimension scoring, SWOT, pricing analysis, UX audits, and stakeholder battle cards.

• Product Strategist

  OKR cascade generator with 5 strategy types and alignment scoring for product leadership.

• Necessity Review Mining Selection Rijoy

  VOC-based product selection and improvement via review pain-point mining with Rijoy.