product-discovery

This skill provides a structured framework for product managers, engineers, and founders to navigate the ambiguity of early-stage product development. By shifting the focus from output-based delivery to outcome-based discovery, it helps teams identify high-value opportunities and de-risk product bets before committing significant engineering resources. The agent acts as a facilitator for evidence-based decision-making, ensuring that every feature or intervention is grounded in user research and measurable data rather than internal speculation.

• Opportunity Solution Tree (OST) facilitation for connecting business outcomes to user needs and actionable experiments.

• Assumption mapping to categorize and prioritize risks across desirability, viability, feasibility, and usability dimensions.

• Structured problem validation techniques, including behavior analysis, journey friction mapping, and user interview synthesis.

• Solution validation protocols using rapid prototyping, concept testing, and demand signal generation (e.g., fake door or concierge testing).

• Discovery sprint planning with 10-day templates including daily evidence reviews and clear pivot/proceed/stop decision gates.

• Automated CLI tools for mapping and prioritizing assumptions based on risk and certainty scores.

• Best for product discovery phases, startup MVP planning, and feature conceptualization workflows.

• Use the assumption_mapper.py script to ingest CSV files or inline inputs for prioritized testing plans.

• Requires setting measurable outcomes and clear baseline/target horizons before starting any discovery branch.

• Recommended usage follows Teresa Torres' continuous discovery frameworks.

• Constraints: Focus on evidence collection; prioritize behavioral metrics over stated preferences in all validation steps.

• Input requirements include target user segments and measurable business metrics; outputs consist of a validated experimentation plan and actionable discovery reports.