product-discovery

What This Skill Does

The product-discovery skill provides a structured framework for AI-assisted product development. It empowers users to apply Teresa Torres’ Opportunity Solution Tree methodology, map risks across desirability, viability, feasibility, and usability dimensions, and orchestrate rigorous discovery sprints. By leveraging the internal assumption_mapper.py script, this skill converts abstract product bets into measurable hypotheses, allowing product managers and engineers to fail fast and iterate based on empirical evidence rather than internal opinion.

Installation

To install the product-discovery skill, run the following command in your terminal: clawhub install openclaw/skills/skills/alirezarezvani/product-discovery

Use Cases

• Problem Validation: Systematically analyze user interviews and support data to confirm if a perceived customer pain is worth solving.
• Risk Mitigation: Use the built-in assumption mapper to identify and prioritize high-risk, low-certainty variables before committing engineering resources.
• Discovery Sprint Planning: Generate detailed 10-day sprint plans that transition from hypothesis framing to evidence-based decision-making (proceed, pivot, or stop).
• Strategic Alignment: Maintain alignment on desired outcomes using an Opportunity Solution Tree to link business metrics directly to customer-centric experiments.

Example Prompts

1. "OpenClaw, help me facilitate an Opportunity Solution Tree for our checkout conversion goal. Start by identifying three primary customer pain points based on the recent user feedback CSV."
2. "I need to map the risks for our new automated billing feature. Run the assumption mapper script and categorize them into desirability, viability, feasibility, and usability."
3. "Plan a 10-day discovery sprint for testing the new mobile app onboarding flow. Include a schedule for user testing and daily evidence review sessions."

Tips & Limitations

• Evidence-First: Do not rely on the agent's internal suggestions alone. Feed it raw data (e.g., CSVs of interviews or analytics) to ensure the outputs are grounded in reality.
• Iterative Refinement: Treat the Opportunity Solution Tree as a living document. Re-run the discovery skill whenever new behavioral data becomes available.
• Human-in-the-loop: While the agent excels at planning and synthesis, final decisions on whether to pivot or proceed should always involve stakeholder synthesis of the evidence provided by the agent.