Product Discovery: AI Skill for Product Management

Product Discovery is an AI skill that plans how to figure out what to build before building it. Continuous cadence, problem before solution, past behavior over hypotheticals, and evidence matched to the decision's risk.

npx skills add Uxcel-Lab/product-skills --skill pm-discovery

Copied

What this skill does

Helps an AI assistant plan discovery that learns continuously, validates problems before solutions, and buys the certainty each decision needs.

Names which risk to retire first: value, usability, feasibility, or business viability.
Makes discovery a weekly habit instead of a one-time research phase.
Orients the team to outcomes (behavior change) rather than shipped output.
Separates root problems from symptoms before designing anything.
Asks about past behavior, not "would you use this?"
Filters requests by pattern, not by the loudest voice.
Generates several solution directions from validated problems, then compares them.
Keeps research ethical and inclusive, with informed consent and representative recruiting.

When to use it

Use it when you need an AI assistant to:

plan discovery or a research effort;
figure out what to build next;
set up continuous discovery;
find problems worth solving;
de-risk a product direction before committing;
design customer or user research;
check a discovery plan for bias or thin evidence.

Decisions this skill helps you make

Decision	Options
Problem vs. solution research	Interviews and observation first, solution testing once the problem is validated
Qualitative vs. quantitative	Qualitative for why, quantitative for what, cross-checked before committing
Cadence	Weekly lightweight touchpoints, plus deep studies for big or unfamiliar bets
Who runs it	PM-led research for speed, specialists for high-stakes or regulated studies
Certainty before committing	Evidence scaled to the decision's risk and reversibility
Whose voices to weight	Patterns across sources over the loudest single client