discover
The /discover command executes a complete product discovery workflow, progressing from problem framing through interview preparation, opportunity mapping, validation planning, and synthesis into an execution plan. Use this when starting a new initiative to systematically validate assumptions and identify solution directions before committing to development.
mkdir -p ~/.claude/commands && curl -fsSL https://raw.githubusercontent.com/deanpeters/Product-Manager-Skills/HEAD/commands/discover.md -o ~/.claude/commands/discover.mddiscover.md
# /discover Run a full discovery loop without manually stitching together skills. ## Invocation ```text /discover Reduce onboarding drop-off for new SMB users ``` ## Workflow 1. Frame the problem using `problem-framing-canvas`. 2. Plan interview and evidence gathering with `discovery-interview-prep`. 3. Map opportunities and options with `opportunity-solution-tree`. 4. Select validation probes with `pol-probe-advisor`. 5. Synthesize into a concrete execution plan using `discovery-process`. ## Checkpoints - Confirm target user and business outcome before solutioning. - Prioritize the top 2-3 assumptions by risk. - Choose fast experiments before committing engineering. ## Next Steps - Run `/write-prd` for the most promising validated solution. - Run `/prioritize` when multiple solution paths survive validation.
Evaluate acquisition channels using unit economics, customer quality, and scalability. Use when deciding whether to scale, test, or kill a growth channel.
Design multi-agent AI workflows with clear boundaries, handoffs, and monitoring. Use when a complex PM task should run as parallel specialized agents instead of one linear process.
Assess whether your product work is AI-first or AI-shaped. Use when evaluating AI maturity and choosing the next team capability to build.
Understand the PM-to-Director transition through altitude and horizon thinking. Use when diagnosing scope, time-horizon, or leadership-level gaps.
Map evidence-backed growth options across the Ansoff Matrix with risk-rated sequencing. Use when the question is where the next tranche of growth comes from, and at what risk.
The protocol behind every investigation skill. Use when AI research must proceed without you: search-plan gate, Fact/Inference/Assumption labels, confidence stacking, diffable outputs.
Research and draft a competitive battle card from public evidence — every claim labeled and sourced. Use when a rep needs a field-action card, not a research report.
Diagnose SaaS business health across growth, retention, efficiency, and capital. Use when preparing a business review or prioritizing urgent fixes.