<!-- Generated by mstack from Misbah's Build Like This workflow. Regenerate instead of editing. -->

research-idea

Run Phase 1 with the idea-validation skill. The product-manager leads and delegates independent evidence lanes to product-researcher and product-analyst; determine whether the idea merits deeper user discovery without inventing validation.

This prompt follows Misbah Khursheed's Build Like This workflow: establish the user outcome and reasoning before generating implementation, then preserve that reasoning in contracts, boundaries, tests, and documentation.

Project identity and sources of truth

The repository where this prompt is installed is the host project being built. Build Like This is the engineering method used to build it, while mstack only installs and reconciles the method's resources. Do not mistake mstack or Build Like This for the host product unless project-owned sources explicitly say this repository develops mstack itself.

Project-owned docs/, decisions, executable code, and tests are the sources of truth. .mstack/templates/ are reference scaffolds that may be copied and adapted into project-owned documents; they are not requirements and do not replace docs/.

Treat the invocation arguments and current repository state as task input. Discover local instructions and relevant product, architecture, decision, contract, and test context before making material assumptions.

Method

1. State the falsifiable problem/value hypothesis, suspected user/context, decision options, current evidence, unknowns, and disconfirming signals.
2. Inspect project-owned docs and existing evidence, then search independent current source classes with citations, dates, access dates, and limitations.
3. Analyze current workarounds, alternatives, switching costs, frequency/severity signals, feasibility constraints, and evidence against the idea.
4. Separate facts, interpretations, assumptions, contradictions, and unanswered questions; treat secondary evidence as hypothesis-shaping rather than user validation.
5. Make a go/refine/stop recommendation tied to an explicit evidence threshold and the cost of being wrong.
6. Create or update a dated docs/research/ discovery brief and define the smallest authorized primary-research or experiment step.

Deliverables

• Cited discovery brief, alternative map, and evidence/assumption/contradiction ledger.
• Go/refine/stop decision with confidence, rationale, constraints, and explicit non-conclusions.
• Next validation plan with method, owner, authorization/privacy boundary, threshold, and stop rule.

Constraints

• Do not jump to features, MVP scope, architecture, or implementation before the idea clears its evidence gate.
• Do not fabricate sources, users, quotes, demand, market size, metrics, or certainty.
• Do not contact people, buy data, create accounts, or mutate external systems without explicit authorization.

Delegation and parallel safety

• For a material lifecycle task, the active lead must delegate at least one bounded specialist lane when subagents are available; prefer two or more concurrent lanes only when their evidence or file ownership is independent.
• The active lead owns acceptance criteria and final integration. Supporting agents must not recursively delegate unless explicitly promoted to lead a named lane.
• Give each delegate distinct inputs, outputs, and ownership. Serialize shared documents, contracts, schemas, migrations, deployments, external writes, and overlapping file edits.
• If subagents are unavailable, perform the named specialist passes sequentially and report the limitation; do not imply parallel verification.
• Delegation does not authorize outreach, paid resources, destructive changes, consequential external writes, or production deployment.

Finish with what changed or was decided, exact verification evidence, remaining risks, and the next decision only if one is genuinely required.

User arguments: $ARGUMENTS