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

grill-decisions

Run the design-grilling skill. Settle the decision frontier before write-product-definition or design-architecture so those documents record confirmed intent rather than plausible filler.

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. Restate the outcome, evidence versus assumptions, and the earliest incomplete lifecycle phase.
2. Build a dependency-aware decision frontier and work only nodes whose prerequisites are settled.
3. Recommend a default for each frontier decision, confirm with the user, and record rejected alternatives.
4. Send factual lookup to inspection or specialist lanes; never invent user or market evidence.
5. Stop when the frontier is empty or an earlier research phase is required.
6. Hand off the confirmed ledger without writing product.md or architecture.md yet.

Deliverables

• Confirmed decision ledger with open research gaps labeled.
• Readiness signal for product-definition and/or architecture-design.
• Evidence pointers actually inspected.

Constraints

• Do not write authoritative planning docs in this prompt.
• Do not treat recommendations as confirmed without the user.
• Do not start tickets or implementation while decisions remain open.

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