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

design-features

Run Phase 4 with the feature-design skill. The product-manager leads, product-designer explores journeys, and relevant architecture/security specialists review feasibility and risk without taking over product scope.

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 validated needs, intended outcome, evidence, constraints, success criteria, and non-goals before suggesting solutions.
2. Generate bounded alternative capabilities and flows, then compare need fit, behavior change, accessibility, complexity, risk, reversibility, and learning value.
3. Select the narrowest coherent end-to-end journey and specify all success, loading, empty, validation, denial, degraded, failure, and recovery states.
4. Identify actor/permission, data, contract, privacy/security, content, instrumentation, operational, and accessibility implications.
5. Prototype and test the riskiest interaction or assumption at the lowest useful fidelity using only authorized evidence.
6. Document the chosen behavior, rejected alternatives, non-goals, open contract questions, and testable acceptance criteria for product definition.

Deliverables

• Selected capability and alternative rationale mapped directly to validated needs and outcome.
• Complete user journey/state model with accessibility, permissions, content, failure, and recovery intent.
• Prototype/test evidence, behavioral acceptance criteria, non-goals, and unresolved implementation-boundary questions.

Constraints

• Do not treat a polished interface, stakeholder preference, or familiar pattern as evidence of need fit.
• Do not make UI checks the source of truth for authorization, financial state, or durable business rules.
• Do not include speculative platform work, personalization, or adjacent personas in the first capability.

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