Brownfield onboarding for an existing mobile-app codebase. Audits PRDs, ADRs, stories, UX specs, and architecture docs for compatibility with this template's review skills, classifies gaps by impact, and produces a numbered migration plan. Use when joining a project mid-flight or upgrading from an older template version.
Creates an Architecture Decision Record (ADR) documenting a significant technical decision — its context, alternatives, decision, consequences, and PRD requirements addressed. Every major mobile-architecture choice should have an ADR. Framework-version-aware: cross-references the framework reference docs to flag knowledge-cutoff risk.
Validates the architecture against all PRDs. Builds a traceability matrix from PRD requirements to ADRs, identifies coverage gaps, detects cross-ADR conflicts, and produces a PASS/CONCERNS/FAIL verdict. Run after Required ADRs are written; rerun whenever PRDs change. Read-only — never edits files.
Audits app assets for naming conventions, file size budgets, format standards, app icon completeness, splash screens, and store-listing imagery. Identifies orphans (asset on disk but never referenced) and missing references (referenced but missing).
Generates per-asset visual specifications and AI-generation prompts from PRDs and the design bible. Produces structured spec files and updates a master asset manifest. Use after design bible is approved and a UX spec or PRD identifies assets to produce. Output: design/assets/<asset>.md plus design/assets/manifest.md.
Analyze pricing tiers, paywall configs, A/B test variants, and feature-flag values for outliers, broken funnels, dominant variants, and monetization imbalance. Use after editing pricing, paywall copy, or any growth-experiment config.
Guided ideation for a mobile app — from a blank page (or a single hint) to a structured concept doc covering target user, core job-to-be-done, MVP scope, and primary metric. Use when starting a new app or when an existing pitch needs to be tightened into a concept.
Author a structured bug report from a description, OR analyze code/logs to derive likely bugs. Captures reproduction steps, severity, device matrix, expected vs actual, and attachments. Use after a manual QA failure or when the user describes a defect.