Software Development Skills

Specialized architecture audit for AI-agent systems and AI-enabled products. Use for agent runtimes, tool-using workflows, memory systems, RAG, MCP integrations, long-running tasks, model routing, evidence tracking, human approval, evaluations, or systems exposed to prompt injection and model uncertainty. Extends rather than replaces the general project architecture audit.

Independently verifies candidate architecture findings against current code and repository evidence. Use after any project, AI-agent, mobile, or portfolio architecture audit; when a finding may be based on weak heuristics; or before remediation and quality gates. Filters false positives, deduplicates findings, recalibrates severity and confidence, and preserves an auditable decision trail without changing code.

Maintains the plugin's architecture quality models, styles, patterns, technology profiles, reference architectures, migration guides, domain guidance, decision rules, machine rule packs, and evidence-provider registry. Use when adding or refreshing architecture knowledge, checking official-source freshness, reviewing framework capability claims, resolving duplicate or contradictory entries, or preparing a release whose decision knowledge may be stale. Does not audit a product or choose a product architecture.

Deterministic architecture quality gate for verified review artifacts. Use in local checks or CI to validate architecture configuration, block configured confirmed severities, enforce review freshness, and honor explicit baselines or time-limited waivers. Never treats raw model findings as gate failures and never replaces finding verification.

Converts an accepted architecture decision for confirmed findings into an executable migration roadmap. Use after architecture-finding-verifier and architecture-solution-advisor when a project needs implementation slices, dependencies, compatibility, data migration, deployment sequencing, observability, rollback, stop conditions, effort, and acceptance criteria. Produces a plan only; it does not choose the target architecture or implement changes.

Compares architecture styles, patterns, technologies, and keep-current options for confirmed findings or an approved Greenfield design brief with explicit quality-attribute scenarios. Use after architecture verification for remediation, or before implementation for a new system, when a project needs a target architecture, technology selection, ADR-like decision, tradeoff analysis, or a reasoned choice between monoliths, services, events, workflows, agent runtimes, mobile data models, or shared portfolio capabilities. Produces an architecture decision, not an implementation plan or code change.

Specialized architecture audit for mobile applications, especially iOS and SwiftUI. Use when assessing local persistence, offline behavior, synchronization and conflicts, migrations, background execution, notifications, networking and caches, state ownership, privacy permissions, battery efficiency, or excessive client-side business logic. Extends rather than replaces the general project architecture audit.

System-of-systems architecture setup and audit across multiple projects. Use when initializing .architecture-portfolio or reviewing duplicated capabilities, project boundary conflicts, technology-stack sprawl, shared infrastructure, cross-project data flows, hidden coupling, deployment and domain complexity, reusable components, or a one-year technical governance roadmap. Requires an explicit portfolio registry and does not replace per-project audits.

Evidence-backed architecture audit and profile setup for one repository. Use when initializing .architecture, onboarding to a codebase, reviewing architecture health, preparing a refactor, investigating structural debt, or assessing module boundaries, ownership, contracts, resilience, security, observability, tests, deployment, and over-design. Produces candidate findings for independent verification, not confirmed conclusions, fixes, or remediation plans.