| name | architecture-design |
| version | 2.1.1 |
| description | [Architecture] Use when designing solution architecture across backend, frontend, deployment, monitoring, testing, and code quality. |
[BLOCKING] Execute skill steps in declared order. NEVER skip, reorder, or merge steps without explicit user approval.
[BLOCKING] Before each step or sub-skill call, update task tracking: set in_progress when step starts, set completed when step ends.
[BLOCKING] Every completed/skipped step MUST include brief evidence or explicit skip reason.
[BLOCKING] If Task tools are unavailable, create and maintain an equivalent step-by-step plan tracker with the same status transitions.
Quick Summary
Goal: Act as solution architect to deliver a complete, evidence-backed, user-validated architecture decision report covering ALL concerns (backend, frontend, design patterns, library ecosystem, testing strategy, CI/CD, deployment, monitoring, code quality, dependency management) — every concern researched with 3+ options, every recommendation carrying confidence % + cited evidence, every decision confirmed by the user — so implementation proceeds on sound, owned architectural choices.
Summary:
- Decide mode FIRST (Step 1): greenfield researches every concern from scratch; brownfield reads reference docs + accepted ADRs and constrains research to the existing stack — NEVER re-litigate a settled ADR-recorded decision without a superseding-ADR rationale.
- Drive the style choice with NUMBERS, not adjectives: quantify Step-2 quality-attribute scenarios (latency p95/p99, throughput, SLO, RPO/RTO, data growth, concurrency); any unknown target becomes an explicit
Unresolved question, never a silent guess.
- Every concern needs 3+ researched options with cited evidence (stars, last release, downloads, CVE scan) + a confidence % — familiarity alone is never sufficient grounds for a recommendation.
- Produce the two binding downstream contracts and you're done; skip either and the chain breaks: emit an ADR per hard-to-reverse decision (
review-architecture Cat 9 enforces it) and the Scaffold Handoff tool-choices table (scaffold/harness-setup consume it), then run the MANDATORY Step-12 user-validation interview before confirming.
Workflow (12 steps):
- Load Context — Read domain model, tech stack, business evaluation, refined PBI
- Derive Architecture Requirements — Map business/domain complexity to architecture constraints
- Backend Architecture — Research top 3 backend architecture styles + design patterns
- Frontend Architecture — Research top 3 frontend architecture styles + design patterns
- Library Ecosystem Research — Best-practice libraries per concern (validation, caching, logging, utils, etc.)
- Testing Architecture — Unit, integration, E2E, performance testing frameworks + strategy
- CI/CD & Deployment — Pipeline design, containerization, orchestration, IaC
- Observability & Monitoring — Logging, metrics, tracing, alerting stack
- Code Quality & Clean Code — Linters, analyzers, formatters, enforcement tooling
- Dependency Risk Assessment — Package health, obsolescence risk, maintenance cost
- Generate Report — Full architecture decision report with all recommendations
- User Validation — Present findings, ask 8-12 questions, confirm all decisions
Key Rules:
- MANDATORY IMPORTANT MUST ATTENTION research minimum 3 options per architecture concern with web evidence
- MANDATORY IMPORTANT MUST ATTENTION include confidence % with evidence for every recommendation
- MANDATORY IMPORTANT MUST ATTENTION run user validation interview at end (never skip)
- Delegate to
solution-architect agent for complex architecture decisions
- All claims must cite sources (URL, benchmark, case study, or codebase evidence)
- Base every recommendation on evidence, never on familiarity alone
Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).
Inputs & Handoffs (consume vs produce)
Skill sits mid-workflow — consumes settled upstream decisions, produces artifacts downstream steps build on. Do NOT re-derive what upstream step already owns; do NOT leave downstream consumer without its needed artifact. — why: re-deriving settled decisions wastes effort and risks divergence from the recorded choice.
| Consumes (read, don't re-derive) | From | Produces (named deliverable) | Consumed by |
|---|
| Bounded contexts, aggregates, domain events, ERD | domain-analysis | Architecture decision report ({plan-dir}/research/...) | plan, plan-execute |
| Confirmed languages/frameworks/databases | tech-stack-research | Confirmed decisions ({plan-dir}/phase-02b-architecture.md) | plan, scaffold |
| Expected scale, compliance, budget constraints | business-evaluation | Scaffold Handoff table (tooling + fitness rules) | scaffold, harness-setup |
| Existing stack/patterns/ADRs (brownfield) | reference docs, docs/adr/** | ADRs for hard-to-reverse decisions (docs/adr/) | review-architecture (conformance) |
If upstream artifact missing, capture minimum needed here and note gap — NEVER silently re-run full upstream analysis. — why: a silent re-run hides the missing-input gap that the owning step should resolve.
Step 1: Load Context
Mode (decide first): Greenfield (new project, e.g. via workflow-greenfield-init) → research every concern from scratch, full 3-options-per-concern. Brownfield (large feature in existing codebase, e.g. workflow-big-feature) → FIRST read project reference docs + accepted ADRs, constrain research to existing stack/patterns, propose changes only where new requirement genuinely outgrows them — NEVER re-litigate settled ADR-recorded decision without superseding-ADR rationale. — why: re-deciding a recorded choice churns the codebase and breaks downstream conformance checks.
Read artifacts from prior workflow steps (search plans/ and team-artifacts/):
- Domain model / ERD (complexity, bounded contexts, aggregate count)
- Tech stack decisions (confirmed languages, frameworks, databases)
- Business evaluation (scale, constraints, compliance)
- Refined PBI (scope, acceptance criteria)
- Discovery interview (team skills, experience level)
Extract, summarize:
| Signal | Value | Source |
|---|
| Bounded contexts | ... | domain model |
| Aggregate count | ... | domain model |
| Cross-context events | ... | domain model |
| Confirmed tech stack | ... | tech stack phase |
| Expected scale | ... | business eval |
| Team architecture exp. | ... | discovery |
| Compliance requirements | ... | business eval |
| Real-time needs | Yes/No | refined PBI |
| Integration complexity | Low/Med/High | domain model |
| Deployment target | ... | business eval |
Step 2: Derive Architecture Requirements
Map signals to architecture constraints:
| Signal | Architecture Requirement | Priority |
|---|
| Many bounded contexts | Clear module boundaries, context isolation | Must |
| High scale | Horizontal scaling, stateless services, caching strategy | Must |
| Complex domain | Rich domain model, separation of domain from infra | Must |
| Cross-context events | Event-driven communication, eventual consistency | Must |
| Small team | Low ceremony, fewer layers, convention over configuration | Should |
| Compliance | Audit trail, immutable events, access control layers | Must |
| Real-time | Event sourcing or pub/sub, WebSocket/SSE support | Should |
| High integration complexity | Anti-corruption layers, adapter pattern, API gateway | Should |
Quality-Attribute Scenarios (quantify — these drive the style choice)
Qualitative "Must/Should" cannot decide between, e.g., modular monolith vs microservices. Capture measurable targets; ask user for any unknown via AskUserQuestion (guess acceptable only when labelled an assumption with confidence %). These targets become ADR-recorded budgets review-architecture Category 9 later checks changes against. — why: a style chosen without numbers is a guess, not an enforceable decision.
| Quality attribute | Scenario (stimulus → measurable response) | Target (fill in) |
|---|
| Latency | p95 / p99 response time for the hottest read and write paths | e.g. p99 < 300ms |
| Throughput | Sustained req/s and peak burst the system must absorb | e.g. 500 rps peak |
| Availability / SLO | Target uptime and error budget | e.g. 99.9% |
| Data durability (RPO) | Max acceptable data loss on failure | e.g. ≤ 5 min |
| Recovery (RTO) | Max acceptable time to restore service | e.g. ≤ 30 min |
| Data-volume growth | Row/document/event growth → storage, index, partition strategy | e.g. 10M rows/yr |
| Concurrency | Concurrent users/sessions and contention hot spots | e.g. 2k concurrent |
| Compliance/retention | Regulated data, retention window, residency, audit | e.g. GDPR, 7yr |
Rule: any target left unknown is explicit Unresolved question (Step 11), NEVER a silent omission — an architecture chosen without scale numbers is a guess, not a decision.
MANDATORY IMPORTANT MUST ATTENTION validate derived requirements with user via AskUserQuestion before proceeding.
Step 3: Backend Architecture
3A: Architecture Styles
WebSearch top 3 backend architecture styles. Candidates:
| Style | Best For | Research Focus |
|---|
| Clean Architecture | Complex domains, long-lived projects | Dependency rule, testability, flexibility |
| Hexagonal (Ports+Adapt) | Integration-heavy, multiple I/O adapters | Port contracts, adapter isolation |
| Vertical Slice | Feature-focused teams, rapid delivery | Slice isolation, code locality |
| Modular Monolith | Starting simple, eventual decomposition | Module boundaries, migration path |
| Microservices | Large teams, independent deployment | Service boundaries, operational overhead |
| CQRS + Event Sourcing | Audit-heavy, complex queries | Read/write separation, event store |
| Layered (N-Tier) | Simple CRUD, small teams | Layer responsibilities, coupling risk |
3B: Backend Design Patterns
Evaluate applicability per layer:
| Pattern | Layer | When to Apply |
|---|
| Repository | Data Access | Abstract data store, enable testing |
| CQRS | Application | Separate read/write models, complex queries |
| Mediator | Application | Decouple handlers from controllers |
| Strategy | Domain/App | Multiple interchangeable algorithms |
| Observer/Events | Domain | Cross-aggregate side effects |
| Factory | Domain | Complex object creation with invariants |
| Decorator | Cross-cutting | Add behavior without modifying (logging, caching) |
| Adapter | Infrastructure | Isolate external dependencies |
| Specification | Domain | Composable business rules, complex filtering |
| Unit of Work | Data Access | Transaction management across repositories |
| Saga/Orchestr. | Cross-service | Distributed transactions, compensating actions |
| Outbox | Messaging | Reliable event publishing with DB transactions |
| Circuit Breaker | Infrastructure | External service resilience |
Per recommended pattern document: Apply to, Why, Example, Risk if skipped.
Step 4: Frontend Architecture
4A: Architecture Styles
WebSearch top 3 frontend architecture styles. Candidates:
| Style | Best For | Research Focus |
|---|
| MVVM | Data-binding heavy, forms-over-data apps | ViewModel responsibility, two-way binding |
| MVC | Server-rendered, traditional web apps | Controller routing, view separation |
| Component Architecture | Configured SPA/component framework | Component isolation, props/events, reuse |
| Reactive Store (Redux) | Complex state, multi-component sync | Single source of truth, immutable state |
| Signal-based Reactivity | Fine-grained reactivity in frameworks that support signals | Granular updates without broad change detection |
| Micro Frontends | Multiple teams, independent deployment | Module federation, routing, shared state |
| Feature-based Modules | Large monolith SPA, lazy loading | Feature boundaries, route-level splitting |
| Server Components (RSC) | SEO, initial load performance | Server/client boundary, streaming |
4B: Frontend Design Patterns
| Pattern | Layer | When to Apply |
|---|
| Container/Presentational | Component | Separate logic from UI rendering |
| Reactive Store | State | Centralized state, cross-component communication |
| Facade Service | Service | Simplify complex API interactions |
| Adapter/Mapper | Data | Transform API response to view model |
| Observer (RxJS) | Async | Event streams, real-time data, debounce/throttle |
| Strategy (renderers) | UI | Conditional rendering strategies per entity type |
| Composite (components) | UI | Tree structures, recursive components |
| Command (undo/redo) | UX | Form wizards, canvas editors, undoable actions |
| Lazy Loading | Performance | Route/module-level code splitting |
| Virtual Scrolling | Performance | Large lists, infinite scroll |
Step 4B: UI System Architecture
Skip if: Backend-only project, no frontend component.
Research, recommend project design system architecture. Use AskUserQuestion for each decision.
4B-1: Styling Approach
WebSearch top 3 styling approaches for confirmed frontend framework:
| Approach | Best For | Research Focus |
|---|
| Utility-first (Tailwind CSS) | Rapid prototyping, design enforcement | JIT, custom config, design tokens |
| CSS Modules / Scoped CSS | Component isolation, no global conflicts | Naming, composition patterns |
| SCSS/SASS with BEM | Complex theming, token variables | BEM methodology, mixin libraries |
| CSS-in-JS | Dynamic styling, theme providers | Runtime perf, SSR support |
| CSS Custom Properties | Native theming, framework-agnostic | Browser support, fallback strategy |
4B-2: Design Token Strategy
| Decision | Options | Default |
|---|
| Token format | CSS custom properties / JSON / SCSS variables | CSS custom properties |
| Token categories | Color, spacing, typography, breakpoints, shadows, z-index | All |
| Token naming | Semantic (--color-primary) vs Functional (--btn-bg) | Semantic first |
| Theming | Light/dark toggle / Multi-brand / Single theme | Single + dark mode |
4B-3: Component Library Strategy
| Decision | Options | Default |
|---|
| Library | Build custom / Headless (Radix, Headless UI) / Full kit (MUI, Ant, PrimeNG) | Based on team and timeline |
| Component tiers | Common → Domain-Shared → Page (per ui-wireframe-protocol) | Standard 3-tier |
| Documentation | Storybook / Docusaurus / In-code only | Based on team size |
4B-4: Responsive Strategy
| Decision | Options | Default |
|---|
| Approach | Mobile-first / Desktop-first / Adaptive | Mobile-first |
| Breakpoints | 320/768/1024/1280 / Custom | Standard |
| Grid system | CSS Grid / Flexbox / Framework grid | CSS Grid + Flexbox |
MANDATORY IMPORTANT MUST ATTENTION validate all UI system decisions with user via AskUserQuestion before proceeding to Step 5.
Step 5: Library Ecosystem Research
Per concern below, WebSearch top 3 library options for confirmed tech stack. Evaluate: maturity, community, bundle size, maintenance activity, license, learning curve.
MUST ATTENTION never recommend a library from familiarity alone — every pick needs cited evidence (stars, release date, downloads, CVE scan). — why: familiarity bias ships unmaintained or insecure dependencies.
Library Concerns Checklist
| Concern | What to Research | Evaluation Criteria |
|---|
| Validation | Input validation, schema validation, form validation | Type safety, composability, error messages |
| HTTP Client / API Layer | REST client, GraphQL client, API code generation | Interceptors, retry, caching, type generation |
| State Management | Global store, local state, server state caching | DevTools, SSR support, bundle size |
| Utilities / Helpers | Date/time, collections, deep clone, string manipulation | Tree-shakability, size, native alternatives |
| Caching | In-memory cache, distributed cache, HTTP cache, query cache | TTL, invalidation, persistence |
| Logging | Structured logging, log levels, log aggregation | Structured output, transports, performance |
| Error Handling | Global error boundary, error tracking, crash reporting | Source maps, breadcrumbs, alerting integration |
| Authentication / AuthZ | JWT, OAuth, RBAC/ABAC, session management | Standards compliance, SSO, token refresh |
| File Upload / Storage | Multipart upload, cloud storage SDK, image processing | Streaming, resumable, size limits |
| Real-time | WebSocket, SSE, SignalR, Socket.io | Reconnection, scaling, protocol support |
| Internationalization | i18n, l10n, pluralization, date/number formatting | ICU support, lazy loading, extraction tools |
| PDF / Export | PDF generation, Excel export, CSV | Server-side vs client-side, template support |
Per-Library Evaluation Template
### {Concern}: Top 3 Options
| Criteria | Option A | Option B | Option C |
| ---------------- | ----------------- | -------- | -------- |
| GitHub Stars | ... | ... | ... |
| Last Release | ... | ... | ... |
| Bundle Size | ... | ... | ... |
| Weekly Downloads | ... | ... | ... |
| License | ... | ... | ... |
| Maintenance | Active/Slow/Stale | ... | ... |
| Learning Curve | Low/Med/High | ... | ... |
**Recommendation:** {Option} — Confidence: {X}%
Step 6: Testing Architecture
Research best testing tools, strategy for confirmed tech stack:
| Testing Layer | What to Research | Top Candidates to Compare |
|---|
| Unit Testing | Test runner, assertion library, mocking framework | Repository's configured unit-test stack |
| Integration Testing | API testing, DB testing, service testing | Supertest, TestContainers, WebAppFactory |
| E2E Testing | Browser automation, BDD, visual regression | Playwright/Cypress/Selenium, SpecFlow |
| Performance Testing | Load testing, stress testing, benchmarking | k6/Artillery/JMeter/NBomber, BenchmarkDotNet |
| Contract Testing | API contract validation between services | Pact, Dredd, Spectral |
| Mutation Testing | Test quality validation | Stryker, PITest |
| Coverage | Code coverage collection, reporting, enforcement | Istanbul/Coverlet, SonarQube |
| Test Data | Factories, fixtures, seeders, fakers | Bogus/AutoFixture/Faker.js |
Test Strategy Template
### Test Pyramid
- **Unit (70%):** {framework} — {what to test}
- **Integration (20%):** {framework} — {what to test}
- **E2E (10%):** {framework} — {what to test}
### Test-Strength Targets
- Line coverage (diagnostic only — NEVER fail the build on a coverage %): Unit: {X}% | Integration: {X}% | E2E: critical paths only
- Gate: mutation score ({tool}) in CI pipeline — fail build on surviving mutants / mutation-score regression, not on a line-coverage %
Step 7: CI/CD & Deployment
Research deployment architecture, CI/CD tooling:
| Concern | What to Research | Top Candidates to Compare |
|---|
| CI/CD Provider | Pipeline orchestration, parallelism, caching | Repository's configured CI/CD tooling |
| Containerization | Container runtime, image building, registry | Docker/Podman, BuildKit, ACR/ECR/GHCR |
| Orchestration | Container orchestration, service mesh, scaling | Kubernetes/Docker Compose/ECS/Nomad |
| IaC (Infra as Code) | Infrastructure provisioning, drift detection | Terraform/Pulumi/Bicep/CDK |
| Artifact Management | Package registry, versioning, vulnerability scanning | NuGet/npm/Artifactory/GitHub Packages |
| Feature Flags | Progressive rollout, A/B testing, kill switches | LaunchDarkly/Unleash/Flagsmith |
| Secret Management | Vault, key rotation, environment variables | Azure KeyVault/HashiCorp Vault/SOPS |
| Database Migration | Schema versioning, rollback, seed data | EF Migrations/Flyway/Liquibase/dbmate |
Deployment Strategy Comparison
| Strategy | Risk | Downtime | Complexity | Best For |
|---|
| Blue-Green | Low | Zero | Medium | Critical services |
| Canary | Low | Zero | High | Gradual rollout |
| Rolling | Med | Zero | Low | Stateless services |
| Recreate | High | Yes | Low | Dev/staging environments |
| Feature Flags | Low | Zero | Medium | Feature-level control |
Step 8: Observability & Monitoring
| Concern | What to Research | Top Candidates to Compare |
|---|
| Structured Logging | Log format, correlation IDs, log levels, aggregation | Serilog/NLog/Winston/Pino |
| Log Aggregation | Centralized log search, dashboards, alerts | ELK/Loki+Grafana/Datadog/Seq |
| Metrics | Application metrics, custom counters, histograms | Prometheus/OpenTelemetry/App Insights |
| Distributed Tracing | Request tracing across services, span visualization | Jaeger/Zipkin/OpenTelemetry/Tempo |
| APM | Application performance monitoring, auto-instrumentation | Datadog/New Relic/App Insights/Elastic |
| Alerting | Threshold alerts, anomaly detection, on-call routing | PagerDuty/OpsGenie/Grafana Alerting |
| Health Checks | Liveness, readiness, startup probes | AspNetCore.Diagnostics/Terminus |
| Uptime Monitoring | External availability monitoring, SLA tracking | UptimeRobot/Pingdom/Checkly |
Observability Decision: 3 Pillars
### Recommended Observability Stack
| Pillar | Tool | Why |
| -------- | ------ | ----------- |
| Logs | {tool} | {rationale} |
| Metrics | {tool} | {rationale} |
| Traces | {tool} | {rationale} |
| Alerting | {tool} | {rationale} |
Step 9: Code Quality & Clean Code Enforcement
Research, recommend tooling for automated code quality:
| Concern | What to Research | Top Candidates to Compare |
|---|
| Linter (Backend) | Static analysis, code style, bug detection | Roslyn Analyzers/SonarQube/StyleCop/ReSharper |
| Linter (Frontend) | JS/TS linting, accessibility, complexity | ESLint/Biome/oxlint |
| Formatter | Auto-formatting, consistent style | Prettier/dotnet-format/EditorConfig |
| Code Analyzer | Security scanning, complexity metrics, duplication | SonarQube/CodeClimate/Codacy |
| Pre-commit Hooks | Git hooks, staged file validation | Husky+lint-staged/pre-commit/Lefthook |
| Editor Config | Cross-IDE consistency | .editorconfig/IDE-specific configs |
| Architecture Rules | Layer dependency enforcement, naming conventions | ArchUnit/NetArchTest/Dependency-Cruiser |
| API Design Standards | OpenAPI validation, naming, versioning | Spectral/Redocly/swagger-lint |
| Commit Conventions | Commit message format, changelog generation | Commitlint/Conventional Commits |
| Code Review Automation | Automated PR review, suggestion bots | Danger.js/Reviewdog/CodeRabbit |
Enforcement Strategy
### Code Quality Gates
| Gate | Tool | Trigger | Fail Criteria |
| ----------- | ------ | -------------- | ------------------------------------------------------------------------------------- |
| Pre-commit | {tool} | git commit | Lint errors, format |
| PR Check | {tool} | Pull request | Surviving mutants / mutation-score regression, issues (line-coverage diagnostic only) |
| CI Pipeline | {tool} | Push to branch | Build fail, test fail |
| Scheduled | {tool} | Weekly/nightly | Security vulns, debt |
Scaffold Handoff (MANDATORY — consumed by /scaffold)
After code quality research, produce this handoff table in architecture report. /scaffold reads this table to generate actual config files — without it, scaffold cannot auto-configure quality tooling. — why: the handoff table is the only contract scaffold has for tool choices.
### Scaffold Handoff — Tool Choices
| Concern | Chosen Tool | Config File | Rationale |
| -------------------- | --------------------------------------------------- | ----------- | ------------------------------------------------------------ |
| Linter (FE) | {tool} | {filename} | {why} |
| Linter (BE) | {tool} | {filename} | {why} |
| Formatter | {tool} | {filename} | {why} |
| Pre-commit | {tool} | {filename} | {why} |
| Arch rules / fitness | {tool: ArchUnit / NetArchTest / Dependency-Cruiser} | {filename} | {layer + dependency rules and Step-2 NFR budgets to enforce} |
| Error handling | {pattern} | {files} | {why} |
| Loading state | {pattern} | {files} | {why} |
| Docker | {compose pattern} | {files} | {why} |
Also include: Error handling strategy (4-layer pattern), loading state approach (global vs per-component), Docker profile structure. Specific tool choices → docs/project-reference/ or project-config.json. The Arch rules / fitness row MUST encode Step-2 quality-attribute budgets and layer/dependency rules as executable checks — harness-setup wires these into CI so recorded ADR decisions stay enforced, not merely documented. — why: documented-but-unenforced budgets erode silently as code changes.
Step 10: Dependency Risk Assessment
Per recommended library/package, evaluate maintenance, obsolescence risk:
Package Health Scorecard
| Criteria | Score (1-5) | How to Verify |
|---|
| Last Release Date | ... | npm/NuGet page — stale if >12 months |
| Open Issues Ratio | ... | GitHub issues open vs closed |
| Maintainer Count | ... | Bus factor — single maintainer = high risk |
| Breaking Change Freq. | ... | Changelog — frequent major versions = churn cost |
| Dependency Depth | ... | npm ls --depth / dependency graph depth |
| Known Vulnerabilities | ... | Snyk/npm audit/GitHub Dependabot |
| License Compatibility | ... | SPDX identifier — check viral licenses (GPL) |
| Community Activity | ... | Monthly commits, PR merge rate, Discord/forums |
| Migration Path | ... | Can swap to alternative if abandoned? |
| Framework Alignment | ... | Official recommendation by framework team? |
Risk Categories
| Risk Level | Criteria | Action |
|---|
| Low | Active, >3 maintainers, recent release, no CVEs | Use freely |
| Medium | 1-2 maintainers, release <6mo, minor CVEs patched | Use with monitoring plan |
| High | Single maintainer, >12mo stale, open CVEs | Find alternative or plan exit strategy |
| Critical | Abandoned, unpatched CVEs, deprecated | DO NOT USE — find replacement |
Dependency Maintenance Strategy
### Recommended Practices
1. **Automated scanning:** {tool} (Dependabot/Renovate/Snyk) — weekly PR for updates
2. **Lock file strategy:** Commit lock files, pin major versions, allow patch auto-update
3. **Audit schedule:** Monthly `npm audit` / `dotnet list package --vulnerable`
4. **Vendor policy:** Max {N} dependencies per concern, prefer well-maintained alternatives
5. **Exit strategy:** For each High-risk dependency, document migration path to alternative
Step 11: Generate Report
Write report to {plan-dir}/research/architecture-design.md with sections:
- Executive summary (recommended architecture in 8-10 lines)
- Architecture requirements table (from Step 2)
- Backend architecture — style comparison + recommended patterns (Steps 3)
- Frontend architecture — style comparison + recommended patterns (Step 4)
- Library ecosystem — per-concern recommendations with alternatives (Step 5)
- Testing architecture — pyramid, tools, coverage targets (Step 6)
- CI/CD & deployment — pipeline design, deployment strategy (Step 7)
- Observability stack — 3 pillars + alerting (Step 8)
- Code quality — enforcement gates, tooling (Step 9)
- Dependency risk matrix — high-risk packages, mitigation (Step 10)
- Architecture diagram (Mermaid — showing all layers and data flow)
- Risk assessment for overall architecture
- Unresolved questions
Emit ADRs for hard-to-reverse decisions (MANDATORY)
For each decision significant AND costly to reverse — backend/frontend style, persistence/consistency model, messaging approach, a Step-2 quality-attribute budget, a rejected-with-reason alternative — write one ADR to docs/adr/{NNNN}-{slug}.md following the repo's existing ADR format (Status, Date, Context, Decision, Consequences [Positive/Negative/Neutral], Alternatives Considered, Related; see docs/adr/0001-skill-lifecycle.md for canonical shape). Start Status: Proposed; promote to Accepted after Step-12 user validation confirms it. These ADRs are the binding record review-architecture Category 9 checks changed code against — a decision not written as an ADR cannot be enforced downstream. Route ADR authoring through the architect sub-agent for cross-service/security/performance impact analysis.
Architecture Diagram Template
```mermaid
graph TB
subgraph "Frontend"
UI[SPA / Micro Frontend]
STORE[State Management]
end
subgraph "API Gateway"
GW[Gateway / BFF]
end
subgraph "Backend Services"
CMD[Commands / Handlers]
QRY[Queries / Read Models]
SVC[Domain Services]
ENT[Entities / Aggregates]
end
subgraph "Infrastructure"
DB[(Database)]
CACHE[(Cache)]
MSG[Message Bus]
SEARCH[(Search Index)]
end
subgraph "Observability"
LOG[Logging]
METRIC[Metrics]
TRACE[Tracing]
end
subgraph "CI/CD"
PIPE[Pipeline]
REG[Container Registry]
K8S[Orchestration]
end
UI --> GW --> CMD & QRY
CMD --> SVC --> ENT --> DB
QRY --> CACHE & SEARCH
ENT -.-> MSG
CMD & QRY -.-> LOG & METRIC & TRACE
PIPE --> REG --> K8S
```
Step 12: User Validation Interview
MANDATORY IMPORTANT MUST ATTENTION present findings, ask 8-12 questions via AskUserQuestion:
Required Questions
- Backend architecture — "I recommend {style}. Agree?"
- Frontend architecture — "I recommend {style} with {state management}. Agree?"
- Design patterns — "Recommended backend patterns: {list}. Frontend patterns: {list}. Any to add/remove?"
- Key libraries — "For {concern}, I recommend {lib} over {alternatives}. Agree?"
- Testing strategy — "Test pyramid: {unit}%/{integration}%/{E2E}% using {frameworks}. Appropriate?"
- CI/CD — "Pipeline: {tool} with {deployment strategy}. Fits your infra?"
- Observability — "Monitoring stack: {logs}/{metrics}/{traces}. Sufficient?"
- Code quality — "Enforcement: {linter + formatter + pre-commit hooks}. Team ready?"
- Dependency risk — "Found {N} high-risk dependencies. Accept or find alternatives?"
- Complexity check — "This architecture has {N} concerns addressed. Appropriate for team size?"
Optional Deep-Dive Questions (pick 2-3)
- "Should we use event sourcing or traditional state-based persistence?"
- "Monolith-first or start with service boundaries?"
- "Micro frontends or monolith SPA?"
- "How important is framework independence for this repository or system?"
- "Self-hosted observability or managed SaaS?"
- "Strict lint rules from day 1 or gradual adoption?"
After user confirms, update report with final decisions, mark status: confirmed.
Best Practices Audit (applied across all steps)
Validate architecture against these principles — flag violations in report. — why: an unflagged SOLID/DRY violation compounds into rework once code lands on the flaw.
| Principle | Check | Status |
|---|
| Single Responsibility (S) | Each class/module has one reason to change | ✅/⚠️ |
| Open/Closed (O) | Extensible without modifying existing code | ✅/⚠️ |
| Liskov Substitution (L) | Subtypes substitutable for base types | ✅/⚠️ |
| Interface Segregation (I) | No forced dependency on unused interfaces | ✅/⚠️ |
| Dependency Inversion (D) | High-level modules depend on abstractions, not concretions | ✅/⚠️ |
| DRY | No duplicated business logic across layers | ✅/⚠️ |
| KISS | Simplest architecture that meets requirements | ✅/⚠️ |
| YAGNI | No speculative layers or patterns for future needs | ✅/⚠️ |
| Separation of Concerns | Clear boundaries between domain, application, infra | ✅/⚠️ |
| IoC / Dependency Injection | All dependencies injected, no new in business logic | ✅/⚠️ |
| Technical Agnosticism | Domain layer has zero framework/infra dependencies | ✅/⚠️ |
| Testability | Architecture supports unit + integration testing | ✅/⚠️ |
| 12-Factor App | Config in env, stateless processes, port binding | ✅/⚠️ |
| Fail-Fast | Validate early, fail with clear errors | ✅/⚠️ |
Output
{plan-dir}/research/architecture-design.md # Full architecture analysis report
{plan-dir}/phase-02b-architecture.md # Confirmed architecture decisions
docs/adr/{NNNN}-{slug}.md # One ADR per hard-to-reverse decision (see Step 11)
MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting.
MANDATORY IMPORTANT MUST ATTENTION validate EVERY architecture recommendation with user via AskUserQuestion — never auto-decide.
MANDATORY IMPORTANT MUST ATTENTION include confidence % and evidence citations for all claims.
MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality.
Next Steps
MANDATORY IMPORTANT MUST ATTENTION — NO EXCEPTIONS after completing this skill, you MUST ATTENTION use AskUserQuestion to present these options. NEVER skip because the task seems "simple" or "obvious" — the user decides:
- "/plan (Recommended)" — Create implementation plan from architecture design
- "/refine" — If need to create PBIs first
- "Skip, continue manually" — user decides
Council escalation (always-offer, second prompt)
After the existing ## Next Steps prompt above resolves, present a second, independent AskUserQuestion call (NEVER merge into the first):
- "Skip council — proceed (Recommended)" — Continue with the architecture decision as-is. Recommended default.
- "Escalate to /llm-council" — Run 11 sub-agent council (5 advisors + 5 reviewers + chairman). Use when this architecture pick is hard to reverse and you need adversarial framing. Cheaper alternatives:
/why-review, /plan-validate (run these first if you haven't).
Prompt-Enhance Closing Anchors
- IMPORTANT MUST ATTENTION follow declared step order for this skill; NEVER skip, reorder, or merge steps without explicit user approval
- IMPORTANT MUST ATTENTION for every step/sub-skill call: set
in_progress before execution, set completed after execution
- IMPORTANT MUST ATTENTION every skipped step MUST include explicit reason; every completed step MUST include concise evidence
- IMPORTANT MUST ATTENTION if Task tools unavailable, maintain an equivalent step-by-step plan tracker with synchronized statuses
Anti-Rationalization (reject these excuses)
| Excuse the model tells itself | Reality |
|---|
| "I know this stack — skip the 3-options research" | Familiarity ≠ evidence. Research 3+ options with cited proof per concern, every time. |
| "The architecture is obvious — skip user validation" | Step 12 is MANDATORY. The user owns hard-to-reverse decisions; never auto-decide. |
| "No scale numbers given, I'll just pick a style" | Missing target = explicit Unresolved question, never a silent guess. Quantify via Step-2 first. |
| "It's a small feature — skip the ADR" | If a decision is significant AND costly to reverse, it needs an ADR or it cannot be enforced. |
| "Brownfield, but my preferred style is better" | NEVER re-litigate a settled ADR-recorded decision without a superseding-ADR rationale. |
| "I'll document the budget, enforcement is optional" | Documented-but-unenforced budgets erode. Encode them as executable fitness checks for CI. |
Closing Reminders
IMPORTANT MUST ATTENTION Goal: Deliver a complete, evidence-backed, user-validated architecture decision report — every concern researched with 3+ options, every recommendation carrying confidence % + cited evidence, every decision confirmed by the user — so implementation proceeds on sound, owned architectural choices.
IMPORTANT MUST ATTENTION — Protocols in force (concise digest of the SYNC/shared blocks this skill carries):
- Critical Thinking: traced
file:line proof per claim, confidence >80% to act.
- Sequential Thinking: multi-step Thought N/M with REVISION/BRANCH/HYPOTHESIS, confidence closer.
- AI Mistake Prevention: verify generated content against evidence, trace downstream references, verify all affected outputs, re-read after context loss, surface ambiguity.
MANDATORY IMPORTANT MUST ATTENTION research min 3 options per architecture concern with cited web evidence (stars, last release, downloads, CVE scan) — NEVER recommend from familiarity alone — why: familiarity bias ships unmaintained or insecure dependencies.
MANDATORY IMPORTANT MUST ATTENTION validate decisions with user via AskUserQuestion (Step 12) — NEVER auto-decide a hard-to-reverse choice — why: the user owns hard-to-reverse decisions; the architect proposes, the user confirms.
MANDATORY IMPORTANT MUST ATTENTION quantify Step-2 quality-attribute scenarios (latency p95/p99, throughput, SLO, RPO/RTO, growth, concurrency) — any unknown target becomes an explicit Unresolved question, NEVER a silent guess — why: a style chosen without numbers is a guess, not an enforceable decision.
MANDATORY IMPORTANT MUST ATTENTION brownfield: FIRST read project reference docs + accepted ADRs, constrain research to the existing stack, and NEVER re-litigate a settled ADR-recorded decision without a superseding-ADR rationale — why: re-deciding a recorded choice churns the codebase and breaks downstream conformance checks.
MANDATORY IMPORTANT MUST ATTENTION search 3+ existing patterns/ADRs before proposing any new style or pattern; cite file:line (or URL/benchmark) evidence and a confidence % for EVERY claim — confidence >80% to recommend, <60% DO NOT recommend — why: speculation without proof is forbidden output.
MANDATORY IMPORTANT MUST ATTENTION evaluate fit before copying a nearby pattern — closest example ≠ matching preconditions; verify the new context shares the same scale, constraints, and boundaries — why: a pattern lifted into a mismatched context fails silently.
MANDATORY IMPORTANT MUST ATTENTION produce the two binding downstream contracts — one ADR per hard-to-reverse decision (review-architecture Cat 9 enforces) AND the Scaffold Handoff tool-choices table (scaffold/harness-setup consume) — a decision not written as an ADR or encoded as an executable fitness check cannot be enforced downstream — why: documented-but-unenforced budgets erode silently as code changes.
MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting; mark one in_progress, mark completed immediately after evidence lands; add a final review todo — why: external task state survives context compaction; memory does not.
Anti-Rationalization (Closing — reject these excuses):
| Excuse the model tells itself | Reality |
|---|
| "I know this stack — skip the 3-options research" | Familiarity ≠ evidence. Research 3+ options with cited proof per concern, every time. |
| "The architecture is obvious — skip user validation" | Step 12 is MANDATORY. The user owns hard-to-reverse decisions; never auto-decide. |
| "No scale numbers given, I'll just pick a style" | Missing target = explicit Unresolved question, never a silent guess. Quantify via Step-2 first. |
| "Small feature — skip the ADR / fitness check" | Significant AND costly-to-reverse → needs an ADR + executable fitness rule, or it cannot be enforced. |
| "Brownfield, but my preferred style is better" | NEVER re-litigate a settled ADR-recorded decision without a superseding-ADR rationale. |
| "Found a nearby pattern, just copy it" | Evaluate fit first — same scale/constraints/boundaries? Closest ≠ matching. Verify before reusing. |
MUST ATTENTION apply critical + sequential thinking — every claim needs appropriate traced evidence (file:line for repo/code claims; source URL or artifact section for research, product, content, and docs claims); confidence >80% to act, <60% DO NOT recommend. Anti-hallucination: never present guess as fact, admit uncertainty freely, cross-reference independently, stay skeptical of own confidence.
Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act.
Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.
Sequential Thinking Protocol — Structured multi-step reasoning for complex/ambiguous work. Use when planning, reviewing, debugging, or refining ideas where one-shot reasoning is unsafe.
Trigger when: complex problem decomposition · adaptive plans needing revision · analysis with course correction · unclear/emerging scope · multi-step solutions · hypothesis-driven debugging · cross-cutting trade-off evaluation.
Format (explicit mode — visible thought trail):
Thought N/M: [aspect] — one aspect per thought, state assumptions/uncertaintyThought N/M [REVISION of Thought K]: ... — when prior reasoning invalidated; state Original / Why revised / ImpactThought N/M [BRANCH A from Thought K]: ... — explore alternative; converge with decision rationaleThought N/M [HYPOTHESIS]: ... then [VERIFICATION]: ... — test before actingThought N/N [FINAL] — only when verified, all critical aspects addressed, confidence >80%
Mandatory closers: Confidence % stated · Assumptions listed · Open questions surfaced · Next action concrete.
Stop conditions: confidence <80% on any critical decision → escalate via AskUserQuestion · ≥3 revisions on same thought → re-frame the problem · branch count >3 → split into sub-task.
Implicit mode: apply methodology internally without visible markers when adding markers would clutter the response (routine work where reasoning aids accuracy).
Deep-dive: see /sequential-thinking skill (.claude/skills/sequential-thinking/SKILL.md) for worked examples (API design, debugging, architecture), advanced techniques (spiral refinement, hypothesis testing, convergence), and meta-strategies (uncertainty handling, revision cascades).
AI Mistake Prevention — Failure modes to avoid on every task:
Re-read files after context changes. Context compaction, resume, or long-running work can make memory stale; verify current files before acting.
Verify generated content against source evidence. AI hallucinates APIs, names, claims, and document facts. Check the relevant source before documenting or referencing.
Check downstream references before deleting or renaming. Removing an artifact can stale docs, generated mirrors, configs, and callers; map references first.
Trace the full impact chain after edits. Changing a definition can miss derived outputs and consumers. Follow the affected chain before declaring done.
Verify ALL affected outputs, not just the first. One green check is not all green checks; validate every output surface the change can affect.
Assume existing values are intentional — ask WHY before changing. Before changing a constant, limit, flag, wording, or pattern, read nearby context and history.
Surface ambiguity before acting — don't pick silently. Multiple valid interpretations require an explicit question or stated assumption with risk.
Keep shared guidance role-relevant. Universal guidance must help every receiving skill or agent; code-specific obligations belong only in code-specific protocols.
MANDATORY IMPORTANT MUST ATTENTION use TaskCreate to break ALL work into small tasks BEFORE starting.
MANDATORY IMPORTANT MUST ATTENTION use AskUserQuestion at EVERY decision point — never assume user preferences.
MANDATORY IMPORTANT MUST ATTENTION research top 3 options per architecture concern, compare with evidence, present report with recommendation + confidence %.
External Memory: For complex or lengthy work (research, analysis, scan, review), write intermediate findings and final results to a report file in plans/reports/ — prevents context loss and serves as deliverable.
Evidence Gate: MANDATORY IMPORTANT MUST ATTENTION — every claim, finding, and recommendation requires file:line proof or traced evidence with confidence percentage (>80% to act, <80% must verify first).
MUST ATTENTION apply sequential-thinking — multi-step Thought N/M, REVISION/BRANCH/HYPOTHESIS markers, confidence % closer; see /sequential-thinking skill.
MUST ATTENTION apply AI mistake prevention — verify generated content against evidence, trace downstream references before deleting or renaming, verify all affected outputs, re-read files after context loss, and surface ambiguity before acting.
[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.
[IMPORTANT] Analyze how big the task is and break it into many small todo tasks systematically before starting — this is very important.
