Architecture Cowork Plugin

Run comprehensive quality checks on architecture blueprints. Validates completeness, consistency, best practices, and readiness for implementation. Identifies missing sections, conflicting decisions, and potential issues.

Environment variable setup patterns. Core file covers Node.js (dotenv, NEXT_PUBLIC_, VITE_). Runtime files: python.md (pydantic-settings, Django settings), dotnet.md (appsettings.json, User Secrets), go.md (caarlos0/env, godotenv).

Structural code quality rules applied at write time (implementer, scaffolder) and check time (reviewer). Covers function length, single responsibility, abstraction levels, meaningful naming, magic values, parameter design, boolean traps, DRY, dead code, premature abstraction, frontend component decomposition, null safety, async safety, input validation at boundaries, and concurrency safety.

Compliance frameworks (SOC2, HIPAA, GDPR, PCI DSS) with control mappings and implementation guidance

Convert architecture documents (blueprints, stakeholder presentations) from Markdown to professionally formatted Word (.docx) files. Applies corporate styling, embeds PNG diagrams, and creates presentation-ready documents.

Generate AI-consumable coding rules (CLAUDE.md, .cursorrules, copilot-instructions) and enforcement tooling from SDL

Sync sprint backlog from architecture blueprint to project management tools (Linear, Jira, GitHub Issues, Asana, ClickUp). Creates issues/tasks with user stories, acceptance criteria, priorities, and sprint assignments.

Templates and rules for generating OpenAPI specs, Postman collections, AsyncAPI specs, and GraphQL schemas from architecture manifests

Structured web research methodology for market analysis, competitor research, and technology evaluation. Ensures research uses live web data with source citations and confidence tags.

Generate a context-aware, production-grade design system from the SDL blueprint. Produces design tokens, typography, palette, motion language, and component inventory — grounded in the product domain, audience, and architecture. Use this skill when generating or refining the SDL design section, scaffolding frontend projects, or when the user asks about visual direction.

Patterns for metrics, tracing, logging, alerting, dashboards, and SLO definition

Solution Design Language (SDL) specification — schema, validation, normalization, and generation rules

Real pricing data for cloud compute, databases, LLM tokens, auth, payments, email, hosting, and monitoring services. Use when estimating infrastructure or operational costs.

Generate OpenAPI 3.0 specification from blueprint API documentation. Creates interactive API docs that can be imported into Postman, Swagger UI, and other API testing tools.

Setup steps, credentials, free tiers, and documentation links for 70+ commonly used services. Use when listing required accounts or recommending third-party services.

Generate comprehensive security audit checklist from architecture blueprint. Covers OWASP Top 10, data security, authentication, authorization, secrets management, compliance, and testing procedures.

Extract and render all Mermaid diagrams from architecture blueprints to PNG images. Creates a diagrams/ folder with high-quality images ready for presentations and documentation.

Detects the current project stage (concept/mvp/growth/enterprise) from _state.json field presence and completeness

Generate presentation-ready Word documents for stakeholder discussions. Translates technical architecture blueprints into business-focused presentations with diagrams, cost analysis, and approval checklists.

Mermaid diagram templates for solution architecture, service communication, C4 Context/Container, data flow, agent flow, deployment, and sequence diagrams. Use when generating architecture diagrams.

Test naming conventions, fixture patterns, mocking strategies, and coverage thresholds by stage

Six-pillar well-architected framework for evaluating architecture quality — operational excellence, security, reliability, performance, cost optimization, and developer experience

Defines the rules used by /architect:validate-consistency to detect conflicts across project outputs

Maps project constraints (budget, team size, timeline, ops maturity, compliance) to architecture decisions

Quantifies exact trade-offs when switching between architecture options

AI agent orchestration patterns (ReAct, chain-of-thought, multi-agent), tool design, memory strategies, guardrails, and token cost modeling. Use when designing AI agent systems.

10-factor weighted scoring methodology for assessing build difficulty. Includes factor definitions, scoring guides, and agent/hybrid adjustments. Use when assessing project complexity.

Canonical system manifest format with all enumerated types for project, frontend, service, database, integration, LLM, agent, and communication components. Use when structuring architecture output.

JSON wireframe spec patterns — SDL-to-screen mapping and section examples for each screen type.

Step-by-step remediation procedures for the consistency rules used by /architect:validate-consistency --fix

ORM and data model generation patterns. Core file covers Node.js (Prisma/Drizzle/TypeORM). Runtime-specific files: python.md (SQLAlchemy/Django ORM), dotnet.md (EF Core), go.md (GORM/sqlc).

Verifies that chosen technologies integrate well together before a stack decision is committed

Architecture pattern selection, folder structures, coding conventions, error handling, testing strategies, and platform-specific patterns for structuring application code

Security architecture, observability, CI/CD pipelines, database migrations, and environment strategy patterns for production-ready systems

Core Node.js patterns + cross-runtime reference. For Python see python.md, for .NET see dotnet.md, for Go see go.md.

Estimates cost and effort to switch from one tech stack to another

Shows cost and performance impact of what-if infrastructure changes before committing to them

Communication guidelines for non-technical founders. Plain English defaults, analogy-first explanations, progressive disclosure. Use when generating any user-facing architecture output.

Detects product type from user requirements to trigger domain-specific architecture depth sections

Validates that a command can execute before running it, failing fast on missing prerequisites or invalid state

SDL generators for Docker Compose, Kubernetes, Monitoring, Nginx, and Deploy Diagram