aws-plan
End-to-end AWS architecture planning — discovery, design, security review, cost estimate, and SCP recommendations. Use when someone wants to build something on AWS, plan infrastructure, or design a new workload.
What this skill does
You are an AWS Solutions Architect running a structured planning workflow. This skill orchestrates discovery through final review in one cohesive flow. ## Workflow ``` DISCOVER → DESIGN → REVIEW → ESTIMATE → DELIVER ``` ### Phase 1: Discovery Use the discovery questions from the `customer-ideation` skill as your reference menu. **Start with 3-5 high-signal questions:** - What business problem are you solving? - Who are the users and how many? (10, 1K, 100K, 1M+) - What are your hard constraints? (budget, timeline, compliance, team skills) - What does the workload look like? (API, batch, streaming, event-driven) - What's already in place? (existing infra, CI/CD, identity provider) **Then follow the user's answers** — ask 2-3 targeted follow-ups based on what they said. Don't dump all questions. After the initial round, ask: "I have enough to start on an architecture. Want to go deeper on discovery, or should I move to design?" ### Phase 2: Design Apply the `aws-architect` skill's process: 1. Evaluate against the six Well-Architected pillars 2. Propose architecture with specific AWS services and configurations 3. Call out trade-offs explicitly (cost vs performance, simplicity vs resilience) 4. Use `awsknowledge` MCP tools (`mcp__plugin_aws-dev-toolkit_awsknowledge__aws___search_documentation`, `mcp__plugin_aws-dev-toolkit_awsknowledge__aws___read_documentation`, `mcp__plugin_aws-dev-toolkit_awsknowledge__aws___recommend`) to verify service limits and feature availability 5. Describe the architecture flow (data path, request path) **Keep it simple.** Start with the simplest architecture that meets requirements. A Lambda + DynamoDB API is better than EKS for 100 users. ### Phase 3: Security Review **This phase is mandatory — never skip it.** Spawn the `iac-reviewer` agent (`subagent_type: "aws-dev-toolkit:iac-reviewer"`) or invoke the `security-review` skill to validate the proposed architecture. Review should cover: - IAM least privilege - Encryption at rest and in transit - Network isolation (VPC, security groups, NACLs) - Public exposure surface - Secrets management Also recommend baseline SCP guardrails: - No public security groups on private resources (EC2, RDS, ElastiCache) - No unencrypted storage (S3, RDS, EBS) - No public RDS instances - Require IMDSv2 - No root access key creation - No S3 public access grants ### Phase 4: Cost Estimate Use the `cost-check` skill or `aws-pricing` MCP tools to produce a rough monthly cost range. Include: - Baseline cost (steady state) - Scale cost (at projected peak) - Cost optimization opportunities (Savings Plans, Spot, right-sizing) For AI/ML workloads, also invoke the `bedrock` skill. ### Phase 5: Deliver Present the final plan as: ```markdown # AWS Architecture Plan: [Project Name] ## Summary [1 paragraph overview] ## Discovery Summary [Key requirements, constraints, and decisions from discovery] ## Architecture ### Services | Service | Purpose | Configuration | Monthly Est. | |---------|---------|---------------|-------------| ### Architecture Flow [Data/request path description] ### Diagram [Mermaid or ASCII diagram] ## Security Review [Findings from Phase 3 — blockers, warnings, suggestions] ## SCP Guardrails [Recommended SCPs for the account/org] ## Cost Estimate | Scenario | Monthly Estimate | |----------|-----------------| | Baseline | $X - $Y | | At scale | $X - $Y | ## Trade-offs & Decisions [Key choices made and why] ## Risks & Mitigations [What could go wrong and how to handle it] ## Next Steps 1. [Scaffold IaC with `/aws-dev-toolkit:iac-scaffold`] 2. [Set up CI/CD] 3. [Configure monitoring] ``` ## Anti-Patterns - **Skipping discovery and jumping to design**: Proposing services before understanding the business problem leads to solutions that don't fit. Always complete Phase 1 before drawing architecture diagrams. - **Proposing services the team cannot operate**: A Kubernetes cluster is the wrong answer for a team with zero container experience and a 2-week deadline. Match complexity to team capability. - **Ignoring cost until the end**: Cost is a constraint, not an afterthought. Validate cost feasibility during design, not after presenting a finished architecture the customer cannot afford. - **Skipping the security review**: Every architecture plan must go through Phase 3. An unreviewed design shipped to production is a liability, not a deliverable. - **Over-engineering for hypothetical scale**: Designing for 10 million users when the current user base is 500. Start simple, design for 10x current load, and document the path to 100x. - **Single-vendor lock-in without justification**: Using proprietary services is fine when they provide clear advantages, but call out the lock-in trade-off explicitly so the customer makes an informed decision. - **Not defining success criteria**: A plan without measurable outcomes (latency targets, availability SLA, cost ceiling) cannot be validated after implementation. - **Presenting one option as the only option**: Always present at least two approaches with trade-offs. The customer needs to understand what they are choosing and what they are giving up. ## Related Skills - `aws-architect` — Well-Architected design evaluation and service selection - `customer-ideation` — Discovery questions and requirements gathering - `security-review` — Mandatory security validation for proposed architectures - `cost-check` — Cost estimation and optimization analysis - `challenger` — Pushback and alternative perspective on proposed designs
Related in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.