figma-blueprint
This skill should be used when the user asks to "visualize architecture in Figma", "create architecture diagrams", "push diagrams to FigJam", "diagram the codebase", "architecture to figma", "create figma boards from code", or wants to turn codebase structure or documentation into FigJam architectural diagrams.
What this skill does
# Figma Blueprint Generate FigJam architectural diagrams from codebase analysis. Explore source code and documentation, extract architectural patterns, convert to Mermaid syntax, and push to FigJam via Figma MCP tools. ## When to Use - User wants visual architecture diagrams derived from their codebase - User mentions "figma", "diagram", "visualize architecture", "architecture to figma" - User provides docs (PRD, system design, implementation plans) they want turned into visual boards - User wants to update existing FigJam boards with current codebase state ## Workflow ### Phase 1 — Codebase Exploration Delegate exploration to a sub-agent (subagent_type: Explore) to avoid polluting the main context. The sub-agent should: 1. Read source files, not just list them — extract class names, function signatures, module relationships 2. Read documentation — PRD, architecture docs, implementation plans, test frameworks 3. Read configuration — docker-compose, CI/CD, infrastructure configs 4. Return a structured summary of: components, layers, data flows, dependencies, and infrastructure Provide the sub-agent with a thorough prompt specifying exactly what to extract. Target architectural structure, not implementation details. ### Phase 2 — Diagram Identification From the exploration results, identify diagram candidates. Common diagram types: | Type | Mermaid Syntax | Best For | |------|---------------|----------| | System architecture | `flowchart TB/LR` | Layer stacks, component relationships | | Data flow | `flowchart LR` | Memory tiers, message pipelines | | Sequence diagram | `sequenceDiagram` | Request flows, message handling | | Timeline/Roadmap | `gantt` | Phase planning, milestones | | Component detail | `flowchart TB` with subgraphs | Zoomed-in subsystem views | Prioritize diagrams that show relationships not obvious from reading individual files. ### Phase 3 — Mermaid Conversion Convert each diagram candidate to Mermaid syntax. Guidelines: - Use `subgraph` sections for logical groupings (layers, tiers, services) - Add meaningful labels with key specs (latency targets, TTLs, port numbers) - Apply color coding via `style` directives to distinguish component categories - Keep node labels concise — full details belong in the docs, not the diagram - For sequence diagrams, show the happy path first; edge cases are secondary ### Phase 4 — FigJam Generation Two paths depending on whether boards exist: **New boards** — Use `generate_diagram` (from either `mcp__claude_ai_Figma__generate_diagram` or `mcp__plugin_figma_figma__generate_diagram`): - Each call creates a separate FigJam board - Returns a claim URL the user must open to save the board to their account - Present all claim links in a clear numbered list with descriptions **Existing boards** — Use `use_figma` (requires the `figma:figma-use` skill loaded first): - Write directly to existing FigJam boards via file key - No claim links needed — changes appear immediately - Prefer the local plugin (`plugin:figma:figma`) for direct read/write **Figma MCP priority:** Prefer the local plugin (`plugin:figma:figma`) over the Claude.ai built-in (`claude.ai/Figma`) when both are available. The local plugin provides direct OAuth-based access without claim links for existing boards. ### Phase 5 — Persistence (Optional) Save board references to project memory for future sessions: 1. Write a reference memory file with board URL, file key, root node ID, and content description 2. Update MEMORY.md index with a one-liner pointer This enables future sessions to read/update boards without the user re-sharing URLs. ## Diagram Candidates Checklist When exploring a codebase, look for these architectural patterns: - **System layers** — How do components stack? (ingestion → processing → storage) - **Data tiers** — Memory hierarchy, caching strategy, promotion/eviction flows - **Message/request flow** — End-to-end path from user input to response - **Infrastructure** — Docker services, databases, monitoring, networking - **Deployment** — Environments, CI/CD pipeline, cloud architecture - **Roadmap** — Development phases, milestones, dependencies between phases - **Component internals** — Zoomed-in views of complex subsystems ## Additional Resources ### Reference Files - **`references/mermaid-patterns.md`** — Common Mermaid syntax patterns optimized for FigJam rendering, including color schemes, subgraph layouts, and connector styles that render well in FigJam
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.