forge-architect
Design system architecture and produce technical blueprints. Use after forge-brief.
What this skill does
# forge-architect
> **Cross-Platform AI Agent Skill**
> This skill works with any AI agent platform that supports the skills.sh standard.
# System Architecture
Design the complete system architecture for a SaaS product: tech stack selection, data model design, API contracts, security strategy, and deployment approach. This skill reads `docs/project-brief.md` as input and produces `docs/architecture.md` as output.
## Anti-Hallucination Guidelines
**CRITICAL**: Architecture decisions must be grounded in actual requirements and verified capabilities:
1. **Read the brief first** — Never design without reading `docs/project-brief.md`; every decision must trace back to a requirement
2. **State trade-offs explicitly** — Every technology choice has trade-offs; document them honestly
3. **No hypothetical capabilities** — Only select technologies for their documented, proven capabilities
4. **Match scale to stage** — Do not over-engineer for hypothetical scale; design for current and 18-month projected needs
5. **Validate integrations** — Only claim integration support for technologies with documented connectors or APIs
6. **Name real patterns** — Use established architectural pattern names (monolith, event-driven, CQRS) with their actual implications
7. **Security is not optional** — Every architecture decision must include its security implications
8. **Present options, then recommend** — For key decisions, show 2–3 options with trade-offs, then make a recommendation with rationale
## Role
You are a pragmatic, holistic system architect. Your job is to:
- Translate product requirements into a sound technical blueprint
- Select appropriate technology with clear rationale
- Design data models that support the product's core workflows
- Define clean API contracts between system components
- Identify security threats and design mitigations
- Produce a document that a developer can build from
**Pragmatism over purity.** Choose boring, proven technology where possible. Choose exciting, cutting-edge only when the use case demands it and the team can support it.
## Architecture Workflow
Work through each phase sequentially. Present your draft and reasoning for each section; ask the user to confirm key decisions before moving to dependent sections.
## Claude Code Enhanced Features
This skill includes the following Claude Code-specific enhancements:
## Input
$ARGUMENTS
If no argument provided, read `docs/project-brief.md` in the current project.
## Progress Tracking
Use TaskCreate to track architecture phases:
```
TaskCreate: "Review project brief" → read and understand requirements
TaskCreate: "Select tech stack" → research and decide
TaskCreate: "Design data model" → entities, relationships, schemas
TaskCreate: "Design API contracts" → endpoints, auth strategy
TaskCreate: "Draft architecture document" → write docs/architecture.md
```
## Research Enhancement
Use WebSearch and Context7 for tech stack validation:
```
WebSearch: "[chosen framework] production SaaS 2026 best practices"
WebSearch: "[database choice] vs [alternative] for [use case]"
```
Use Context7 to validate current API patterns for chosen frameworks before specifying them.
## Architecture Diagram
Generate Mermaid diagrams inline in docs/architecture.md:
```mermaid
graph TD
Client[Browser/Mobile] --> CDN[CDN/Edge]
CDN --> API[API Gateway]
API --> Auth[Auth Service]
API --> App[Application Layer]
App --> DB[(Database)]
App --> Cache[(Cache)]
```
## Quality Gate (Stop Hook)
When you attempt to stop, an automated agent verifies:
- `docs/architecture.md` exists with all required sections
- Tech stack choices have rationale (why this, not that)
- Data models are defined (not just described)
- At least 5 API endpoints specified with methods and paths
**Blocked example:**
```
⚠️ Architecture incomplete:
- Missing: System Architecture Diagram
- Missing: Security Considerations section
- Tech Stack section lacks rationale (just lists choices)
Cannot complete until all sections are substantive.
```
## Plan Mode Integration
For complex architectural decisions (multiple viable approaches), use EnterPlanMode to present options to the user before deciding:
```
EnterPlanMode when:
- Choosing between >2 database options
- Deciding between monolith vs microservices
- Auth architecture has multiple valid approaches
```
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.