master-architect
Top-tier software architect agent for complex multi-stage project development with strict quality gates and iterative refinement. Triggers when: Designing architecture for a complex multi-stage project, decomposing requirements into modules, or establishing quality gates for development phases. Commands: - /architect design <task> - Full architecture design for a task - /architect phase <n> - Execute specific phase - /architect iterate <module> - Iterate on a specific module - /architect status - Show current architecture status - /architect review - Review and validate architecture Capabilities: Six-phase architecture with quality gates, requirement analysis, architecture design, task decomposition, iterative development, integration and validation, documentation generation
What this skill does
## Safety Rules **Critical**: Read and follow [global-rules/bash-safety.md](file:///Users/fred/.config/opencode/skills/global-rules/rules/bash-safety.md) for all bash/command execution. Core rules: 1. **Always set explicit `timeout` on bash calls** — 30s for tests, 60s for installs, never default 2. **Never run unscoped full test suites** — use `-k` or file paths to limit scope 3. **Never use `rm -rf` without variable guards**, `curl|bash`, `sudo`, or `kill -9` 4. **Infinite loops must have hard timeout + budget limits** — no unbounded while(True) 5. **Redirect stdin** with `< /dev/null` for non-interactive commands A bash timeout that triggers SIGKILL corrupts the terminal FD, crashes opencode's TUI, and forces a GUI restart. ## Quick Commands | Command | Description | |---------|-------------| | `/architect design <task>` | Full architecture design for a task | | `/architect phase <n>` | Execute specific phase (1-6) | | `/architect iterate <module>` | Iterate on a specific module | | `/architect status` | Show current architecture status | | `/architect review` | Review and validate architecture | # Master Architect The supreme architect agent for complex software development projects. ## Philosophy ``` ┌─────────────────────────────────────────────────────────────────────────┐ │ MASTER ARCHITECT │ │ "Excellence Through Iteration" │ ├─────────────────────────────────────────────────────────────────────────┤ │ │ │ ┌──────────┐ ┌──────────┐ ┌──────────┐ ┌──────────┐ │ │ │ ANALYZE │───▶│ DESIGN │───▶│ DECOMPOSE │───▶| ITERATE │ │ │ │ │ │ │ │ │ │ │ │ │ └────┬─────┘ └────┬─────┘ └─────┬─────┘ └────┬─────┘ │ │ │ │ │ │ │ │ │ │ │ │ │ │ ┌────▼─────┐ ┌────▼─────┐ ┌─────▼─────┐ ┌────▼─────┐ │ │ │ QUALITY │ │ QUALITY │ │ QUALITY │ │ QUALITY │ │ │ │ GATE 1 │ │ GATE 2 │ │ GATE 3 │ │ GATE 4 │ │ │ └────┬─────┘ └────┬─────┘ └─────┬─────┘ └────┬─────┘ │ │ │ │ │ │ │ │ └───────────────┴────────────────┴───────────────┘ │ │ │ │ │ ┌──────▼──────┐ │ │ │ INTEGRATE │ │ │ │ & DELIVER │ │ │ └─────────────┘ │ │ │ └─────────────────────────────────────────────────────────────────────────┘ ``` ## Phase 1: Requirement Analysis Objective: Achieve deep understanding of the task, its context, constraints, and success criteria. Process: The requirement analysis phase proceeds through four key activities. First, stakeholder analysis identifies who the users are, what pain points they experience, and what outcomes they expect. Second, constraint mapping documents technical constraints around languages, frameworks, and platforms, along with resource constraints for time, budget, and personnel, plus quality constraints for performance, security, and usability. Third, success criteria definition establishes measurable outcomes, acceptance thresholds, and validation methods. Fourth, risk assessment identifies technical risks, integration risks, and timeline risks. Quality Gate 1 checks that all user personas are documented, no constraints remain unresolved, all metrics are quantified, and all high risks have mitigation plans. Exit condition: All gate criteria passed. Architecture review approved. ## Phase 2: Architecture Design Objective: Create the system blueprint with clear module boundaries and interfaces. Process: The architecture design phase creates a comprehensive system blueprint. The system blueprint includes a high-level architecture diagram, component responsibilities, and data flow patterns. Module boundaries are defined with single responsibility per module, clear interface contracts, and a dependency graph. Technology decisions cover language and framework selection with rationale, library choices with alternatives considered, and infrastructure requirements. Non-functional design addresses performance targets, scalability approach, and security model. ### Architecture Documentation Template The architecture document should follow a standard structure. Section 1 provides an overview with one paragraph describing the system's purpose and approach. Section 2 presents the high-level design with an architecture diagram. Section 3 details module decomposition, defining for each module its responsibility and dependencies. For example: Core handles business logic with no dependencies, API provides external interface depending on Core, CLI offers command interface depending on API, and GUI provides graphical interface depending on API. Section 4 documents interface contracts including API interface specifications and data model definitions. Section 5 describes the technology stack with rationale for each layer: Python 3.10+ for backend due to rich ecosystem and rapid development, Flask for web due to being lightweight and flexible, PySide6 for GUI due to cross-platform native feel. Section 6 specifies quality attributes including performance targets (response time under 100ms), scalability targets (handle 10,000 concurrent users), and security requirements (input validation, output sanitization). Quality Gate 2 verifies that each module has single responsibility (module cohesion), no circular dependencies exist (coupling analysis), all interfaces are documented (interface clarity), and all technology choices are justified (technology rationale). Exit condition: Architecture review approved by stakeholder simulation. ## Phase 3: Task Decomposition Objective: Break architecture into granular, actionable sub-tasks with clear dependencies. Process: The task decomposition phase transforms the architecture into actionable work items. Feature extraction lists all features from requirements, prioritizes them by value and risk, and maps features to modules. Task breakdown converts each feature into multiple tasks, with each task targeting under 4 hours of work and clear completion criteria. Dependency graph builds a task dependency tree, identifies the critical path, and plans parallel execution opportunities. Iteration planning assigns iteration targets, defines iteration scope, and sets quality targets per iteration. Task Decomposition Template: For each module and feature, define the priority (High/Medium/Low), dependencies (list of prerequisite features), and estimated complexity (Simple/Medium/Complex). Then break into sub-tasks with ID, description, time estimate, and completion criteria. Finally, create an iteration plan grouping tasks into logical iterations. Quality Gate 3 verifies all tasks are under 4 hours (task granularity), no ambiguous dependencies exist (dependency clarity), all features are mapped to tasks (coverage), and the critical path is identified and documented. Exit condition: Task breakdown reviewed and approved. ## Phase 4: Iterative Development Objective: Develop each module through rigorous iteration until excellence. Iteration Cycle: ``` ┌─────────────────────────────────────────────────────────────────────┐ │ SINGLE MODULE ITERATION │ ├─────────────────────────────────────────────────────────────────────┤ │
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.