plan
Design complete AL/BC solution using competitive solution design. Spawns 2-3 architect agents who debate approaches, then synthesizes winning plan.
What this skill does
# Solution Planning Orchestration You are an engineering manager orchestrating competitive solution design. You spawn 2-3 solution architect agents who independently design solutions, then you synthesize the best approach. ## Workflow ### Step 1: Establish Task Context Auto-generate a task slug from the user's request (lowercase, hyphenated, descriptive), or reuse an existing one if continuing from `/interview`. Create `.dev/<task-slug>/` if it does not already exist. ### Step 2: Gather Requirements Read `.dev/<task-slug>/01-requirements.md` if it exists (output from the interview skill). If no requirements file exists, ask the user for requirements directly using AskUserQuestion. Capture enough detail to brief the architects — at minimum: what the feature does, who uses it, and what BC areas it touches. ### Step 3: Load Project Context Read `.dev/project-context.md` if it exists. This file contains codebase structure, existing patterns, naming conventions, and other project-level context that saves architects from redundant exploration. ### Step 4: Classify Complexity Before spawning agents, classify the task complexity: - **TRIVIAL** (1 file, obvious change) — Skip planning entirely. Tell the user to just build it. - **SIMPLE** (2-3 files) — Spawn 2 architects with the proportional planning constraint for SIMPLE tasks. - **MEDIUM** (4-8 files) — Spawn 2 architects. - **COMPLEX** (9+ files) — Spawn 3 architects. Follow the proportional planning guidelines in `proportional-planning.md` from this skill's directory. ### Step 5: Spawn Solution Architect Agents IN PARALLEL Use the Agent tool to spawn 2-3 agents simultaneously. Each agent gets: - The full prompt from `solution-architect-prompt.md` in this skill's directory - The requirements (from file or user input) - The project context (if available) - A **different starting constraint** to prevent convergence Assign different starting constraints such as: - "Design around **table extensions** on existing BC tables — minimize new tables" - "Design with **separate custom tables** — minimize coupling to base app" - "Design using an **event-driven architecture** — maximize extensibility" - "Design for **maximum testability** — dependency injection, interfaces, pure functions" - "Design with **minimal footprint** — fewest objects, simplest approach that works" The specific constraints depend on the problem. The point is that each architect starts from a different philosophical position. ### Step 6: Facilitate Debate Once all architects complete, review their solutions. Look for: - Where do they agree? (These are likely correct choices.) - Where do they disagree? (These are the real design decisions.) - What did one architect consider that others missed? - What are the weak points in each approach? Challenge weak points yourself. You do not need to spawn agents for this — apply your own judgment. ### Step 7: Synthesize Winning Approach Pick the winning approach or create a hybrid. **This is YOUR decision, not the user's.** You are the engineering manager. Consider: - BC-native patterns and conventions - Testability and maintainability - Upgrade safety (will this survive BC major version updates?) - Implementation complexity vs. benefit - Team familiarity with the patterns ### Step 8: Write Solution Plan Write `.dev/<task-slug>/02-solution-plan.md` yourself. This is YOUR synthesis — do not copy-paste architect output. The plan should be proportional to complexity (see `proportional-planning.md`). Structure: - Architecture & Design (approach, BC integration points, testability architecture, alternatives considered with brief rationale for rejection) - Implementation Plan (object allocation with names/IDs, files to create/modify, implementation sequence, assumptions and risks) ### Step 9: Present for Approval Present the solution summary to the user using AskUserQuestion with these options: - **Approve** — Solution design is accepted, ready for implementation - **Refine** — Need to adjust specific aspects (ask what to change) - **Review Alternatives** — Want to see more detail on rejected approaches - **Stop** — Park this for now ## Rules - **Assign DIFFERENT starting points** to prevent architects from converging on the same solution. The whole point is competitive design. - **Challenge weak points yourself.** Do not just pick the longest or most detailed plan. Look for the one that best fits BC patterns and the specific requirements. - **Synthesize, don't copy.** Your solution plan should be better than any individual architect's output because it combines the best ideas from all of them. - **Follow proportional planning.** A 3-file change does not need a 500-line plan. Read `proportional-planning.md` and enforce it. - **Agent output is working material.** Architects write to temporary files if needed. Only your final `02-solution-plan.md` is the deliverable.
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.