brainstorm
Workflow-first design through collaborative dialogue. Use before creating features, building components, or modifying behavior.
What this skill does
# Feature Tree Brainstorming Turn ideas into fully formed plans through collaborative dialogue. **Four phases:** Discovery → Product → Design → Specification --- ## CRITICAL: How to Use This Skill **ONE QUESTION AT A TIME.** Do NOT dump all questions at once. That produces shallow, useless answers. For each question: 1. Present the question 2. ULTRATHINK — deeply consider it, write your thinking 3. Ask user: "Does this seem right?" or "Is this the right read?" 4. Wait for user response 5. Only then move to next question **DO NOT MOVE TO NEXT PHASE UNLESS USER EXPLICITLY AGREES.** At the end of each phase, ask: "Phase N complete. Ready for Phase N+1?" Wait for "ok" or "yes" before continuing. This is collaborative dialogue, not a checklist dump. --- ## Phase 1: Discovery Push yourself to think. Don't skip these. ### First Principle — Find Actual Intention Users communicate in solutions, not problems. "Add a spinner" might mean "page feels slow." Ask yourself: - What did they say? (surface) - Why did they say it? (intention) - Is there a better approach? ### Crux — Core Assumption Every project has ONE assumption that must be true or everything falls apart. Ask yourself: - What's the ONE thing that must be true? - How do we test it before building everything else? ### Pre-Mortem — How This Fails Imagine it failed. Why? Ask yourself: - "It failed because..." (top 3 reasons) - What are early warning signs? - What can we do to prevent each? ### Scope Fence — What This Is NOT Scope creep kills projects. Define the boundaries. Ask yourself: - This IS: [one sentence] - This is NOT: [explicit exclusions] - Features we're saying no to? ### User Day-In-Life — Who Specifically "Users" is too vague. Pick a real person. Ask yourself: - Who specifically has this problem? - When in their day does it appear? - What do they do now? What's annoying about it? --- ## Phase 2: Product Think like you're explaining to a YC partner. Capture the essence. ### What IS This Product? Not the features. The VALUE. Ask yourself: - If I had 30 seconds to explain this, what would I say? - What's the ONE thing that makes this valuable? - What's the core experience? ### Core Workflows Identify the workflows that ARE the product (not supporting stuff like auth). For each core workflow: - Write the Description (YC partner level) - Write the Steps (the actual user experience) This is human thinking. No technical details yet. --- ## Phase 3: Design Technical thinking. Consider alternatives, find simplicity, identify risks. ### Approaches & Trade-offs Don't jump to first solution. Ask yourself: - What are 2-3 ways to solve this? - What are the trade-offs of each? - Which fits this context best? Why? ### Simplest Thing That Works Complexity is the enemy. Ask yourself: - What's the minimal solution? - What can we NOT build? - What complexity are we avoiding? ### Hard Parts / Where It Breaks Every design has weak points. Ask yourself: - What's the technically risky part? - Where will this fail first? - What needs extra attention during implementation? --- ## Phase 4: Specification Output the plan. Workflows first, always. ### Output Format ```markdown # [Topic] Plan ## Summary [What we're building, why, for whom — 2-3 sentences] ## Workflows ### WORKFLOW.id — Workflow Name **Status:** planned **Description:** [YC partner explanation — what this journey IS, why it matters] **Steps:** 1. [Detailed step — what user does, what system does] 2. [Next step...] 3. [...] **Depends on:** FEATURE.id, FEATURE.id --- ### WORKFLOW.id — Another Workflow ... --- ## Features ### FEATURE.id — Feature Name **Status:** planned **Description:** [YC partner explanation — what it does, user-facing] **Technical Notes:** [How it works, gotchas, implementation details — enough for Claude to implement without asking questions] **Uses:** INFRA.id, FEATURE.id --- ### INFRA.id — Infrastructure Feature **Status:** planned **Description:** [What it provides] **Technical Notes:** [Technical details] **Uses:** — --- ## Implementation Order Group by commit. Distribute effort evenly — big features get own commit, small ones batch together. ### Commit 1: [Group Name] - [ ] INFRA.database — setup connection pool - [ ] INFRA.config — env-based config (small, related → batch together) ### Commit 2: [Big Feature Name] - [ ] AUTH.login — validate credentials, create session, handle errors (complex feature → own commit) ### Commit 3: [Group Name] - [ ] AUTH.logout — destroy session - [ ] AUTH.refresh — refresh token (small, related → batch together) ### Commit 4: [Integration] - [ ] USER.login_flow — end-to-end test (workflow integration test) **Grouping rules:** - Big/complex feature → own commit - Small/simple features → batch with related ones - Each commit should be test-able with REAL testing - If a group feels too big to test confidently → split it ## Decisions - [Decision]: [Why we chose this over alternatives] - [Decision]: [Why] ``` ### Key Points for Specification - **Workflows FIRST** — Always - **Self-contained detail** — Description + Technical Notes + Steps should be complete enough that Claude can implement without further questions - **Status markers** — planned / in-progress / done - **Commit grouping** — Group by effort: big features alone, small features batched - **Each commit must be testable** — If you can't test it REAL, the group is wrong --- ## After Plan Approval ### 1. Save Plan Write to `docs/plans/YYYY-MM-DD-<topic>.md` ### 2. Create in Feature Tree Create the workflows and features in Feature Tree: ``` add_workflow(id="...", name="...", description="...", purpose="...", steps=[...], depends_on=[...]) add_feature(id="...", name="...", description="...", technical_notes="...", uses=[...]) ``` ### 3. Sync to Memory **Use sub-skill:** `ft-mem:brainstorm-sync` Syncs discoveries to CONTEXT.md and memories. ### 4. Implementation **Use sub-skill:** `feature-tree:executing-plans` Implements the plan task-by-task with commits between. --- ## Principles - **Workflow-first, always** — Broad context before details - **Think, don't checkbox** — Mind tools push real thinking - **Self-contained output** — Plan needs no further explanation - **Simplest thing that works** — YAGNI ruthlessly - **Capture WHY** — Decisions include rationale
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.