self-consistency
Generate N independent reasoning paths and vote on the answer. Use for architectural trade-offs, ambiguous design decisions, or when single-path reasoning risks locking onto the first plausible answer. Paper: Wang et al. 2022.
What this skill does
> **AI-consumed reference.** Optimized for Claude to read during execution. > Human-readable explanation: see [docs/architecture/HIERARCHICAL_PLANNING.md](../../../docs/architecture/HIERARCHICAL_PLANNING.md) > or [docs/getting-started/](../../../docs/getting-started/) depending on topic. # Self-Consistency For ambiguous design decisions with multiple plausible answers. Generate multiple independent paths, take the majority. **Governed by:** `rules/workflow/self-consistency.md` (when / why) --- ## When NOT to Use - Single-answer tasks (file rename, typo) - Quick/Standard complexity — cost doesn't pay back - User said `must do:` / `just do:` / `no discussion` - Budget already >85% of session limit --- ## The Protocol ### Step 1 — Frame the decision Write the decision as a question with ≥2 possible answers: > "Should the API use REST or GraphQL?" > "Monolith, modular monolith, or microservices?" > "Redis for cache vs in-memory LRU?" If the question has only one sensible answer, skip SC. ### Step 2 — Generate N = 3 paths For each path, reason from scratch in an isolated context: ``` Path 1: - Consider user scale (est. 10K DAU for this product) - Consider team size (2 backend devs) - Consider infra (already on Fly.io, no k8s expertise) → Answer: Modular monolith Path 2: - Consider dev velocity (team ships weekly) - Consider deploy complexity (monorepo, single deploy) - Consider failure domains (single point of failure OK at this scale) → Answer: Modular monolith Path 3: - Consider future scale (could hit 100K DAU in 12mo) - Consider hiring plan (doubling team in 6mo) - Consider isolation needs (auth service is security-critical) → Answer: Microservices (start with auth as separate service) ``` Each path should use **different starting considerations** — don't copy-paste one reasoning with cosmetic changes. ### Step 3 — Extract answers, count votes ``` Answers: [modular monolith, modular monolith, microservices] Votes: modular monolith: 2 | microservices: 1 Winner: modular monolith (2/3 majority) ``` ### Step 4 — Report If clear majority (2/3 or 3/3): > **Decision: Modular monolith (2/3 paths agreed)** > > Both winning paths cited scale (10K DAU), team size (2 devs), and existing Fly.io infra. The dissenting path optimized for 12-month scale which is speculative. > > Flagging dissent: if hiring doubles and we hit 100K DAU fast, consider extracting auth service as a Phase 2 refactor. If no majority (1/1/1 with 3 different answers): > **Paths disagreed — pausing to ask.** > > Path 1 → REST (simplicity) > Path 2 → GraphQL (client flexibility) > Path 3 → tRPC (end-to-end types) > > Which constraint matters most to you: simplicity, client flexibility, or type safety across client/server? Per `rules/core/no-assumption.md` — when paths disagree, ask rather than pick. --- ## Anti-Patterns - **Cosmetic paths** — same reasoning with word swaps. Don't. Each path must start from different considerations. - **Forcing consensus** — if paths disagree, don't pick silently. Ask. - **N > 3** — diminishing returns. 3 catches most issues; 5+ is expensive and rarely changes the answer. - **Using SC for non-trade-offs** — if the answer is obvious, skip this. SC costs 3× tokens. --- ## Output Format ```markdown ## Decision: [Answer] **Votes:** [X/N paths] **Majority reasoning:** [1-2 sentence summary of why the winning paths agreed] **Dissent:** [if any — what the losing path(s) prioritized] **Flag for Phase 5:** [any follow-up action implied by dissent] ``` --- ## Tie-Ins - `rules/workflow/self-consistency.md` — policy - `rules/workflow/tree-of-thoughts.md` — for branching exploration (different technique) - `rules/core/no-assumption.md` — when to escalate to user - `skills/chain-of-verification/SKILL.md` — verify the SC winner's facts
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.