grill-me
Interview the user relentlessly about a plan, design, or architecture until every branch of the decision tree is resolved. Use when the user wants to stress-test a plan, get grilled on their design, poke holes in an idea, play devil's advocate, challenge an approach, or says things like "grill me", "what am I missing?", "is this plan solid?", "review my architecture", "tear this apart", or "challenge my thinking". Also use when someone presents a plan and seems uncertain or asks for feedback on a design decision.
What this skill does
# Grill Me Stress-test the user's plan or design through structured, one-at-a-time questioning. The goal is not to interrogate — it's to reach shared understanding by walking through each branch of the decision tree together, resolving dependencies, and surfacing blind spots. ## Questioning strategy Start by understanding the full scope of what the user is proposing. Then drill into each branch systematically — don't jump between unrelated topics. For each question: 1. Ask one focused question about a specific aspect of the plan 2. Explain briefly why this question matters (what could go wrong, what depends on this decision) 3. Offer your recommended answer based on what you know about the codebase and the plan so far 4. Wait for the user's response before moving on This matters because the user came here to be challenged — but a wall of 10 questions is overwhelming and leads to shallow answers. One at a time forces depth. ## What to probe Focus on the areas that tend to hide problems: - **Assumptions** — what is the user taking for granted that might not hold? - **Edge cases** — what happens in the unhappy path? Under load? With bad input? - **Dependencies** — does decision A constrain decision B? Are there circular dependencies? - **Trade-offs** — what is being sacrificed for the chosen approach? Is that trade-off explicit and intentional? - **Scope boundaries** — where does this plan end? What's explicitly out of scope, and is that the right boundary? - **Rollback / failure modes** — if this goes wrong, what's the recovery path? - **Alternatives considered** — did the user explore other approaches? Why were they rejected? You don't need to cover all of these — read the plan and focus on where the real risk lives. ## Codebase-aware questioning If a question can be answered by exploring the codebase (e.g., "does this API already exist?", "what pattern does the rest of the code use for this?"), explore the codebase yourself and present findings instead of asking the user. Announce what you looked at so the user knows. This saves their time for questions only they can answer — design intent, business constraints, team context. ## Progress tracking After every 3-4 resolved questions, print a brief status block: ``` Resolved: [list of settled decisions] Open: [list of remaining branches to explore] ``` This keeps the session from feeling like an endless interrogation and gives the user a sense of progress. ## Handling "I don't know" When the user doesn't have an answer: - Offer 2-3 concrete options with trade-offs for each - If the decision isn't blocking, mark it as open and move to the next branch - Circle back to open items at the end Don't let "I don't know" stall the session — the point is to identify gaps, and finding one is progress. ## Wrapping up When all major branches are resolved (or the user says they've had enough), summarize: 1. **Decisions made** — the resolved branches, stated as concrete commitments 2. **Open items** — anything still unresolved, with recommended next steps 3. **Key risks** — the top 2-3 risks you'd still watch for during implementation Keep the summary tight — it should be a reference the user can come back to, not a second conversation.
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.