challenge-that
Force critical evaluation of proposals, requirements, or decisions by analyzing from multiple adversarial perspectives. Triggers on: accepting a proposal without pushback, 'sounds good', 'let's go with', design decisions with unstated tradeoffs, unchallenged assumptions, premature consensus. Invoke with /challenge-that.
What this skill does
# Challenge That Force critical evaluation by analyzing from multiple adversarial perspectives. ## When to Use Invoke `/challenge-that` when: - Claude accepted a proposal without critical evaluation - You want to stress-test a decision before committing - Requirements feel under-examined - Something seems off but you can't articulate why ## The Five Hats Each perspective challenges from a different angle: | Hat | Focus | Key Questions | |-----|-------|---------------| | 🔴 **Skeptic** | Evidence & proof | "What evidence supports this? Has this been validated? Are we guessing?" | | 🟡 **Pragmatist** | Cost/benefit | "Is this the simplest fix? What's the maintenance burden? Is it worth it?" | | 🟢 **Edge Case Hunter** | Failure modes | "What breaks this? What's the worst case? What did we miss?" | | 🔵 **Structural Critic** | Architecture | "Is this the right location? Does it fit the existing design? Will it cause problems elsewhere?" | | 🟣 **Root Cause Analyst** | Problem diagnosis | "Is the problem correctly identified? Are we treating symptoms? What's the actual cause?" | ## Behavior When `/challenge-that` is invoked: 1. Identify what was just accepted/proposed 2. State it clearly: "Challenging: [the proposal/decision]" 3. Analyze from each of the five perspectives 4. Synthesize into actionable concerns 5. Ask: "Which concerns should we address before proceeding?" ## Output Format ``` ## Challenging: [proposal/decision being challenged] ### 🔴 Skeptic [Challenge from evidence/proof perspective] ### 🟡 Pragmatist [Challenge from cost/benefit perspective] ### 🟢 Edge Case Hunter [Challenge from failure modes perspective] ### 🔵 Structural Critic [Challenge from architecture perspective] ### 🟣 Root Cause Analyst [Challenge from problem diagnosis perspective] --- **Key Concerns:** 1. [Most significant concern] 2. [Second concern] 3. [Third concern] Which of these should we address before proceeding? ``` ## Critical Rules 🚨 **Be genuinely adversarial.** Don't softball the challenges. If a perspective finds nothing wrong, say so—but look hard first. 🚨 **Challenge the proposal, not the person.** Focus on the idea's weaknesses, not who suggested it. 🚨 **Provide actionable output.** Each challenge should point to something that could be investigated or changed. ## Example **User:** `/challenge-that` **Context:** Claude just accepted a proposal to add edge case validation to TDD's GREEN state. **Output:** ## Challenging: Add edge case validation checklist to TDD GREEN state ### 🔴 Skeptic What evidence shows that GREEN state is the right location? The proposal assumes this will catch bugs, but has anyone tested whether developers actually use checklists at this stage? GREEN means "tests pass"—adding a review step here changes what GREEN means. ### 🟡 Pragmatist This adds friction to every TDD cycle. Is the bug frequency high enough to justify the overhead? The PR mentioned 3 bugs in one PR—is that representative or an outlier? What's the cost of false negatives (checklist fatigue)? ### 🟢 Edge Case Hunter What happens when the checklist reveals missing tests? There's no GREEN → PLANNING transition. The developer would need to either ignore the finding or break the state machine. This creates a dead end. ### 🔵 Structural Critic GREEN state is about code quality assessment, not test coverage. Test writing happens in PLANNING. This checklist belongs in PLANNING state where tests are actually written—not after they've already passed. ### 🟣 Root Cause Analyst The actual problem was insufficient edge case consideration during test writing. The proposal treats the symptom (bugs shipped) not the cause (incomplete test planning). Moving this to PLANNING would address the root cause. --- **Key Concerns:** 1. GREEN is structurally the wrong location—no recovery path exists 2. Root cause is in PLANNING, not GREEN 3. No evidence this will be used effectively at GREEN stage Which of these should we address before proceeding?
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.