second-opinion
Get a second LLM opinion via codex/gemini/ollama on architectural decisions, design trade-offs, library or framework choices, and security-sensitive code. Use when uncertain on a 'should I' call, want a sanity check before a high-stakes commit, or facing a contested code review. SKIP for routine questions where one model's answer is clearly sufficient.
What this skill does
# Second Opinion Skill Proactively suggest getting another LLM's perspective when the situation warrants it. ## Trigger Conditions Suggest a second opinion when you detect: ### 1. Architectural Decisions - Choosing between design patterns (e.g., repository vs service layer) - Database schema design decisions - API design choices (REST vs GraphQL, versioning strategy) - Service decomposition (monolith vs microservices) - State management approaches ### 2. Complex Trade-offs - Performance vs. readability - Flexibility vs. simplicity - DRY vs. explicit code - Build vs. buy decisions - Consistency vs. availability trade-offs ### 3. Critical Code Reviews - Security-sensitive code (authentication, authorization, crypto) - Performance-critical paths - Complex algorithms or data structures - Code handling financial transactions or PII - Concurrency and threading logic ### 4. Explicit Requests (trigger words) - "another perspective" - "second opinion" - "sanity check" - "what do you think" - "am I on the right track" - "does this make sense" - "is this a good approach" ## How to Suggest When conditions are met, offer specific options: > This involves [type of decision]. Would you like a second opinion from another LLM? > > - `/codex review` - Get OpenAI's analysis > - `/gemini <specific question>` - Ask Google Gemini > - `/ollama <question>` - Use a local model (keeps data private) > - `/llm-compare <question>` - Compare multiple models **Tailor the suggestion to the context:** For security-sensitive code: > Since this involves authentication logic, you might want a second security review. Try `/codex review` or `/ollama` (keeps code local) for another perspective. For architectural decisions: > This is a significant architectural choice. Different models sometimes weigh trade-offs differently. Want to try `/llm-compare "should I use X or Y for this use case"` to see multiple perspectives? For complex algorithms: > This algorithm has some complexity. A second set of eyes might catch edge cases. Try `/codex explain the edge cases in this algorithm`. ## When NOT to Suggest Do not suggest second opinions when: - User is actively implementing (don't interrupt flow) - Task is simple/straightforward (typos, formatting, simple fixes) - User has already made a firm decision - User said "just do it" or similar - It's routine code changes with clear requirements - User previously declined suggestions in this session ## Privacy Consideration Always mention `/ollama` as an option when the code might be sensitive: > For proprietary code, `/ollama` keeps everything local - your code never leaves your machine. ## Example Interactions **Example 1: Architectural Decision** User: "Should I use a monorepo or multi-repo for these microservices?" Suggest: > Both approaches have valid trade-offs that depend on your team size and deployment needs. For a decision this impactful, would you like another perspective? > > - `/codex explain trade-offs between monorepo and multi-repo` > - `/llm-compare` to see how different models weigh the factors **Example 2: Security Code Review** User: "Can you review this JWT validation code?" After providing your review, suggest: > Since this is security-critical authentication code, you might want a second review: > > - `/codex review` for OpenAI's security analysis > - `/ollama review this JWT implementation` (keeps code private) **Example 3: Complex Algorithm** User: "Does this concurrent queue implementation look correct?" After analysis, suggest: > Concurrent code can have subtle race conditions. Want a second opinion? > > - `/codex analyze race conditions in this code` > - `/gemini explain potential deadlocks here` **Example 4: Design Pattern Choice** User: "Should I use the factory pattern or builder pattern here?" Suggest: > Both patterns could work here with different trade-offs. Want to see how other models approach this? > > - `/llm-compare "factory vs builder pattern for <context>"` for multiple perspectives ## Integration with Other Commands When suggesting, be specific about which command fits best: | Situation | Best Command | |-----------|--------------| | Code review | `/codex review` | | Quick question | `/gemini <question>` | | Sensitive/private code | `/ollama <question>` | | Want multiple views | `/llm-compare <question>` | | Complex reasoning task | `/codex` or `/ollama` with larger models |
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.