discuss-mcp
Advisory skill for reflecting on and improving an MCP server — trace analysis, chained tool design, and behavioral coverage review.
What this skill does
# Discuss MCP Advisory skill for reflecting on and improving an MCP server. Unlike builder skills (`/build-tools`, `/build-evals`) that execute generation workflows, this skill is **conversational** — it helps developers understand what to improve, why, and how. ## When to Use Use this skill when the developer asks: - "How can I improve my MCP server?" - "Why are my evals slow/expensive/failing?" - "Should I add composite tools or proxy tools?" - "What tools am I missing?" - "What should I build next?" - "Are my tools well-designed?" - "How do I reduce eval cost/turns?" ## Improvement Paths Route to the appropriate sub-file based on what the developer wants to discuss: ### 1. Trace Optimization — "My evals are slow/expensive/failing" The developer wants to analyze eval performance and iteratively improve tools based on trace data. **Read**: [trace-optimization.md](trace-optimization.md) **Signals**: mentions evals, traces, cost, turns, tokens, performance, "why does the LLM struggle", repeated tool calls, wrong tool selection. ### 2. Chained Tool Design — "Should I add composite/proxy tools?" The developer wants to discuss adding tools that delegate to other MCP servers — whether to proxy or create composites. **Read**: [chained-tools.md](chained-tools.md) **Signals**: mentions chaining, proxy, composite, multi-server, delegation, orchestration, combining data from multiple sources. ### 3. Behavioral Analysis — "What should I build next?" The developer wants a holistic review of their MCP: coverage gaps, organizational quality, prioritization of next steps. **Read**: [behavioral-analysis.md](behavioral-analysis.md) **Signals**: mentions coverage, gaps, what's missing, next steps, priorities, tool organization, modes, slices, "are my tools well-designed". ## Conversational Guidelines When advising on MCP improvements, follow these principles: 1. **Ask before recommending.** Understand the developer's goals before suggesting changes. "What workflows are you trying to support?" is more useful than jumping to solutions. 2. **Propose with trade-offs, not prescriptions.** Present options with pros and cons. "You could simplify the response schema (reduces tokens but loses detail) or add a composite tool (preserves detail but adds complexity)." 3. **Use their own codebase as evidence.** Reference specific tool files, descriptions, eval results, and collection structures. Abstract advice is less useful than "your `get-document-by-id` description says X but the eval trace shows the LLM tried Y first." 4. **Enter plan mode for concrete changes.** When a specific improvement is identified and the developer agrees, **enter plan mode** to design the change before executing. This ensures the developer approves the approach. 5. **Summarize action items.** After each discussion thread, list what was agreed: changes to make, things to investigate, next steps. Keep it concrete. 6. **Iterate, don't overhaul.** Prefer small, measurable improvements over large rewrites. One description fix that drops turns from 5 to 3 is more valuable than a speculative restructuring. 7. **Respect ignored endpoints.** Read `docs/analysis/IGNORED_ENDPOINTS.md` before suggesting new tools. Endpoints listed there are deliberately excluded — do not recommend implementing them. They represent settled decisions about scope. ## Multiple Topics If the developer's question spans multiple paths (e.g., "my evals are slow and I think I need composite tools"), read both sub-files and synthesize. Start with the most pressing concern — usually trace optimization reveals whether chaining is actually needed.
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.