todo-evaluation

This skill implements AI agents with MCP (Model Context Protocol) server integration using the OpenAI Agents SDK. It covers agent creation, tool definitions, MCP server connections (stdio, HTTP, SSE), tool filtering, caching, handoffs, guardrails, and multi-agent orchestration patterns. Use when building AI agents that connect to MCP servers, implementing tool-mediated AI interactions, or creating production-grade agentic systems.

Configure Better Auth on the frontend and coordinate JWT issuance. This skill should be used when setting up Better Auth in Next.js frontend, configuring authentication providers, handling user sessions, and coordinating token issuance for backend API authentication.

This skill configures OpenAI ChatKit for React frontends with proper domain security, authentication, and backend integration. It covers ChatKit UI setup, domain allowlist configuration, domain key injection, client secret management, and production vs localhost deployment patterns. Use when integrating ChatKit widget, configuring domain security, or connecting ChatKit UI to backend endpoints.

This skill normalizes errors and produces human-friendly confirmations across API and UI layers. It prevents silent failures, ensures graceful degradation, and maintains consistent UX quality. Use when implementing error responses, success confirmations, "not found" handling, or improving agent response quality.

This skill designs FastAPI application structure, routing, middleware, and separation of concerns. It establishes architectural patterns for building scalable, maintainable Python APIs that integrate with the monorepo structure and support authentication and data persistence requirements. Use when designing overall FastAPI application structure, planning API routing, or establishing middleware chains.

This skill structures frontend code for scalability, readability, and API interaction. It establishes patterns for organizing frontend code beyond routing, including component organization, state management, and integration with backend APIs. Use when designing overall frontend code organization, planning component library structure, or establishing state management patterns.

Define authentication flow using JWT between frontend and backend. This skill should be used when designing the overall authentication architecture, planning token flow between frontend and backend, establishing token format and claims structure, and defining authentication state machine.

Verify JWT tokens in backend services and enforce authenticated user context. This skill should be used when implementing JWT token validation in FastAPI, extracting user identity from JWT claims, designing authenticated endpoint middleware, establishing user context for request processing, handling token expiration and refresh scenarios, and debugging authentication failures.

This skill registers, validates, and executes MCP (Model Context Protocol) tools deterministically, enforcing tool-mediated AI interactions. Use when implementing MCP server integrations, tool invocation lifecycles, or ensuring AI agents interact with external systems through proper tool mediation.

Design and reason about full-stack monorepo layouts compatible with Spec-Kit Plus and Claude Code. This skill should be used when designing the initial monorepo structure for a full-stack application, planning directory organization for frontend and backend separation, establishing shared configuration and tooling patterns, defining workspace boundaries for package managers, creating architectural plans that span multiple application layers, and ensuring Spec-Kit Plus artifacts integrate correctly across the monorepo.

Integrate Neon Serverless PostgreSQL using environment-based configuration. This skill should be used when setting up Neon PostgreSQL connection, configuring database connection strings, handling environment-based database configuration, managing connection pooling for serverless, troubleshooting database connectivity issues, and planning database migrations with Neon.

Design Next.js App Router structure with server/client components. This skill should be used when designing Next.js application structure, planning route organization with App Router, deciding server vs client component boundaries, implementing layouts and nested routing, planning data fetching patterns, and optimizing for server-side rendering.

Organize backend Python code cleanly for FastAPI projects. This skill should be used when setting up initial backend directory structure, organizing code into logical modules, defining layer separation (routers, services, models), establishing import patterns and dependency flow, creating new backend features or domains, and reviewing code organization for consistency.

Define RESTful API behavior, HTTP methods, status codes, and endpoint conventions. This skill should be used when designing new API endpoints, establishing HTTP method conventions (GET, POST, PUT, DELETE), defining response status codes and error formats, creating API contract documentation, reviewing existing endpoints for REST compliance, and planning resource naming and URL structure.

This skill designs SQLModel schemas aligned with PostgreSQL and FastAPI. It establishes patterns for defining database models that leverage SQLModel's dual nature as both SQLAlchemy ORM models and Pydantic validation schemas. Use when designing database table schemas, defining model relationships, or creating request/response models for API endpoints.

This skill implements task persistence with user scoping, supporting add, list, update, complete, and delete operations. It enforces business logic correctness and handles missing tasks safely. Use when implementing task management systems with proper user isolation and data integrity.

Design agent system prompts with explicit behavior rules and cognitive control. This skill should be used when users need to define agent instructions, create intent-to-tool mappings, establish confirmation policies, or prevent hallucinated actions in AI agents.

Implement single-endpoint chat API with deterministic request orchestration. This skill should be used when users need to create /api/{user_id}/chat endpoint, implement request validation, resolve conversation IDs, call agent runners, or design chat API contracts with structured responses.

Implement DB-persisted conversation state for stateless AI agent servers. This skill should be used when users need to create/load conversations, append messages with role ordering, fetch history for agents, or resume conversations after server restart.