claude-toolkit

This skill should be used when the user asks to "evaluate agents", "test agent", "create eval dataset", "design evals", "benchmark agent", "debug agent", "run evals", or needs guidance on testing, evaluating, and iterating on deep agent systems using an evals-driven approach.

This skill should be used when the user asks about "agent prompts", "system prompt design", "tool patterns", "anti-patterns", "agent best practices", "subagent prompts", or needs guidance on implementing effective prompts, tools, and avoiding common mistakes in DeepAgents.

This skill should be used when the user asks to "start a deepagent project", "create a new agent", "quickstart agent", "simple agent example", "get started with deepagents", or needs a quick introduction to building agents with LangChain's DeepAgents framework. Provides minimal setup and basic patterns for rapid prototyping.

This skill should be used when the user asks to "design tools", "create tools for agent", "tool design", "API to tools", "define tools", "convert API to tools", or needs guidance on designing AI-friendly tools for agents — LangChain `@tool` functions, MCP tool definitions, or DeepAgents tool catalogs. Provides principles from AI-Friendly API Design, Agent Native architecture, and real-world tool catalogs.

Use when writing AWS CDK code in TypeScript — starting a new CDK project, building serverless APIs with Lambda and DynamoDB, adding authentication with Cognito, hosting a single-page app on S3 and CloudFront, designing DynamoDB access patterns, writing Lambda handlers, or running CDK deploys.

Build, ship, and maintain Expo / React Native mobile apps. Covers project scaffold (feature-folder DDD, expo-router, EAS profiles), navigation + deep links, client and server state (Zustand + TanStack Query) with offline sync, Cognito + Google federation via expo-auth-session, push notifications, OTA updates, EAS Build / Submit, web / PWA target, performance (Hermes, FlashList, reanimated), testing (Jest + RNTL + Maestro), i18n + accessibility, observability (Sentry + analytics), in-app purchases and subscriptions with RevenueCat. TypeScript examples, gotchas catalog.

Design DynamoDB schemas from access patterns. Covers key design, GSIs, hot-partition mitigation, atomic write patterns (optimistic locking, counters, batch ops), DynamoDB Streams and CDC, schema evolution without downtime, and local testing. Stack-agnostic modeling with TypeScript code examples.

This skill should be used when the user asks to "design agent topology", "plan agent architecture", "create bounded contexts", "map business capabilities to agents", "organize subagents", or needs guidance on structuring multi-agent systems. Provides Team Topologies principles applied to AI agents.

This skill should be used when the user asks to "improve agent architecture", "assess agent maturity", "refactor agents", "evolve agent system", "scale agent architecture", or needs guidance on measuring, improving, and evolving deep agent systems over time.

This skill should be used when the user asks to "create a LinkedIn post", "write AI content", "generate thought leadership", "optimize my post", "improve engagement", "write viral hooks", "enterprise AI content", or mentions LinkedIn posting, AI thought leadership, or building authority on LinkedIn.