This is the skill to reach for when you're building AI agents that need to reason, use tools, and execute multi-step tasks. It defaults to Pydantic AI for Python projects and Claude's Agent SDK for Node.js, both chosen for type safety and production readiness. The core workflow is explore-plan-execute-verify, which means your agent gathers context, explicitly plans steps before acting, then verifies each result before moving forward. The project structure separates agents, tools, and prompts cleanly, and the planning phase is treated as non-negotiable. Agents that plan before they act consistently outperform ones that jump straight to execution.
npx skills add https://github.com/alinaqi/claude-bootstrap --skill agentic-development