agentic-crisis-orchestrator

Guides the professional implementation of application configuration using pydantic-settings and .env files. Use when the user needs to manage environment variables, validate config schemas, or structure settings for agents and web apps (FastAPI, etc.).

Manages Python projects using UV package manager exclusively. Use when users need to create Python projects, manage dependencies, handle virtual environments, or work with Python packages. This skill enforces UV workflows for all Python package operations including installing packages, creating projects, managing dependencies, running scripts, and building distributions. NOT when working with existing pip/poetry projects that user explicitly wants to keep unchanged.

Build production-grade FastAPI backends with SQLModel, Pydantic settings, and JWT authentication. Use when building REST APIs with PostgreSQL, implementing environment-based configuration with .env files, creating CRUD endpoints with JWT/JWKS verification, or setting up pydantic-settings for app configuration. NOT when building distributed microservices with Dapr (use scaffolding-fastapi-dapr for that).

Builds AI agents using OpenAI Agents SDK with async/await patterns and multi-agent orchestration. Use when creating tutoring agents, building agent handoffs, implementing tool-calling agents, or orchestrating multiple specialists. Covers Agent class, Runner patterns, function tools, guardrails, and streaming responses. NOT when using raw OpenAI API without SDK or other agent frameworks like LangChain.

Design tools that agents can use effectively. Use when creating new tools for agents, debugging tool-related failures, or optimizing existing tool sets.