Agent skills for Gemini CLI

When to activate: configuration management, pydantic-settings, env files, feature flags, environment-specific settings

Python data processing pipelines with modular architecture.

SQLAlchemy and database patterns for Python.

When to activate: dataclasses, attrs, msgspec, frozen dataclasses, slots, inheritance, value objects

Modern Python development workflow where ALL Python execution goes through uv run — never call python, pip, or pytest directly.

Set up a Python virtual environment and install Reflex.

When to activate: event-driven architecture, domain events, event sourcing, Kafka, RabbitMQ, NATS

Guidance for structuring a Python/FastAPI backend into layers (routers/services/repositories) and feature-first modules so it stays easy…

When to activate: Strawberry, Graphene, GraphQL, subscriptions, dataloaders, N+1, schema-first design

Python patterns for system reliability — background jobs and task queues (Celery, async), resilience and recovery (retries, backoff…

When to activate: Python logging, structlog, JSON logs, correlation IDs, log levels, observability setup

When to activate: scikit-learn, machine learning pipelines, feature engineering, model evaluation, cross-validation

Complete Python Cloudflare deployment system.

Facilitates the creation of high-performance Python bindings for Rust cores using PyO3 and idiomatic wrapper patterns.

When to activate: Python security review, OWASP, SQL injection, secrets management, authentication, cryptography

Use this when authoring integration tests against a real backend (PostgreSQL, Redis, Kafka, MinIO, NATS, MongoDB), debugging slow or flaky…

Use pytest as the testing framework for its powerful features and clean syntax. pytest automatically discovers tests following these…

AI/ML Python code tutor that provides actionable hints for writing pythonic, high-performance, modern code.

Architects distributable Python desktop tools and web-ready applications using a lightweight five-layer structure with FastAPI, pywebview…

Force Python versions via uv for cloud compatibility.

Fully sharded data-parallel training for large models.