python▌

Static type checking with annotations, generics, protocols, and strict mode enforcement. \n \n Covers type annotations, generics with TypeVars, structural protocols, and type narrowing patterns for catching errors at analysis time \n Includes modern syntax (Python 3.10+ union types), bounded type variables, and generic repository patterns for type-safe APIs \n Provides configuration guidance for mypy strict mode and incremental adoption strategies for existing codebases \n Demonstrates 10 fundam

Modern Python project setup with uv, ruff, and ty for Python 3.11+. \n \n Replaces pip, Poetry, black, flake8, mypy, and pre-commit with faster, simpler alternatives from the Astral team \n Covers new project creation, dependency management via uv add / uv remove , and linting/formatting/type-checking workflows \n Includes migration paths from legacy tooling (requirements.txt, setup.py, flake8+black+isort, mypy/pyright) \n Provides decision tree for single-file scripts (PEP 723), simple projects

Python SDK for building AI applications, agents, and integrations with 150+ inference.sh models. \n \n Supports sync and async execution with streaming progress updates, fire-and-forget task submission, and stateful sessions for warm worker continuity \n Agent SDK includes template agents, ad-hoc agent creation with custom tools, and built-in capabilities like web search, code execution, and image generation \n Tool builder API enables four tool types: client tools (run in your code), app tools

Python SDK setup and CRUD snippets for Microsoft Dataverse operations. \n \n Generates installation commands and DataverseClient initialization with InteractiveBrowserCredential authentication \n Includes single-record CRUD patterns (create, retrieve, update, delete) following official SDK conventions \n Covers bulk operations with both broadcast and 1:1 update modes for efficient batch processing \n Demonstrates retrieve-multiple queries with paging support (top, page_size parameters) \n Option

Complete Python MCP server project generator with tools, resources, and proper configuration. \n \n Scaffolds a new Python project using uv with MCP SDK, proper directory structure, and .gitignore \n Supports both stdio (local) and streamable-http (remote) transport types with optional host, port, and stateless mode configuration \n Generates decorated tools, resources, and prompts with automatic schema generation from type hints and docstrings \n Includes comprehensive error handling, async/awa

Type-safe, async-first Python 3.11+ code generation with strict validation and comprehensive testing. \n \n Generates fully type-annotated code with mypy strict mode validation, dataclasses, and modern Python patterns (3.10+ union syntax, async/await) \n Includes pytest test suite generation with fixtures, parametrization, and mocking; enforces >90% code coverage \n Validates output with black formatting and ruff linting; provides structured error handling and logging configuration \n Covers asy

Common Python anti-patterns to catch during code review and debugging. \n \n Covers 14+ anti-patterns across infrastructure, architecture, error handling, resources, type safety, and testing with before/after code examples \n Includes a quick review checklist and summary table for fast reference during code reviews \n Focuses on practical fixes: centralized retry logic, DTOs, repository pattern, specific exception handling, and async-native libraries \n Emphasizes validation at API boundaries, c

Pythonic idioms, PEP 8 standards, type hints, and best practices for building robust Python applications. \n \n Covers core principles including readability, explicit code, EAFP exception handling, and modern type hints with generics and protocols \n Includes practical patterns for error handling, context managers, comprehensions, generators, dataclasses, and decorators with runnable examples \n Addresses concurrency patterns for I/O-bound (threading, async/await) and CPU-bound (multiprocessing)

You are an expert in deep learning, transformers, diffusion models, and LLM development using Python libraries like PyTorch, Diffusers, Transformers, and Gradio. Follow these guidelines when writing deep learning code.

Generate complete, production-ready solutions for Dataverse SDK use cases with architecture guidance. \n \n Analyzes requirements across data volume, frequency, performance, and error tolerance to recommend appropriate patterns (transactional, batch, query, file management, scheduled, or real-time) \n Provides full Python implementation including authentication, singleton service classes, CRUD operations, bulk processing, and comprehensive error handling \n Includes data model design with table