sc-python

Python code quality auditor. Detects the project stack via sniff (01-scan), loads the applicable Python knowledge pivots from the plugin, and delegates a structured code review to aidd-dev:reviewer using the pivots as acceptance criteria. Use when the user asks to: audit Python code, check Python best practices, review code quality, check my Python, audit Django/FastAPI conventions, check Pythonic compliance, or invokes /sc-python:audit. Does not install any files to .claude/rules/.

Analyzes the Python codebase for Pythonic idiom gaps, design pattern opportunities, and maintainability issues, then produces a prioritized improvement plan. Covers EAFP/LBYL patterns, proper type hints, async best practices, dependency injection, dataclasses vs NamedTuple, mutable default arguments, context managers, and framework idioms (Django, FastAPI). Use when the user says "how can I improve this", "is this Pythonic", "find anti-patterns", "code quality", "refactoring suggestions", "how to better structure this". Do NOT use for performance (web-optimize), data layer (data-optimize), version migrations (legacy), or line-by-line code review (aidd-dev:05-review).

Scans Python code for version-specific and deprecated patterns, then proposes an upgrade (toward Python 3.12+) or a downgrade (for target Python version compatibility). Handles Python 2 remnants (print statements, xrange, unicode, iteritems), typing evolution (PEP 484 → 604 → 695, Optional → X|None, List → list), old-style string formatting (% and .format() → f-strings), and framework version migrations (Django, FastAPI). Use when the user says "modernize", "upgrade to Python 3.12", "add type hints", "this is Python 2 style", "downgrade for 3.8 compat", or when deprecated patterns appear in the codebase. Do NOT use for dependency management (pip/poetry), performance optimization (web-optimize), or general refactoring unrelated to Python version compatibility.

Analyzes Python application logs across three environments: host filesystem (local), Docker containers (docker), and remote production server (prod via SSH). Works with Django request logs, uvicorn/gunicorn access logs, Python tracebacks, structlog JSON output, and Celery task logs. Auto-discovers Docker containers. Use when the user says "check logs", "Python errors", "find in logs", "log summary", "500 errors", "traceback in prod", "analyze logs", "what's wrong in prod". Do NOT use for application debugging (use aidd-dev:08-debug), DB queries (use data-optimize), or performance profiling.

Python stack detector. Reads requirements.txt, pyproject.toml, setup.py, Pipfile, and sentinel files (manage.py) to detect the framework (Django, FastAPI, Flask), ORM (Django ORM, SQLAlchemy), and capabilities including ActivityPub federation (activitypub/ module + httpx + cryptography). Uses a three-tier model: capability pivots (Python idioms) are loaded at audit time by /sc-python:audit and never written to disk; perf pivots (for web-optimize), data pivots (for data-optimize), and AP pivots (for ap-optimize) are installed selectively to .claude/rules/07-quality/. Emits a pivot manifeste for use by /sc-python:audit. Reports gaps when a capability is detected but no matching plugin pivot exists. Do NOT use to update a single rule manually — edit it directly instead.