From compound-engineering-feat-python
Django core patterns for models, views, admin, signals, middleware, and Django Ninja APIs. Use when working on projects with django in their dependencies.
npx claudepluginhub weorbitant/compound-engineering-feat-python-plugin --plugin compound-engineering-feat-pythonThis skill uses the workspace's default tool permissions.
Patterns and conventions for building Django applications. Follow the philosophy of fat
Searches, retrieves, and installs Agent Skills from prompts.chat registry using MCP tools like search_skills and get_skill. Activates for finding skills, browsing catalogs, or extending Claude.
Searches prompts.chat for AI prompt templates by keyword or category, retrieves by ID with variable handling, and improves prompts via AI. Use for discovering or enhancing prompts.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Patterns and conventions for building Django applications. Follow the philosophy of fat models and thin views, prefer explicit over implicit, and adhere to Django conventions for project structure and naming.
Apply these patterns when working on any project that lists django in its dependencies.
Detect this by checking pyproject.toml, requirements.txt, or Pipfile for Django.
Always run Django apps locally without Docker:
ENVIRONMENT=local poetry run python src/manage.py runserver 0.0.0.0:8000
Use | None instead of Optional for all type annotations:
def get_user(user_id: int) -> User | None:
...
Use emojis as prefixes in log messages:
logger.info("✅ Order %s created successfully", order.id)
logger.warning("⚠️ Payment retry #%d for order %s", attempt, order.id)
logger.error("❌ Failed to process webhook: %s", exc)