Write agent output for the accountable human reviewer — route narrative by audience and lifespan, lead with a budgeted summary, keep detail collapsed, and plan before building. Use when writing PR or issue descriptions, commit messages, or code comments, when addressing or resolving PR review comments, when deciding whether to raise an issue or where work-narrative belongs, or when scoping a non-trivial change before generating code.
Write asyncio Python to this project's standards — concurrent coroutines, async-all-the-way, and safe handling of errors from concurrent tasks. Use when writing async/await code, gathering coroutines, designing async FastAPI endpoints or clients, or handling failures from concurrent work.
Write Python source to this project's standards. Use when authoring or refactoring Python code and deciding on style, type hints, docstrings, comments, imports, or language idioms.
Work with dates, times, and timezones to this project's standards. Use when creating, parsing, serialising, comparing, or storing datetimes, or handling timezones.
Handle errors in Python to this project's standards — custom domain exceptions, narrow catches, and failing fast. Use when raising or catching exceptions, writing try/except, designing an exceptions module, or deciding whether to swallow or propagate an error.
Reach for this project's preferred, well-supported libraries instead of hand-rolling. Use when choosing a library for HTTP, retries, JSON, or parsing, or whenever you are about to write something the standard library or a maintained package already does.
Lint and format a Python project with the prek hook runner. Use when checking or cleaning the working tree, resolving lint/format/type/complexity/spelling failures, or understanding what each linter config enforces.
Write Pandas code to this project's standards — vectorised operations, Pandas-native types, and Pandera schemas. Use when importing or using pandas — transforming DataFrames or Series, handling missing values, or type-hinting tabular data.