coodie

Multi-agent code review for Python projects. Use when reviewing local uncommitted changes, pull request diffs, or when asked to do a code review. Dispatches specialist agents (bug-hunter, security-auditor, test-coverage, code-quality, contracts, historical context) and aggregates results with confidence scoring.

Configures Python projects with modern tooling (uv, ruff, ty). Use when creating projects, writing standalone scripts, or migrating from pip/Poetry/mypy/black.

Guides the design and structuring of workflow-based Claude Code skills with multi-step phases, decision trees, subagent delegation, and progressive disclosure. Use when creating skills that involve sequential pipelines, routing patterns, safety gates, task tracking, phased execution, or any multi-step workflow. Also applies when reviewing or refactoring existing workflow skills for quality.

Guides refactoring of Python test suites to reduce duplication using pytest.mark.parametrize, split large monolithic test files into focused modules, and deduplicate mirrored sync/async test classes. Use when test files exceed 400 lines, when multiple test functions share identical structure with different inputs, or when sync and async test classes are copy-pasted mirrors of each other.

Guides the creation and structuring of project plans in docs/plans/. Use when writing feature-parity plans, gap analyses, documentation plans, or implementation roadmaps. Covers plan templates, status tracking conventions, phase numbering, task tables, and test plan sections.

Guide for running and writing coodie vs cqlengine performance benchmarks. Use when asked to run benchmarks, add new benchmarks, investigate performance, or debug benchmark failures.