maou

Validate Clean Architecture compliance including dependency flow verification (infra → interface → app → domain), module organization analysis, layer separation checks, and circular dependency detection. Use when reviewing code structure, analyzing imports, ensuring architectural principles, or validating refactoring changes.

Execute performance benchmarks for DataLoader configurations, training performance analysis, GPU utilization monitoring, and optimization validation. Use when analyzing performance bottlenecks, finding optimal training settings, validating speed improvements, or testing array bundling efficiency.

Validate that benchmark-training command stays in sync with learn-model command. Checks for missing CLI options, verifies test exclusion list accuracy, and identifies options that need to be added to benchmark-training when learn-model features are added. Use after adding new options to learn-model, before creating PRs that modify CLI commands, or when reviewing benchmark-training compatibility.

Execute cloud provider integration tests for Google Cloud Platform (GCP) and Amazon Web Services (AWS), validate S3 and GCS operations, test cloud storage authentication, verify bucket access, and debug cloud integration issues. Use when testing cloud storage features, validating parallel upload/download operations, or troubleshooting cloud connectivity.

Validate data pipeline configuration including array_type parameter verification, HCPE and preprocessing data format validation, storage configuration checks, and schema compliance verification. Use when configuring data sources, validating pipeline setup, debugging data loading issues, or ensuring data type consistency.

Manage Python dependencies using uv exclusively, add new packages, update existing dependencies, remove unused packages, and validate dependency compatibility. Use when adding packages, updating dependencies, resolving conflicts, or managing development dependencies. NEVER use pip directly.

Automate feature branch creation following project conventions, verify branch naming patterns, check base branch state, run initial QA validation, and prepare development environment. Use when starting new features, creating bug fix branches, or setting up development branches.

Create comprehensive GitHub pull requests using gh command with intelligently generated PR descriptions. Analyzes commit history, code changes, and project context to generate detailed PR bodies that include problem statement, solution approach, impact analysis, testing strategy, and reviewer guidance. Use when creating pull requests that require thorough documentation for effective code review.

Capture screenshots of Gradio web UI using Playwright headless browser for visual feedback and verification. Use when testing UI rendering, debugging visual issues, or verifying component appearance.

Validate Japanese documentation punctuation rules including full-width comma and period usage (，．), half-width parenthesis validation, and format compliance checking. Use when writing Japanese docstrings, validating Japanese comments, or ensuring Japanese text formatting standards.

Perform comprehensive pre-PR validation including code quality checks, test execution, architecture compliance verification, commit message formatting validation, and branch status confirmation. Use when preparing pull requests, validating branches before submission, or ensuring all PR requirements are met.

Execute complete QA pipeline including code formatting with ruff, linting, import sorting with isort, type checking with mypy, and testing with pytest. Use when preparing code for commits, running pre-commit checks, ensuring code quality standards, or validating changes before pushing.

Build Rust extensions efficiently in memory-constrained environments (2-4GB RAM), using optimized build profiles, split workspace compilation, and memory monitoring. Use when encountering OOM errors during Rust builds, setting up Rust backend in DevContainer/Colab, troubleshooting maturin failures, or optimizing compilation for low-memory systems.

Enforce type safety requirements by running mypy type checker, detecting missing type hints, verifying docstring presence on public APIs, and identifying type annotation gaps. Use when validating type coverage, ensuring type safety compliance, checking documentation completeness, or preparing code for strict type checking.

maou visualize の可視化機能をスクリーンショットで網羅的にチェックする．Gradio サーバーを起動し，各画面状態のスクリーンショットを撮影・目視確認する．