193 skills · sorted by relevance
Auto-activate for pytest_databases, Docker DB fixtures, PostgreSQL/pgvector/ParadeDB, MySQL/MariaDB, Oracle/SQL Server, CockroachDB, MongoDB, Redis/Valkey, BigQuery/Spanner, MinIO, or RustFS. Not for mocked DBs.
The English summary is being prepared. Showing the original description.
テスト実行時の絞り込み運用ルール。プロジェクト全体テストではなく修正範囲に絞ったテスト実行を行う。`gradlew test`/`pytest`/`jest`/`go test`等のテストランナーを実行するとき、テスト実行コマンドを組み立てるときに必ず参照する。コミット差分や修正ファイルから対象テストを特定する手順を含む。
The English summary is being prepared. Showing the original description.
Generate Python/pytest unit test skeletons from specifications.
The English summary is being prepared. Showing the original description.
pytest、フィクスチャ、モッキング、テスト駆動開発を使用した包括的なテスト戦略を実装。Pythonテストの記述、テストスイートのセットアップ、テストベストプラクティスの実装時に使用。
The English summary is being prepared. Showing the original description.
pytest、TDD方法論、フィクスチャ、モック、パラメタライズ、カバレッジ要件を使用したPythonテスト戦略。
The English summary is being prepared. Showing the original description.
pytest-djangoによるDjangoテスト戦略、TDD方法論、factory_boy、モック、カバレッジ、Django REST Framework APIのテスト。
The English summary is being prepared. Showing the original description.
Run pytest tests with coverage, discover lines missing coverage, and increase coverage to 100%.
The English summary is being prepared. Showing the original description.
Build end-to-end tests that operate Windows desktop apps through pywinauto and Windows UI Automation, an interface for accessing screen controls. Covers stable element selection, waits, failure screenshots, test isolation, and CI setup for native applications.
Diagnose REST and GraphQL API failures by checking connectivity, authentication, request formats, and returned data. Prepare reproducible commands, identify likely causes, and build regression tests that check whether a fix keeps working.
Guide development through test-driven development (TDD): write a test, confirm it fails, add minimal code, then clean up. Apply this cycle to features and bug fixes while checking that existing behavior still passes its tests.
Investigate Python bugs by pausing execution, inspecting variables, and stepping through code. Choose pdb for local inspection or debugpy for remote connections, with guidance for failing tests, crash analysis, and already running processes.
Create or revise skills shipped within the Hermes Agent repository. The guidance covers file placement, required metadata, clear procedures, platform checks, tests, and documentation updates so contributions follow the repository’s authoring standards.
Turn specifications and designs into working code using test-driven development: write failing tests, implement enough code to pass, then refactor. The workflow also covers error handling, performance improvements, documentation, and coordinated changes across components.
Set up a realtime evaluation folder with a suitable shared harness, the framework that runs evaluations. Prepare prompts, tool definitions, realistic starter data, and a README, then validate the setup with evaluation and test runs.
Build repeatable evaluations for AI agent responses, tool choices, and multi-step tasks. Use reference datasets and scoring criteria to compare changes, detect quality regressions, and set automated checks that must pass before deployment.
Update Flask-AppBuilder in Apache Airflow’s FAB provider, including pinned versions, dependency locks, and documentation. Check compatibility tests and review copied security code, with asset and database migration updates when the upstream release requires them.
Set up Python projects with uv, manage required packages, and create isolated environments for each project. Covers Python versions, dependency updates, migration from existing tools, and lockfiles that record package versions for repeatable installations.
Set up Python APIs with FastAPI using organized project templates. Build routes, asynchronous database operations, authentication, and error handling, with examples for sharing dependencies and testing endpoints through a separate test database.
Design workflows that evaluate and refine AI outputs through self-review, separate generation and evaluation roles, tests, or weighted scoring criteria. Includes patterns for structured feedback, iteration limits, and stopping when quality stops improving.
Plan features before coding by defining requirements, acceptance criteria, and scope. Validate the specification, generate starter tests from expected behaviors, and guide implementation and review so each delivered feature can be checked against its agreed requirements.
Add DeepEval tracing to Python AI applications so execution steps appear in Confident AI. Choose a supported integration or manual @observe instrumentation, then capture inputs, outputs, step types, tags, and metadata.
Configure OpenTelemetry to send AI application traces, records of execution steps, to Confident AI. Reuse existing exporters, choose the regional endpoint, and add AI-specific attributes without requiring the deepeval Python package.
Merge GitHub pull requests while preserving credit for the original contributors. Covers straightforward merges, conflict resolution, selective file inclusion, duplicate PR closure, and checks that confirm both attribution and working code after integration.
Build Python APIs with FastAPI and Pydantic V2, including input validation, database operations that avoid blocking other work, and token-based authentication. Implement REST or WebSocket endpoints, then check their behavior with automated tests and generated API documentation.