Run smoke tests on a deployed environment to ensure basic functionality.
npx skills add https://github.com/METR/hawk --skill smoke-testsこのコマンドをClaude Codeにコピー＆ペーストしてスキルをインストール
Use when an SQS dead-letter queue has accumulated messages and you need to investigate, redrive, or drain them — e.g. a DLQ-depth CloudWatch alarm fires, the importer is failing, or you're cleaning up after a known bug fix has shipped.
How to develop the frontend and backend together. When you want to make changes to the UI, use this.
How to create and use our alembic database migration tool. Use when making changes to models.py.
| name | smoke-tests |
| description | Run smoke tests on a deployed environment to ensure basic functionality. |
Run hawk login first if not logged in. Full docs in hawk/tests/smoke/README.md.
scripts/dev/smoke # current Pulumi stack, includes warehouse
scripts/dev/smoke --stack staging # target a specific stack
scripts/dev/smoke -k test_real_llm # pass args through to pytest
scripts/dev/smoke --skip-warehouse # exclude warehouse checks