メニュー
Use when developing the frontend and backend together, making UI changes, or setting up local dev with linked inspect_ai/scout libraries. Triggers on frontend changes, "yarn dev", "vite", "www/", or React component work.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | fullstack-dev |
| description | Use when developing the frontend and backend together, making UI changes, or setting up local dev with linked inspect_ai/scout libraries. Triggers on frontend changes, "yarn dev", "vite", "www/", or React component work. |
We have a frontend React app in www/. It is pretty lightweight for the moment. It has some views to list eval sets, scans, and samples, from the data warehouse DB.
It embeds the inspect_ai and inspect_scout frontend components.
If you want to make changes to inspect_ai and inspect_scout, you can link them to this project.
Inspect_ai uses yarn and inspect_scout uses pnpm.
It's perfectly okay to make changes to inspect_ai and inspect_scout. We can contribute changes upstream.
You should have an env file that corresponds to the environment you're using.
E.g.
set -a ; source env/dev3; set +a ; uv run fastapi dev hawk/api/server.py --port 8080
Requires Node.js ≥22.12.0 (CI uses 22.21.1). Check with node --version. Use nvm to install if needed:
nvm install 22
nvm use 22
cd www
# optional
yarn link "@meridianlabs/log-viewer"
yarn dev
cd ~/dev/inspect_ai/src/inspect_ai/_view/www
yarn link -g
yarn dev:lib
Scout is a little trickier because it uses pnpm not yarn.
Debug stuck Hawk/Inspect AI evaluations. Use when user mentions "stuck eval", "eval not progressing", "eval hanging", "samples not completing", "eval set frozen", "runner stuck", "500 errors in eval", "retry loop", "eval timeout", or asks why an evaluation isn't finishing.
Use when creating alembic migrations, applying migrations to remote environments, or recovering from schema drift. Triggers on changes to models.py, "run migration", "schema drift", "alembic", "database error in batch jobs".
Use when deploying code changes to dev environments (dev1-4), running terraform apply against dev, or verifying changes end-to-end. Triggers on "deploy to dev", "apply to dev2", "test in dev", "update dev environment".
Use when running smoke tests, debugging smoke test failures, or verifying a deployed environment works correctly. Triggers on "run smoke tests", "smoke tests failing", "test against dev", "verify deployment".
Monitor Hawk job status, view logs, and diagnose issues. Use when the user wants to check job progress, view error logs, debug a failing job, or generate a monitoring report for a Hawk evaluation run.
View and analyze Hawk evaluation results. Use when the user wants to see eval-set results, check evaluation status, list samples, view transcripts, or analyze agent behavior from a completed evaluation run.