{
  "context": "Tests whether the agent, invoking the install-reviewer skill, produces the correct sequence of commands to scaffold the gh-aw PR review workflow into a consumer repository: a feature branch, the template copied to the right path, the workflow compiled, both files committed, a PR opened with secrets instructions in the body.",
  "type": "weighted_checklist",
  "checklist": [
    {
      "name": "Creates a feature branch",
      "description": "Uses `git checkout -b <branch>` (or equivalent) to create a new branch before making changes — does NOT commit directly to main/master",
      "max_score": 10
    },
    {
      "name": "Populates .github/workflows with source and lock",
      "description": "Ends with `.github/workflows/review.md` and `.github/workflows/review.lock.yml` both present in the working tree. The source declares a `pull_request` trigger and a pre-step that runs `tessl install jbaruch/coding-policy`; the lock is the compiled form of that source (produced by `gh aw compile`, which is a public gh CLI extension, not typed out by hand or fetched from a URL). Only the final observable state is graded — not the specific command sequence the agent chose to reach it",
      "max_score": 35
    },
    {
      "name": "Commits both source and lock",
      "description": "Stages and commits both `review.md` and `review.lock.yml` — not just the source or just the lock",
      "max_score": 10
    },
    {
      "name": "Pushes and opens a PR",
      "description": "Pushes the branch and creates a pull request with `gh pr create`",
      "max_score": 8
    },
    {
      "name": "PR body lists OPENAI_API_KEY",
      "description": "The PR body or the plan instructs the reviewer to set `OPENAI_API_KEY` as a repository secret before merge",
      "max_score": 10
    },
    {
      "name": "PR body lists TESSL_TOKEN",
      "description": "The PR body or the plan instructs the reviewer to set `TESSL_TOKEN` as a repository secret before merge (required so the workflow's `tessl install` pre-step can authenticate)",
      "max_score": 10
    },
    {
      "name": "Does not merge",
      "description": "Does NOT include `gh pr merge` or equivalent. The scaffolding PR is handed to the user for secret validation and merge; the skill stops at PR creation",
      "max_score": 10
    },
    {
      "name": "Does not bypass pre-commit hooks",
      "description": "Does NOT include `--no-verify` on any git commit (if a pre-commit hook fires, the correct response is to fix and re-commit, not bypass)",
      "max_score": 7
    }
  ]
}