Independently review an raytsystem run, diff, contract, test result, or milestone checkpoint and return structured findings. Use for REVIEW, architecture/contracts/data-integrity/test critique, gate verification, or pre-promotion review; remain read-only and separate from the writer context.
インストール
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。
Independently review an raytsystem run, diff, contract, test result, or milestone checkpoint and return structured findings. Use for REVIEW, architecture/contracts/data-integrity/test critique, gate verification, or pre-promotion review; remain read-only and separate from the writer context.
raytsystem Run Review
Inputs and outputs
Accept one bounded target, exact file/source references, rubric, and stop condition.
Return PASS or sorted Critical/High/Medium findings with file:line, impact, evidence, and minimal fix.
Write scope
Keep the reviewer read-only.
Never edit files, acquire writer leases, promote, create Git refs, or perform external actions.
Let the main agent resolve contradictions and own all writes.
Preflight
Run uv run raytsystem agent preflight --skill raytsystem-run-review --write --json locally.
Run agent subagent-check before sending any excerpt to a reviewer surface.
Supply only the minimal non-sensitive target; do not leak the intended answer or suspected fix.
Workflow
Inspect target contracts, implementation, tests, and declared gate evidence.
Reproduce suspected failures read-only when safe.
Rank findings by concrete impact; omit style-only commentary unless requested.
Return summaries with source references, not raw logs.
