メニュー
Generate safe query rewrite candidates with deterministic explainability without executing SQL.
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
Designs dry-run experiments across query rewrites, indexes, workload twins, and rollout gates.
Produces a board-level briefing for closed-loop autonomous database operations.
Enforces closed-loop dry-run boundaries and blocks autonomous production apply.
Scores whether enough evidence exists to recommend, defer, or escalate an autonomous operator decision.
Compares do-nothing, dry-run-change, rollback, and defer scenarios for an operating objective.
Builds an executive-grade decision evidence packet from runtime signals and confidence checks.
| name | ai-query-rewrite-lab |
| description | Generate safe query rewrite candidates with deterministic explainability without executing SQL. |
Use this skill to propose safer or cheaper SQL variants before running EXPLAIN or executing a statement.
Run:
node runtime/runTool.js ai_query_rewrite_lab '{"engine":"postgres","database":"analytics","schema":"public","table":"events","sql":"SELECT * FROM events WHERE user_email = ''a@example.com''"}'
The lab never executes SQL. It returns rewrite candidates, expected impact ranges, applied rewrite rules, and a safety block that marks the output as analysis-only.