菜单
Grade advisory recommendations by evidence strength and identify missing proof before production change.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
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 | advisor-confidence-grader |
| description | Grade advisory recommendations by evidence strength and identify missing proof before production change. |
Run:
node runtime/runTool.js advisor_confidence_grader '{"evidence":{"hasLivePlan":true,"hasWaits":true,"hasRollback":true}}'
Returns evidence grade, score, missing evidence, and required next evidence.