audit
免费Review code through focused dimensions, with one independent agent per dimension.
中文简介正在准备中。当前显示原文说明。
Obtain an independent review of the approach and trade-offs in completed work.
中文简介正在准备中。当前显示原文说明。
查看安装方法安装前可以查看交给 AI 代理的指令内容。
Review $ARGUMENTS, or the latest substantive work when omitted. Infer scope from the conversation and relevant files; ask only if ambiguity would materially change the review.
Delegate to one independent, read-only reviewer with a clean context: the requested outcome, constraints, subject, relevant files, stack, and project conventions. Do not provide your verdict or preferred critique. Add reviewers only for materially distinct expertise. If delegation is unavailable, disclose that limitation; do not call self-review independent.
Ask the reviewer to assess domain fitness, architectural choices, proportionality, and fundamentally different ways to achieve the outcome. Distinguish justified deviations from missed constraints; compare simplicity against real requirements and account for the adoption costs of alternatives. Feature necessity is a separate lens available through /audit necessity, not an automatic additional pass.
Retain findings supported by specific evidence, an actionable alternative, and its costs. Distinguish defects, valid trade-offs, and preferences. Remove claims that misread constraints or lack evidence; preserve meaningful disagreements if multiple reviewers were used.
Report a clear recommendation and its rationale, validated strengths, findings by importance, and the single most valuable change, if any. Identify missing evidence and reviewer limitations. Stop after the report; implement only when asked.
还没有评价。欢迎分享你的使用感受。
无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。
还没有评论。来写第一条吧。
Review code through focused dimensions, with one independent agent per dimension.
中文简介正在准备中。当前显示原文说明。
Explore competing approaches through independent agents before selecting an implementation.
中文简介正在准备中。当前显示原文说明。
Distill rough text into dense, expert-register English where terms of art carry the intent.
中文简介正在准备中。当前显示原文说明。
Apply personal Git conventions when committing, creating or updating PRs, merging, rebasing, or explicitly shipping work end to end.
中文简介正在准备中。当前显示原文说明。
Refine a supplied question into a precise, expert-level query when the user asks to rewrite or optimize their question or prompt. Do not use to answer the underlying question.
中文简介正在准备中。当前显示原文说明。
Unanchored expert verdict on the open decision, checked against the current state of the art.
中文简介正在准备中。当前显示原文说明。