review-change

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

The implementer makes it work, this skill makes it good, in a context that did not write it. The reviewer's default output is a fix; it reports only what it may not fix. It judges standards and fit with the rest of the codebase, not the spec, and passes on a bug only as a question.

Arguments: an optional fixed point, an optional

--no-check

, then optional standards paths.

实现者负责让它能用，这个 skill 负责让它变好，而且整个过程必须在一个未编写该变更的上下文中进行。审查者的默认输出是修复；它只报告自己可能无法修复的内容。它依据编码标准及其与代码库其余部分的适配性进行判断，而不是依据 spec；遇到 bug 时，仅以问题的形式提出。

参数：一个可选的固定点、一个可选的

--no-check

，随后是可选的标准文件路径。

Steps

步骤

Pin the diff. The fixed point defaults to the merge-base of
```
HEAD
```
and the default branch;
```
HEAD
```
means uncommitted work only. Resolve it with
```
git rev-parse --verify <ref>^{commit}
```
and stop if it fails. The change is everything from the fixed point to the working tree, untracked files included:
```
git diff --name-only <fixed-point>
```
plus
```
git ls-files --others --exclude-standard
```
. Drop untracked dependency installs and build output, and remember them for the report. An empty list ends the skill: say there is nothing to review.
Find the standards, all of them, in precedence order: paths passed as arguments,
```
.agents/coding-standards.md
```
,
```
CODING_STANDARDS.md
```
,
```
CONTRIBUTING.md
```
and any other doc on how to write code here (not a user manual, product doc, or brand guide). Also collect the linter, formatter and type-checker configs the project's check command uses (not build or test-runner configs), and every
```
AGENTS.md
```
and
```
CLAUDE.md
```
at the root or in a touched directory. No standards at all is normal: the review runs on the baseline.
Run one reviewer in a fresh subagent, passing everything below the line in references/reviewer-brief.md with placeholders filled and paths absolute. If your harness has no subagents, stop and tell the user to run this skill in a fresh session: the context that wrote the change will agree with it. Check the block it returns: it matches the template, every
```
file:line
```
points at the code it describes in the working tree, and it is at most 400 words. On a miss, send it back once naming what failed; if it still fails, return it with a
```
Shape:
```
line after
```
Dropped:
```
.
Check the fixes, unless the call carried
```
--no-check
```
(a caller running its own gate). If the reviewer fixed anything, run the project's typecheck, lint and tests once, taken from the agent instructions, then the package scripts, then CI. Leave fixes in place when a check fails; the next step's owner decides.

锁定 diff。 固定点默认为
```
HEAD
```
与默认分支的 merge-base；
```
HEAD
```
表示仅审查未提交的工作。使用
```
git rev-parse --verify <ref>^{commit}
```
解析固定点；若失败则停止。变更包括从固定点到工作区之间的所有内容，并包含未跟踪文件：
```
git diff --name-only <fixed-point>
```
加上
```
git ls-files --others --exclude-standard
```
。从中排除未跟踪的依赖安装文件和构建输出，并在报告中记住它们。列表为空时结束 skill，并说明没有可审查的内容。
查找全部标准，并按以下优先级排序：作为参数传入的路径、
```
.agents/coding-standards.md
```
、
```
CODING_STANDARDS.md
```
、
```
CONTRIBUTING.md
```
，以及任何其他说明如何在此编写代码的文档（不包括用户手册、产品文档或品牌指南）。同时收集项目 check 命令所使用的 linter、formatter 和 type-checker 配置（不包括 build 或 test-runner 配置），以及根目录或已触及目录中的每个
```
AGENTS.md
```
和
```
CLAUDE.md
```
。完全没有标准也是正常情况：审查将基于现有代码基线进行。
在一个全新的 subagent 中运行一个 reviewer，并传入 references/reviewer-brief.md 中分隔线以下的所有内容，同时填好占位符并使用绝对路径。如果 harness 不支持 subagent，则停止并告知用户在全新的 session 中运行此 skill：编写该变更的上下文会认同它。检查返回的 block：它应符合模板、每个
```
file:line
```
都指向工作区中所描述的代码，且不超过 400 words。如果不符合，将其退回一次，并明确指出失败之处；如果仍不符合，则返回该 block，并在
```
Dropped:
```
后添加
```
Shape:
```
行。
检查这些修复，除非调用包含
```
--no-check
```
（调用方正在运行自己的 gate）。如果 reviewer 修复了任何内容，则运行项目的 typecheck、lint 和 tests，各运行一次；检查命令依次取自 agent instructions、package scripts 和 CI。检查失败时保留修复；下一步的负责人将决定如何处理。

Report

报告

The reviewer's block, then:

text

Checks: <command> pass | <command> fail: <first failing step> | not run: no fixes | not run: --no-check
Dropped: <paths, or "none">

The block is plain text so a caller can paste it into a commit or PR unchanged. This skill always finishes; what a

blocks

finding stops is the caller's call. It never stages, commits, pushes, or comments on a PR.

reviewer 的 block，然后：

text

Checks: <command> pass | <command> fail: <first failing step> | not run: no fixes | not run: --no-check
Dropped: <paths, or "none">

该 block 为纯文本，便于调用方原样粘贴到 commit 或 PR 中。此 skill 始终会运行完毕；即使存在

blocks

级发现，是否中止也由调用方决定。它绝不会 stage、commit、push，也绝不对 PR 发表评论。