review-implementation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Review Implementation (internal scope/classification engine)

审查实现（内部范围/分类引擎）

The classification engine the review/audit skills compose: it consumes the synthesized findings table (the fused output of the applicable per-axis passes), verifies every applicable axis is represented, and returns the classified decision table — then stops. Never refactors or edits code. It owns the scope/axis-coverage contract and the classification rubric (the current-unit contract + routing) that

review-change

audit-pr

, and

product-audit

reference instead of restating.

It does not scan the diff: every finding concern has exactly one owning pass (see the axis ownership map) — the per-axis passes (

review-code

review-security

review-verify

review-perf

, design/a11y/brand/SEO) find, and this engine classifies. No broad findings scan here.

该分类引擎由审查/审计类技能组成：它接收合成的问题检查表（各适用维度检查的融合输出），验证所有适用维度均已覆盖，并返回分类后的决策表——随后停止运行。绝不重构或编辑代码。它拥有范围/维度覆盖协议和分类准则（当前单元协议+路由规则），

review-change

、

audit-pr

和

product-audit

均引用该准则，无需重复定义。

它不扫描代码差异：每个问题都对应唯一的检查模块（详见维度归属映射）——各维度检查模块（

review-code

、

review-security

、

review-verify

、

review-perf

，以及设计/无障碍/品牌/SEO检查）负责发现问题，而本引擎负责分类。此处不进行宽泛的问题扫描。

When to use

使用场景

Invoked by
```
review-change
```
(the user-facing review entry) as its classification engine, over the fused findings table.
The audit skills reference its rubric and coverage contract.

作为
```
review-change
```
（面向用户的审查入口）的分类引擎，对融合后的问题检查表进行处理。
审计类技能引用其分类准则和覆盖协议。

Scope

范围

The caller's scope statement (the branch diff vs. the default branch, or the passed path/glob) is authoritative; the synthesized table was gathered over it. State the scope at the top of the classified report.

调用方的范围声明（分支差异与默认分支对比，或传入的路径/通配符）具有权威性，合成检查表是基于该范围收集的。需在分类报告顶部明确说明范围。

Step 0 — Discover the project (always first)

步骤0 — 项目调研（始终优先执行）

Per the agent guide's Workflow conventions + documentation map, read what THIS skill needs: the architecture/layering rules, the testing philosophy, and any runtime/platform, security, money, i18n/SEO/a11y and bundle rules. Pull the project's specific risk axes from its guardrail skills where present. The

FIND.md

axis map is the default; the project's docs refine which axes are applicable.

根据Agent指南的工作流约定 + 文档映射，读取本技能所需的信息：架构/分层规则、测试理念，以及任何运行时/平台、安全、成本、国际化/SEO/无障碍和包体积规则。从项目的防护技能中提取特定的风险维度（若存在）。

FIND.md

维度映射为默认规则，项目文档会细化哪些维度适用。

Step 1 — Verify axis coverage (the synthesized table)

步骤1 — 验证维度覆盖（合成检查表）

For the declared scope, confirm every applicable axis is represented in the synthesized findings table — one finding owner per axis, per the

FIND.md

map: an axis the change touches that the table says nothing about is a missing-axis finding (axis

coverage

), not a silent pass. Overlapping signals from different passes on the same defect collapse into one row during synthesis — the table must contain neither duplicates nor gaps. State which axes were applicable and confirm each appears.

针对已声明的范围，确认所有适用维度均在合成检查表中有所体现——根据

FIND.md

映射，每个维度对应唯一的问题归属模块：若变更涉及某个维度，但检查表中未提及该维度，则属于缺失维度问题（维度

coverage

），而非默认通过。不同检查模块针对同一缺陷的重叠信号会在合成过程中合并为一行——检查表中不得存在重复行或遗漏项。需说明哪些维度适用，并确认每个维度均已覆盖。

Step 2 — Classify (the current-unit contract)

步骤2 — 分类（当前单元协议）

Read Classify and route and classify every row of the synthesized table without reopening source files:

ignore

first (the claim), then the current-unit contract (fix-now / replan-in-unit / decision-required for in-scope work), then

proposal

for genuinely independent future capabilities. One pass — no per-pass or per-reviewer classification.

阅读分类与路由，无需重新打开源文件即可对合成检查表的每一行进行分类：首先标记

ignore

（无需处理的问题），然后根据当前单元协议对范围内的工作标记

fix-now

replan-in-unit

decision-required

，最后对真正独立的未来功能标记

proposal

。仅执行一次分类——不按检查模块或审查者分别分类。

Context budget

上下文限制

The input is the synthesized table, not the diff. Read at most 10 non-diff files in full for surrounding context (callers, contracts, SPEC); targeted reads (≤ 50 lines of a named range) and grep/glob results don't count. Record each classification as its table row immediately and drop raw file content.

输入为合成检查表，而非代码差异。最多完整读取10个非差异文件以获取上下文信息（调用方、协议、SPEC）；定向读取（指定范围≤50行）和glo b/通配符搜索结果不计入限制。需立即将每个分类记录到对应表行，并丢弃原始文件内容。

Guardrails

防护规则

Findings + table only. Never refactor or edit code in this skill.
One classifier. Classification happens HERE, once, over the fused table — never per-reviewer, never re-litigated in the per-axis passes.
Honor the dead-code exception — staged/planned code is not dead code.
Don't inflate severity; separate "correctness/security" from "taste".
Don't deflate either: current-unit work is never
```
postpone
```
/
```
tradeoff
```
/
```
wontfix
```
/
```
disputed
```
and never a new issue — size routes to
```
replan-in-unit
```
, not to a downgrade (current-unit contract in
```
CLASSIFY.md
```
).
Otherwise per the project's Workflow conventions (docs-language, evidence): cite
```
file:line
```
, mark uncertainties verify.

仅处理问题与检查表。本技能绝不重构或编辑代码。
单一分类器。 分类仅在此处执行一次，基于融合后的检查表——绝不按审查者分别分类，也不在各维度检查模块中重新讨论分类结果。
遵循死代码例外规则——已排期/规划的代码不属于死代码。
不夸大问题严重性；区分“正确性/安全性”与“个人偏好”。
也不低估问题严重性：当前单元的工作绝不能标记为
```
postpone
```
/
```
tradeoff
```
/
```
wontfix
```
/
```
disputed
```
，也不能创建新问题——问题规模决定是否标记为
```
replan-in-unit
```
，而非降低优先级（详见
```
CLASSIFY.md
```
中的当前单元协议）。
其他需遵循项目的工作流约定（文档语言、证据）：引用
```
file:line
```
，对不确定项标记verify。

Relationship to other skills

与其他技能的关系

Classification engine of
review-change
— the user-facing review skill runs the applicable per-axis passes (the finders), fuses their tables, then composes this engine to classify.
```
audit-pr
```
and
```
product-audit
```
reuse this rubric.
Sits in Stage 4 of the feature workflow (verification & review).
```
fix-now
```
folds into the current unit;
```
replan-in-unit
```
appends user-confirmed phases then
```
execute-phase
```
on the same branch;
```
decision-required
```
blocks for the user; independent work becomes proposals the user routes to
```
triage-issue
```
(D3).

review-change
的分类引擎——面向用户的审查技能运行各适用维度检查模块（问题发现模块），融合其检查表，然后调用本引擎进行分类。
```
audit-pr
```
和
```
product-audit
```
复用该分类准则。
处于功能工作流的第4阶段（验证与审查）。
```
fix-now
```
问题需纳入当前单元；
```
replan-in-unit
```
问题需追加用户确认的阶段，然后在同一分支上执行
```
execute-phase
```
；
```
decision-required
```
问题需等待用户决策；独立工作会转化为提案，由用户路由至
```
triage-issue
```
（D3）。

Done when

完成标志

A synthesized table consumed, axis coverage verified (no applicable axis missing, no duplicate rows), every finding classified with reasoning and routed — and no code changed.

已接收合成检查表，验证维度覆盖（无适用维度缺失，无重复行），每个问题均已分类并给出理由和路由——且未修改任何代码。