Back to Details

review-change

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Review Change

变更评审

Quality gate: run every applicable review and skip the rest, then synthesize and classify one report. Findings only; never edit or refactor.
质量门禁：运行所有适用的评审，跳过其余评审，然后合并结果并生成一份分类报告。仅输出问题发现；绝不编辑或重构代码。

Turn contract

交互契约

Load and verify the canonical Turn contract (11 boxes) before ending every turn. Skill-specific additions (receipt closeout, isolation rule, applicability) live here and in REVIEW_PROCESS.md. Missing reference → STOP.
For a final PR review, the turn is incomplete until this additional box passes:
text
✓ Decision: REVIEW-PASS + PR exists → `gh pr comment <N> --body-file <path>` RUN;
  then `gh pr view <N> --json comments` RUN and the newest exact-HEAD
  `review-change:pass` marker is confirmed before printing `→ Next:`
The receipt closeout is a precondition of the report, not a follow-up: do not print the fixed report block until the comment is current. A clean report without that current receipt must not recommend 
/audit-pr
.
For 
REVIEW-FAIL
or 
NEEDS-DECISION
, list every open finding ID in the closing recommendation, joined with 
+
; the review must never hand off only the first finding.
Consume the internal verification contract; the reviewer checks the same frozen 
ACCEPTANCE.md
blob as the executor before mapping candidate evidence.
在每轮交互结束前，加载并验证标准的Turn contract（11项检查）。技能专属的补充内容（收尾确认、隔离规则、适用性）在此文档及REVIEW_PROCESS.md中。若缺失参考文档→立即停止。
对于最终的PR评审，需完成以下额外检查项才算交互完成：
text
✓ Decision: REVIEW-PASS + PR exists → `gh pr comment <N> --body-file <path>` RUN;
  then `gh pr view <N> --json comments` RUN and the newest exact-HEAD
  `review-change:pass` marker is confirmed before printing `→ Next:`
收尾确认是生成报告的前提条件，而非后续步骤：在确认评论已更新前，不得输出固定格式的报告块。若没有当前的收尾确认，即使报告无问题也不得推荐使用
/audit-pr
。
若评审结果为
REVIEW-FAIL
或
NEEDS-DECISION
，需在收尾建议中列出所有未解决的问题ID，用
+
连接；评审不得仅移交第一个发现的问题。
遵循内部的验证契约；评审者在映射候选证据前，需与执行者检查同一个冻结的
ACCEPTANCE.md
文件。

When to use

使用场景

  • Mandatory before every merge. Review in a context that did not implement the change; if it did, stop and hand off to a fresh one. 
    execute-phase
    may also recommend optional checkpoints at layer boundary, accumulation or sensitivity (
    #77
    ).
  • Use when you need applicable reviews without irrelevant passes.
  • 合并前强制要求。在未参与变更实现的环境中进行评审；若评审环境参与了变更实现，则停止评审并移交至全新环境。
    execute-phase
    也可能建议在层边界、代码累积或敏感点处设置可选检查点（
    #77
    ）。
  • 当你需要仅针对适用场景进行评审，避免无关检查时使用。

Scope

评审范围

Default target is the current change (branch diff vs the default branch); accept a path/glob to widen or narrow. State the scope at the top of the report.
默认评审目标为当前变更（分支与默认分支的差异）；可接受路径/通配符来扩大或缩小范围。需在报告顶部说明评审范围。

Step 0 — Discover the project & the change (always first)

步骤0 — 了解项目与变更（始终第一步）

Per Workflow conventions + documentation map, decide axes from:
  1. Project nature: UI (
    docs/frontend/
    ), web/mobile/CLI/library/backend, and optional recorded platform skills (extras only).
  2. Footprint: what the diff touches (UI, API, infra, domain). An axis applies only when both project and footprint support it.
根据工作流规范及文档映射，从以下维度确定评审轴：
  1. 项目性质：UI（
    docs/frontend/
    ）、Web/移动/CLI/库/后端，以及可选的已记录平台技能（仅额外内容）。
  2. 影响范围：变更涉及的内容（UI、API、基础设施、业务领域）。只有当项目性质与影响范围均支持某一轴时，该轴才适用。

Applicability matrix (default; the project's docs refine it)

适用性矩阵（默认；项目文档可细化）

Every axis maps to a skill of the workflow's own internal review pack (
skills/review-*
— installed with the workflow, so none can be missing):
Axis — internal pack skillWebMobileConsole/CLILib/SDKBackend/Infra
review-code
(correctness, simplification, dead code, duplication, arch)		✓✓✓✓✓
review-security
✓✓✓✓✓
review-verify
(run it, confirm real behavior, tests)		✓✓✓✓✓
review-design
(UI/UX)		✓✓TUI only✗✗
review-a11y
✓✓rare✗✗
review-brand
(voice/copy)		✓✓output text✗✗
review-perf
✓✓✓✓✓
review-seo
✓✗✗✗✗
API ergonomics / usage docs (inline pass)if APIif APIflags/help✓✓✓
review-implementation
(the single classifier over the synthesized table — process step 7) and 
review-debt
(the debt transform over the classified table — process step 8) are not axis finders: they run once per review, not per axis.
每个轴对应工作流内部评审包中的一项技能（
skills/review-*
— 随工作流安装，无缺失）：
轴 — 内部包技能Web移动控制台/CLI库/SDK后端/基础设施
review-code
（正确性、简化、死代码、重复代码、架构）		✓✓✓✓✓
review-security
✓✓✓✓✓
review-verify
（运行验证、确认实际行为、测试）		✓✓✓✓✓
review-design
（UI/UX）		✓✓仅TUI✗✗
review-a11y
✓✓罕见✗✗
review-brand
（语气/文案）		✓✓输出文本✗✗
review-perf
✓✓✓✓✓
review-seo
✓✗✗✗✗
API 易用性 / 使用文档（内联检查）若涉及API若涉及API命令行参数/帮助✓✓✓
review-implementation
（对合并后的结果表进行分类的单一分类器 — 流程步骤7）和
review-debt
（对分类后的结果表进行债务转换 — 流程步骤8）不属于轴查找器：它们在每次评审中仅运行一次，而非每个轴运行一次。

Isolation rule (default — every pass, not only adversarial)

隔离规则（默认 — 每次检查均适用，不仅限于对抗式评审）

Each applicable pass, the classifier (step 7), and debt transform (step 8) runs isolated/context-clean and returns only its fixed findings table plus 
PASS | FAIL
—never diff or prose. Spawn one fresh subagent/headless run per pass; without those, use a fresh conversation. Pass only scope, its checklist, and Step 0 docs; cap full non-diff reads at 10 (targeted ≤50-line reads/greps excluded). The orchestrator retains tables, not sources, and fuses them in step 6. Inline fallback is sequential table reduction. A pass runs at its own tier or stronger, never weaker.
每个适用的检查、分类器（步骤7）和债务转换（步骤8）均需在独立/干净的上下文中运行，仅返回固定格式的问题发现表及
PASS | FAIL
结果——绝不返回差异内容或散文式描述。为每次检查生成一个全新的子Agent/无头运行实例；若无法实现，则使用全新对话。仅传递评审范围、检查清单及步骤0的文档；非差异内容的完整读取上限为10次（针对性的≤50行读取/ grep除外）。编排器仅保留结果表，不保留源内容，并在步骤6中合并这些表。内联回退方案为顺序表归约。检查需在自身层级或更强层级运行，绝不使用更弱层级。

Progressive loading — choose one review route

渐进式加载 — 选择一条评审路径

After applicability and isolation are established:
The reference allowlist is exactly the seven linked paths below. Never invent or read another 
references/
path.
Invocation routeLOAD in this orderSKIP
Default reviewreview process → adversarial recommendation → persist and decide → output and guardrailssynthesis, portability, adversarial setup
--adversarial N
review process → adversarial setup before reviewers → adversarial synthesis before fusion → persist/decide → output/guardrailsportability
--synthesize
review process → adversarial synthesis plus the supplied reviewer tables → persist/decide → output/guardrailsadversarial setup, portability
legacy 
--merge
print the fixed migration refusal below and stop — zero git/forge mutationeverything
Legacy 
--merge
is removed — not an alias. Calling 
/review-change --merge
prints this fixed migration refusal and stops before any git or forge mutation command runs:
migration: --merge is removed. Table fusion is --synthesize: pass the fixed
reviewer tables the same way and the synthesis contract fuses them. No
repository merge is performed by this skill.
Active review paths use only 
--synthesize
/fusion language. Add portability only when contexts, parallelism, slash commands or tier controls are unavailable. 
docs/workflow/REPOSITORY_STATE.md
is evidence for output/guardrails, not a skill reference; that route owns NRS and Architectural invariants rules.
Resources are one hop from this file. Fixed reviewer/synthesis/output contracts are literal. Missing required resource → stop; never approximate a review contract.
确定适用性与隔离规则后：
参考白名单仅包含以下7个链接路径。不得创建或读取其他
references/
路径。
调用路径按此顺序加载跳过内容
默认评审评审流程 → 对抗式评审建议 → 记录与决策 → 输出与防护规则结果合并、可移植性、对抗式设置
--adversarial N
评审流程 → 评审前加载对抗式设置 → 合并前加载对抗式结果合并 → 记录/决策 → 输出/防护规则可移植性
--synthesize
评审流程 → 对抗式结果合并 + 提供的评审结果表 → 记录/决策 → 输出/防护规则对抗式设置、可移植性
旧版
--merge
打印以下固定的迁移拒绝信息并停止 — 不执行任何git/代码托管平台操作所有内容
旧版
--merge
已移除 — 无别名。调用
/review-change --merge
将打印以下固定的迁移拒绝信息，并在执行任何git或代码托管平台操作前停止：
migration: --merge is removed. Table fusion is --synthesize: pass the fixed
reviewer tables the same way and the synthesis contract fuses them. No
repository merge is performed by this skill.
当前有效的评审路径仅使用
--synthesize
/合并相关术语。仅当上下文、并行性、斜杠命令或层级控制不可用时，才添加可移植性。
docs/workflow/REPOSITORY_STATE.md
是输出/防护规则的参考证据，而非技能参考文档；该路径负责NRS和架构不变性规则。
资源均与此文件处于同一层级。固定的评审者/结果合并/输出契约为字面内容。若缺失必需资源→停止；绝不近似评审契约。

Portability

可移植性

Keep reviewer contexts isolated. Use portability for sequential/headless fallbacks; never collapse independent adversarial passes.
保持评审者上下文独立。使用可移植性作为顺序/无头回退方案；绝不合并独立的对抗式检查。

Relationship to other skills

与其他技能的关系

Orchestrates internal finders (
review-code
, 
review-security
, 
review-verify
, 
review-design
, 
review-a11y
, 
review-brand
, 
review-perf
, 
review-seo
), then one 
review-implementation
classifier and 
review-debt
transform, isolated by default; installed platform packs are optional. 
triage-issue
is user-invoked only for independent proposals (D3). It is Stage 4: checkpoint reviews are optional, the end review is mandatory and fresh. 
fix-now
folds in-unit, 
replan-in-unit
adds user-confirmed phases, and independent work becomes proposals. 
audit-pr
consumes only the verified PR-comment receipt, never the chat report; 
product-audit
is the periodic sweep; 
loop-review-fold
may run this skill fresh and route FAIL to 
fold-findings
.
编排内部查找器（
review-code
、
review-security
、
review-verify
、
review-design
、
review-a11y
、
review-brand
、
review-perf
、
review-seo
），然后运行一次
review-implementation
分类器和
review-debt
转换，默认情况下相互隔离；已安装的平台包为可选。
triage-issue
仅由用户调用，用于独立提案（D3）。此技能属于第4阶段：检查点评审为可选，最终评审为强制且需在全新环境中进行。
fix-now
将问题合并至单元内，
replan-in-unit
添加用户确认的阶段，独立工作将成为提案。
audit-pr
仅使用已验证的PR评论记录，绝不使用聊天报告；
product-audit
为定期扫描；
loop-review-fold
可重新运行此技能，并将失败结果路由至
fold-findings
。

Done when

完成标志

  • One synthesized/classified table covers every applicable axis, lists skipped axes with reasons, and includes manual checks. Every finding has a destination: fold, confirmed replan phase, surfaced decision, or user-routed proposal; none is silently lost and review creates no backlog (D3). Print the closing 
    → Next:
    block (clean → 
    /audit-pr
    ; recurring drift → 
    /product-audit
    ) and change no code.
  • 一份合并后的分类表覆盖所有适用的评审轴，列出跳过的轴及原因，并包含人工检查项。每个问题都有明确的处理方向：合并至单元内、确认重新规划阶段、提交决策或用户路由至提案；无问题被静默忽略，且评审不会产生待办积压（D3）。打印收尾的
    → Next:
    块（无问题→
    /audit-pr
    ；持续漂移→
    /product-audit
    ），且不得修改任何代码。