菜单
Use when evaluating system architecture, platform design, or high-level technical structure to identify production risks, evidence gaps, and prioritized remediation without directly redesigning or implementing the system.
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
Use when handling local Git CLI daily operations such as checking status or diff, staging files, creating conventional commits, restoring local changes, reverting commits, or resolving merge/rebase/cherry-pick conflicts.
Use when explaining code, answering technical questions, comparing approaches, or providing repository-grounded analysis without entering an implementation or remediation workflow.
Use when improving internal code structure without intentionally changing externally observable behavior, such as module splits, simplification, dependency cleanup, or maintainability and performance-oriented restructuring.
Use when feature ideas, issues, stakeholder notes, or partial specs need to be reviewed and turned into a concise, testable PRD with clear scope, user stories, acceptance criteria, and explicit open decisions.
Use when a PRD, feature spec, or acceptance criteria already exist and need to be turned into a concise test plan and traceable test cases with clear priorities, coverage, and execution focus.
Use when reviewing pull requests, diffs, patches, or repository files to identify merge-blocking issues, important risks, and evidence gaps without directly fixing the reviewed artifact.
| name | architecture-review |
| description | Use when evaluating system architecture, platform design, or high-level technical structure to identify production risks, evidence gaps, and prioritized remediation without directly redesigning or implementing the system. |
architecture-review 是系统级风险评审 lane。它的职责是：围绕目标、约束和证据，识别架构层阻断风险、重要缺口与优先修复项，并把结论绑定到可追溯依据。
它不是直接做重构、重设计或实现的 lane。除非用户明确要求方案设计，否则它默认产出的是评审结论，而不是替代架构演进本身。
适用于：
以下情况不要直接进入本 skill：
遇到这些情况时，优先转交：
skills/develop-feature/SKILL.mdskills/fix-bug/SKILL.mdskills/refactor/SKILL.mdskills/review-code/SKILL.mdskills/reviewing-product-requirements/SKILL.mdsuperpowers:brainstorming评审对象 / 范围 / 目标 / 非目标 / 约束 / 当前证据。Architect / Software Engineer / QA / Operations/SRE；涉及安全、成本、合规或 Prompt/Agent 行为时必须追加对应视角。architecture-review 退化成直接重设计、代写实现方案或顺手改系统。XY 风险，必须先回到 superpowers:brainstorming。Align
对象 / 范围 / 目标 / 非目标 / 约束 / 证据Assess Input Quality
Gather Evidence
Review
边界与耦合 / 数据一致性 / 容量与扩展 / 可靠性与恢复 / 安全与访问控制 / 可观测性 / 部署与回滚 / 成本与效率合规 / Prompt-Agent Behavior / 数据治理 / 支持与可启用性Decide
Review Action: Accept | Concern | ReworkQuality Result: PASS | CONDITIONAL PASS | FAILAccept + PASSReport
Findings -> Assumptions / Evidence Gaps -> Review Action -> Quality Result -> Priority Fixes -> Risks -> Done / Partial / SkippedCritical
Important
Suggestion
每条 finding 至少应包含：
DomainSeverityIssueWhy it mattersEvidenceRecommended action按需读取以下规则或相邻 skill：
rules/roles.md
rules/deliverable-quality-gate.md
PASS / CONDITIONAL PASS / FAIL 判定与证据门槛时读取rules/output-style.md
skills/review-code/SKILL.md
skills/reviewing-product-requirements/SKILL.md
不要把 provider-specific 框架清单整段抄进评审；只保留对当前系统有判别力的风险视角。
出现以下信号时，说明架构评审正在退化：
对用户的交付至少应包含：
FindingsAssumptions / Evidence GapsReview ActionQuality ResultPriority FixesRisksDone / Partial / Skipped若未发现阻断问题，必须明确写出：未发现阻断问题，并补充证据边界与残余风险。
若当前路径没有更优替代方案，应明确写出：当前路径合理，暂无更优替代建议。
rules/output-style.md 与 rules/deliverable-quality-gate.md