メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
| name | refactor |
| description | 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. |
refactor 是结构调整的执行 lane。它的职责是：在不主动改变外部可观察行为的前提下，完成代码结构、依赖关系、模块边界、性能实现或可维护性的改进，并把“行为保持不变”的结论绑定到证据。
它不是 feature lane，也不是 bugfix lane。凡是目标包含“新增能力”“改变产品行为”“顺手修一批历史问题”，都不应伪装成重构。
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/architecture-review/SKILL.mdskills/answer/SKILL.mdsuperpowers:brainstorming目标 / 范围 / 不做 / 行为边界 / 验收。公共 API / 输入输出 / 错误语义 / 副作用 / 时序 / 数据兼容性 / 资源特征。XY 问题，必须先回到 superpowers:brainstorming。superpowers:writing-plans，不得直接边改边想。superpowers:test-driven-development 约束；不得先改生产实现再补测试。Align
目标 / 范围 / 不做 / 行为边界 / 验收Baseline
Gate
superpowers:brainstormingsuperpowers:writing-planssuperpowers:test-driven-developmentRefactor
Verify
superpowers:verification-before-completion 执行验证Report
Done / Partial / Skipped按需读取以下规则或技能：
rules/deliverable-quality-gate.md
PASS / CONDITIONAL PASS / FAIL 判定时读取rules/output-style.md
skills/develop-feature/SKILL.md
skills/fix-bug/SKILL.md
skills/architecture-review/SKILL.md
不要把所有规则与相邻 skill 一次性压进上下文。
出现以下信号时，说明重构正在退化：
对用户的交付至少应包含：
Done / Partial / Skipped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。
brainstorming / writing-plans / TDD / verification-before-completion 冲突rules/output-style.md 与 rules/deliverable-quality-gate.mdUse 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 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.
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.