Loading...
Loading...
Compare original and translation side by side
/pre-merge/pre-mergegh issue view <number>
gh issue list --search "in:body #<prd-number>" --state all --json number,title,state,body --limit 100git diff main...HEAD --stat
git log --oneline main..HEADgh issue view <number>
gh issue list --search "in:body #<prd-number>" --state all --json number,title,state,body --limit 100git diff main...HEAD --stat
git log --oneline main..HEADgh pr list --head $(git branch --show-current) --json number,urlgh pr creategh pr editundefinedgh pr list --head $(git branch --show-current) --json number,urlgh pr creategh pr editundefined
**PR body template (no PRD):**
```markdown
**PR正文模板(无PRD时使用):**
```markdown
3. Print the PR URL.
3. 输出PR的URL。review-checklist.mdreview-checklist.mddocs/solutions/componentstechnologies.ts.tsx/ts-audit/ts-auditreview-checklist.mdreview-checklist.mddocs/solutions/componentstechnologies.ts.tsx/ts-audit/ts-auditundefinedundefined
**Scope Notes (only when a PRD with slice issues was provided):**
After the three-tier findings, note any significant scope drift between the planned decomposition and the actual diff:
- Work that appears in the diff but wasn't in any slice's Boundary Map (omitted scope discovered during implementation)
- Declared Produces that don't appear in the diff (planned work that was cut or deferred)
- Slices where the actual diff footprint was dramatically different from the boundary map's declared scope
These are factual notes, not review findings. They don't produce Observations, Suggestions, or Concerns — they record plan-vs-actual divergence so the user and `/compound` can decide whether a pattern is worth capturing. Omit this section entirely if the diff aligns closely with the planned boundary maps.
If a concern warrants deeper work, note: "Consider running `/request-refactor-plan` for this area." Do not invoke it.
If a finding looks like a behavioral bug, note: "Consider running `/qa` to verify." Do not file an issue.
Omit any tier that has zero findings.
**范围说明(仅在提供了带拆分任务issue的PRD时展示):**
在三级审查结果之后,标注规划的任务拆分与实际diff之间的重大范围偏差:
- diff中存在但没有出现在任何拆分任务边界映射中的工作(实现过程中发现的遗漏范围)
- 声明的产出没有出现在diff中(被削减或延期的规划工作)
- 实际diff的影响范围与边界映射声明的范围存在显著差异的拆分任务
这些是事实记录,不属于审查结果,不会被归入观察项、建议项或风险项——它们记录了计划与实际的偏差,方便用户和`/compound`命令判断是否有值得记录的模式。如果diff与规划的边界映射高度对齐,可以完全省略该部分。
如果某个风险项需要更深入的处理,提示:"可以考虑针对该范围运行`/request-refactor-plan`",不要自动调用该命令。
如果某个审查结果看起来是功能bug,提示:"可以考虑运行`/qa`进行验证",不要自动创建issue。
如果某个层级没有任何结果,直接省略该层级。/qa/request-refactor-plan/qa/request-refactor-plan/qa/request-refactor-plan/compound/qa/request-refactor-plan/compound