Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →vaycentsun/sw-code-review
Use when requesting code review for completed work or when receiving code review feedback
Passed 18 of 22 test cases with the skill, and 7 of 22 without it.
and 13 more in the full report
11 fixed7 passed either way4 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Our sub-agent automated code review loop just failed its second iteration due to remaining style and logic issues. How many total review-and-fix iterations are permitted in this review pipeline before stopping, and what happens when a review passes?
| Checked | Without skill | With skill |
|---|---|---|
| States that the review loop is capped at a maximum of 3 attempts | Passed | Passed |
| Indicates that passing review automatically triggers sw-task-verification | Missed | Passed |
The instructions your model reads when the skill loads.
在软件开发流程中自动执行代码审查：完成任务后自动发起审查，收到反馈后技术严谨地处理。
核心原则： 审查是流程的自动环节，不是可选步骤。实现前先验证，不表演性同意。
强制触发点：
开发流程集成：
1. 获取 git SHAs：
BASE_SHA=$(git rev-parse HEAD~1) # 或 origin/main
HEAD_SHA=$(git rev-parse HEAD)
2. 分派代码审查者子 Agent：
使用 Task 工具配合 sw-code-review 类型，填写 ./code-reviewer.md 模板
占位符：
{WHAT_WAS_IMPLEMENTED} - 你刚刚构建了什么{PLAN_OR_REQUIREMENTS} - 它应该做什么{BASE_SHA} - 起始提交{HEAD_SHA} - 结束提交{DESCRIPTION} - 简要摘要3. 根据反馈行动：
test cases passed, vs 7 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.