Thermos

作者 cursorccb5507cec15无许可证10K 个星标收录于 2026年10月8日更新于 2026年10月8日仓库今天更新

Launch both thermo-nuclear review subagents in parallel, then synthesize their findings. Use for thermos, double thermo review, or combined bug/security and code-quality branch audits.

AI 生成的概览

并行运行两个代码审查子代理,并将其发现综合为一份按优先级排序的结论。

功能
该技能以并行后台子代理的方式编排两轮审查:一轮覆盖缺陷、破坏性变更、安全性、开发者体验回退和功能开关泄漏,另一轮覆盖可维护性、结构、文件体积增长、代码混乱和抽象健康度。它收集差异和上下文,将相同的限定材料传给两位审查者,然后把结果合并为去重并按优先级排序、带文件引用的发现。最终输出是一份统一结论,对重叠发现给予更高权重,并说明仍存在的不确定性。
适用场景
适用于对分支、拉取请求或一组变更文件进行缺陷、安全与代码质量的综合审查。也适合被称为 thermos 或双重 thermo 审查的请求,即需要运行并协调两种独立审查视角。
运行要求
不附带脚本,仅为指令。需要支持以异步后台任务方式启动指定子代理类型的代理环境。

Thermos

Run the two thermo review passes as async background subagents in parallel, then synthesize their results.

Workflow

  1. Determine the review scope from the user request, PR, current branch, or relevant changed files.
  2. Gather the diff and any file/context excerpts needed for reviewers to evaluate the change without guessing.
  3. Launch both subagents in the same message with run_in_background: true:
    • subagent_type: "thermo-nuclear-review-subagent" for bugs, breakages, security, devex regressions, feature-flag leaks, and other branch-audit risks.
    • subagent_type: "thermo-nuclear-code-quality-review-subagent" for maintainability, structure, file-size growth, spaghetti, abstractions, and codebase-health risks.
  4. Pass each subagent the same scoped diff/file context and ask it to return prioritized findings with file references and evidence.
  5. After both finish, synthesize the results with findings first, deduplicated across reviewers. Weight overlapping findings more heavily, resolve disagreements with your own judgment, and keep summaries brief.

If individual background summaries are already visible to the user, do not restate them wholesale. Surface the unified verdict, the highest-signal findings, and any remaining uncertainty.

来源与署名

来源:cursor/plugins位于thermos/skills/thermos提交ccb5507

许可证: 无许可证

内容归原作者所有。SourceWeft 从公开仓库中收录这些内容。

举报或申请下架