菜单
Diagnose a reported bug, a failing CI or lint job, or a performance regression, and find its cause. Use when something is broken, failing, throwing, hanging, or slower than it was, when CI or a pipeline fails, or when the user asks why something is happening.
默认使用会先检查来源的 Prompt；你也可以切换为直接命令，或下载本地副本。
决定是否安装前，请先阅读 SKILL.md，以及 SkillsMP 当前展示的配套文件。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/bendrucker/claude --skill diagnosing-bugs命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
Working with GitLab merge requests via glab. Use when creating, updating, reviewing, or merging MRs, enabling auto-merge or merge trains, requesting or re-requesting reviewers, handling approvals, or working review threads, discussions, and draft notes. Load before running any `glab mr` or MR-mutating `glab api` command.
Create a pull request, merge request, or change request with proper formatting and content guidelines. Invoke when the user wants to create, open, or submit a PR, MR, or CR, including after committing changes.
Update a pull request or merge request body to reflect the current state of changes. Use when a PR/MR has evolved through additional commits and the body needs to reflect what will be merged.
| name | diagnosing-bugs |
| description | Diagnose a reported bug, a failing CI or lint job, or a performance regression, and find its cause. Use when something is broken, failing, throwing, hanging, or slower than it was, when CI or a pipeline fails, or when the user asks why something is happening. |
| argument-hint | [<what is broken>] |
Diagnose the failure in $ARGUMENTS, or the one the user just reported.
Build one command that fails on this bug. Reading and grepping to work out how to invoke the failing path is how you build it, not a detour around it.
A command that shows only that nothing crashed does not count. It has to drive the real code path and produce the symptom that was reported.
For a failing CI or pipeline job, that command already ran. Use github:actions-monitor or gitlab:ci-monitor to get the logs rather than reconstructing the job locally.
When nothing you try reaches the bug, say so and stop. Name what you tried and what each attempt could not reach, then ask for an environment where it reproduces, a captured artifact, or permission to add instrumentation.
Change one thing per run and let the command settle it. A cause the command has not responded to is a guess, and saying which line is at fault is not the same as showing the command go green when you change it.
Report one cause. When the cause is not clear, say what you ruled out and how you ruled it out, then ask rather than presenting a list to choose from.
With the cause established and the fix clear, enter plan mode and map out the implementation.
When the user asked you to diagnose without changing anything, stop at the cause and the plan.
Once a fix is in, run the original reproduction again. Report it fixed only after that command passes, and quote the run.
A fix that was never run against the thing that failed is not a fix, and neither is one verified against a smaller case you built along the way.