来源信息
- 仓库
- codejunkie99/agentic-stack-desktop
- 最近来源活动
- 2026年9月10日 07:18
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 72
- 分支
- 9
安装方式
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。
检查来源文件
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。
正在显示 SKILL.md
SKILL.md
来源说明 · 只读预览- name
- debug-investigator
- description
- Reproduce, isolate, and verify the root cause of a software failure.
- version
- 2026-01-01T00:00:00.000Z
- triggers
- ["debug","why is this failing","investigate","stack trace","bug"]
- tools
- ["bash","memory_reflect"]
- constraints
- ["reproduce before fixing","fix root cause, not symptoms"]
# Debug Investigator — systematic, not vibes-based
Follow this loop every time. Jumping straight to "fix" without reproducing
is how false fixes ship.
## The loop
1. **Reproduce.** Get a deterministic failure. If you can't reproduce, you
can't fix.
2. **Isolate.** Bisect the problem space: narrow inputs, narrow code paths,
narrow time windows.
3. **Hypothesize.** Form *one* explicit hypothesis. Write it in
`memory/working/WORKSPACE.md` under "Active hypotheses".
4. **Test the hypothesis.** A single change that proves or disproves it —
no shotgun fixes.
5. **Verify.** After the fix, re-run the repro. If the bug is gone, the
repro is your new regression test.
## What to log
- Each hypothesis that was wrong (high importance; these compound into
domain knowledge).
- The actual root cause and why it wasn't obvious.
## Anti-patterns
- "It works now, not sure why" — keep investigating.
- Adding `try/except` to silence an error without understanding it.
- Changing five things at once and claiming one of them fixed it.
## Self-rewrite hook
If the same class of bug appears 3+ times (timezone bugs, race conditions,
off-by-one), promote a lesson to `LESSONS.md` and update this skill with
a domain-specific sub-procedure.
在 GitHub 查看