一键导入
investigate
Debug and investigate issues — trace symptoms to root cause. Use when something is broken, a test fails mysteriously, or behavior is unexpected.
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。
菜单
Debug and investigate issues — trace symptoms to root cause. Use when something is broken, a test fails mysteriously, or behavior is unexpected.
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。
基于 SOC 职业分类
Commit all changes, push to remote, and open a pull request in one shot. The most common inner-loop workflow.
Clean start for a new task. Saves important decisions, clears context, and re-reads project config.
Resume work from a previous session. Reads MEMORY.md and continues autonomously.
Adversarial code review — stress-tests recent changes by hunting for bugs, edge cases, security holes, and design flaws. Spawns parallel attack agents, consolidates into a severity-rated report.
Prove that the current implementation works. Runs tests, diffs behavior, validates correctness. Use after implementing a feature or fix to verify before marking complete.
Post-task retrospective — capture lessons learned and store them for future sessions. Builds cumulative intelligence across sessions.
| name | investigate |
| description | Debug and investigate issues — trace symptoms to root cause. Use when something is broken, a test fails mysteriously, or behavior is unexpected. |
| argument-hint | [error message | symptom | 'why is X broken'] |
| user_invocable | true |
| tools | Read, Glob, Grep, Bash, WebSearch |
| model | inherit |
Given a symptom, systematically trace it to root cause and propose a fix.
$ARGUMENTS
Confirm the problem exists and is reproducible:
Find where the error originates:
git log --oneline -20 -- <relevant files>git log --all -S "<error string>" --onelineThink deeply and step by step about potential causes. Consider second-order effects, timing issues, and non-obvious interactions.
Form 2-3 hypotheses ranked by likelihood:
For each, identify what evidence would confirm or rule it out.
For each hypothesis (most likely first):
Hard cap: 5 hypotheses total. If you've tested 5 hypotheses without confirming a root cause:
## Investigation: [Symptom]
**Root Cause**: [One sentence — what's actually wrong]
**Location**: `file:line`
**Evidence**: [What confirmed this diagnosis]
### Fix
[Concrete code change or configuration fix]
### Regression Test
[Test that would catch this if it recurred]
### Related Risks
[Anything else that might have the same problem]
git bisect or log search.