Menü
Investigate production-like failures from symptoms, logs, and reproduction steps.
Mit Codex oder Claude installieren Kopieren Sie diesen Prompt, fügen Sie ihn in Codex, Claude oder einen anderen Assistant ein und lassen Sie die Skill-Seite prüfen und installieren.
Basierend auf der SOC-Berufsklassifikation
Guided git commit workflow — review changes, draft message, stage, commit
Manage context pressure during large codebase work without losing critical state.
Create a pull request with structured summary and test plan
Interactive debugging — reproduce, isolate, trace, fix
Explore a codebase or directory to understand its structure and purpose
Implement a requested code change end-to-end with scoped edits and verification.
| name | incident |
| description | Investigate production-like failures from symptoms, logs, and reproduction steps. |
| when_to_use | Use when behavior is intermittent, channel-specific, timing-sensitive, or observed in logs. |
| required_tools | ["bash","symbol_search"] |
| tags | ["debug","incident"] |
| activation | {"input_patterns":["(?i)(incident|outage|logs|timeout|丢消息|超时|日志|故障)"]} |
${ARGS}
Establish exact user-visible symptoms, timestamps, affected clients, and expected behavior.
Read logs and persisted session state before changing code. Separate transport failure, runtime failure, provider failure, and rendering failure.
Create the smallest repeatable scenario. If intermittent, identify timing windows and retry boundaries.
Patch the owning layer, not the symptom. Add regression coverage or an operational check where possible.
Report root cause, fix, verification, and any remaining monitoring gap.
