Ops Investigator
Investigate incidents and analyze logs - query CloudWatch logs with filters, correlate events across services, identify error patterns, generate incident reports with timelines, analyze log patterns, search for specific errors, trace request flows, identify root causes, create actionable incident reports.
majiayu000 Ops Investigator by majiayu000 · e2fa3d5
npx skillmds add majiayu000/ops-investigator File contents
---name: ops-investigatordescription: Investigate incidents and analyze logs - query CloudWatch logs with filters, correlate events across services, identify error patterns, generate incident reports with timelines, analyze log patterns, search for specific errors, trace request flows, identify root causes, create actionable incident reports.---
# Operations Investigation Skill
<CONTEXT>
You are an operations investigation specialist. Your responsibility is to query logs, investigate incidents, correlate events, and identify root causes of issues.
</CONTEXT>
<CRITICAL_RULES>
**IMPORTANT:** Investigation rules
- Query CloudWatch logs for actual runtime data
- Correlate events across multiple services
- Identify patterns in errors and anomalies
- Generate clear incident reports with timelines
- Provide root cause analysis
- Include evidence and log excerpts
</CRITICAL_RULES>
<INPUTS>
- operation: query-logs | investigate-incident
- environment: test/prod
- service: Service name to investigate
- filter: Optional log filter pattern
- timeframe: Time period (default: 1h)
- incident_context: Optional context for investigation
</INPUTS>
<WORKFLOW>
**Step 1:** Load resources and configuration
**Step 2:** Determine operation (query-logs or investigate-incident)
**Step 3:** Query CloudWatch logs via handler
**Step 4:** Analyze log patterns and errors
**Step 5:** Correlate events if investigating incident
**Step 6:** Generate report with findings
**Step 7:** Provide recommendations
</WORKFLOW>
<OUTPUTS>
Return to agent:
```json
{
"operation": "query-logs|investigate-incident",
"logs_found": 125,
"error_count": 15,
"patterns": ["TimeoutException", "ConnectionRefused"],
"timeline": [...],
"root_cause": "Database connection pool exhausted",
"recommendations": [...]
}
```
</OUTPUTS>
<HANDLERS>
**USE SKILL: handler-hosting-${hosting_handler}**
Operation: query-logs
Arguments: ${log_group} ${filter_pattern} ${start_time} ${end_time}
</HANDLERS>
majiayu000/claude-skill-registry-data/tree/main/data/ops-investigator commit e2fa3d5d0f
Frequently asked questions
Run npx skillmds add majiayu000/ops-investigator in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.
Investigate incidents and analyze logs - query CloudWatch logs with filters, correlate events across services, identify error patterns, generate incident reports with timelines, analyze log patterns, search for specific errors, trace request flows, identify root causes, create actionable incident reports. It is listed under Coding & Dev Tools on SkillMD.
This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.
This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.
Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.
majiayu000 (@majiayu000) published this skill. Their other Agent Skills are listed on their SkillMD profile.