Agent Skills › anthropics/cwc-workshops › incident-triage-runbook

incident-triage-runbook

GitHub

SRE生产事故排查手册，指导处理延迟和错误率异常。按顺序检查部署、指标关联、代码变更及日志，识别常见故障模式并生成根因摘要，辅助快速定位问题。

ship-your-first-managed-agent/incident-triage-runbook/SKILL.md anthropics/cwc-workshops

Trigger Scenarios

调查线上事故分析延迟飙升错误率升高询问服务异常原因

Install

npx skills add anthropics/cwc-workshops --skill incident-triage-runbook -g -y

More Options

Non-standard path

npx skills add https://github.com/anthropics/cwc-workshops/tree/main/ship-your-first-managed-agent/incident-triage-runbook -g -y

Use without installing

npx skills use anthropics/cwc-workshops@incident-triage-runbook

指定 Agent (Claude Code)

npx skills add anthropics/cwc-workshops --skill incident-triage-runbook -a claude-code -g -y

安装 repo 全部 skill

npx skills add anthropics/cwc-workshops --all -g -y

预览 repo 内 skill

npx skills add anthropics/cwc-workshops --list

SKILL.md

Frontmatter

{
    "name": "incident-triage-runbook",
    "description": "The SRE team's runbook for triaging production latency and error-rate incidents. Use this whenever investigating an incident, a latency spike, elevated error rates, or when asked \"what caused X\" about a production service."
}

Incident triage

If you change the order below, say why in #sre.

Order of operations

Pull deploys for the last 6h. Don't open the log first.
Line the deploy timestamps up against p99_latency_ms / error_rate for the paged service. State the gap ("deploy 14:31, p99 moves 14:33").
If a deploy lines up: pull the diff, read it. Check for the stuff in the next section.
Then grep the log to confirm. Don't grep to fish.
No deploy lines up → check db_pool_utilization across checkout/cart/auth/inventory, then upstream deps.