菜单
Generate a blameless incident postmortem from the current or recent SRE Agent investigation. Use after an incident is resolved, when asked for a postmortem, RCA report, or lessons learned document.
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。
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。
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。
直接命令不会经过审查 Prompt；运行前请先检查来源。
npx skills add https://github.com/Azure/sre-agent-plugins --skill incident-postmortem-generator命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地？可下载 SkillsMP 当前能够提供的文件。
Assess security, reliability, and cost posture of Azure OpenAI and AI Foundry deployments. Detects anti-patterns like API keys instead of Managed Identity, public endpoints, disabled content filtering, deprecated models, over-provisioned PTU, missing AI Gateway, and single-region deployment.
Assess Azure resource capacity, quota utilization, and growth trends to prevent outages from resource exhaustion. Use when asked about capacity, quotas, scaling readiness, load testing prep, or growth projections.
Audit Azure environment for compliance and governance posture. Checks Azure Policy, RBAC, tagging, resource locks, naming conventions, and regulatory alignment. Use when asked about compliance, governance, audit readiness, or policy violations.
正在显示 SKILL.md
| name | incident_postmortem_generator |
| description | Generate a blameless incident postmortem from the current or recent SRE Agent investigation. Use after an incident is resolved, when asked for a postmortem, RCA report, or lessons learned document. |
Automatically generate a structured, blameless postmortem document from the context of a resolved incident investigation.
From the current conversation and agent memory, extract:
| Metric | Description |
|---|---|
| Time to detect (TTD) | Issue start to alert firing |
| Time to acknowledge (TTA) | Alert to human engagement |
| Time to mitigate (TTM) | Engagement to mitigation |
| Time to resolve (TTR) | Total duration |
Apply the 5 Whys technique to the root cause to identify systemic issues.
For each finding, create a SMART action item with owner, priority, and due date. Categories: prevent recurrence, improve detection, improve response, improve resilience.
Generate the full document with: executive summary, impact, timeline, root cause, Five Whys, detection assessment, what went well, what could be improved, action items, and lessons learned.
| Field | Value |
|---|---|
| Incident Date | 2026-07-10 |
| Severity | Sev-2 |
| Duration | 1h 23m |
Summary: payment-service returned HTTP 500 errors for 1h 23m due to OOM-killed pod. Root cause: memory leak in connection pool from release v2.14.0. Impact: ~340 failed transactions, 120 customers.
| Metric | Value | Target | Status |
|---|---|---|---|
| TTD | 6m | <5m | ⚠️ |
| TTA | 4m | <15m | ✅ |
| TTM | 28m | <30m | ✅ |
| TTR | 1h 23m | <2h | ✅ |
