菜单
AI-powered incident triage for PagerDuty. List active incidents, deep-dive with timeline and alert correlation, check on-call schedules, acknowledge, resolve, and annotate — all from your agent. Read-only by default; write operations require explicit --confirm.
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/javimosch/open-claw-skills --skill pager-triage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。
基于 SOC 职业分类
正在显示 SKILL.md
| name | pager-triage |
| version | 0.1.1 |
| displayName | PagerDuty Incident Triage |
| description | AI-powered incident triage for PagerDuty. List active incidents, deep-dive with timeline and alert correlation, check on-call schedules, acknowledge, resolve, and annotate — all from your agent. Read-only by default; write operations require explicit --confirm. |
| author | Anvil AI |
| tags | ["pagerduty","opsgenie","incident","sre","oncall","triage","discord","discord-v2"] |
| tools | [{"name":"pd_incidents","description":"List active PagerDuty incidents (triggered + acknowledged)"},{"name":"pd_incident_detail","description":"Get detailed incident info including timeline, alerts, and notes"},{"name":"pd_oncall","description":"Show current on-call schedules and escalation policies"},{"name":"pd_incident_ack","description":"Acknowledge an incident (requires --confirm)"},{"name":"pd_incident_resolve","description":"Resolve an incident (requires --confirm)"},{"name":"pd_incident_note","description":"Add a note to an incident (requires --confirm)"},{"name":"pd_services","description":"List PagerDuty services and their current status"},{"name":"pd_recent","description":"Show recent incidents for a service (last 24h/7d/30d)"}] |
AI-powered incident triage for PagerDuty. Read-only by default. Write operations require explicit confirmation.
Use this skill when the user:
OpenClaw Agent# Required — your PagerDuty REST API v2 token
export PAGERDUTY_API_KEY="u+your_key_here"
# Optional — required only for write operations (ack, resolve, note)
export PAGERDUTY_EMAIL="you@company.com"
Ask your agent: "What's firing on PagerDuty?"
incidents — List Active IncidentsLists all triggered and acknowledged incidents, sorted by urgency.
pager-triage incidents
Example output:
{
"tool": "pd_incidents",
"provider": "pagerduty",
"timestamp": "2026-02-16T03:45:00Z",
"total_incidents": 3,
"incidents": [
{
"id": "P123ABC",
"incident_number": 4521,
"title": "High CPU on prod-web-03",
"status": "triggered",
"urgency": "high",
"service": { "id": "PSVC123", "name": "Production Web" },
"created_at": "2026-02-16T03:00:00Z",
"assignments": [{ "name": "Jane Doe", "email": "..." }],
"alert_count": 3,
"escalation_level": 1,
"last_status_change": "2026-02-16T03:05:00Z"
}
],
"summary": "3 active incident(s): high (triggered) x1, high (acknowledged) x1, low (triggered) x1"
}
detail <incident_id> — Incident Deep DiveFull incident details including timeline (log entries), related alerts, notes, and automated analysis.
pager-triage detail P123ABC
Example output (abbreviated):
{
"tool": "pd_incident_detail",
"incident": {
"id": "P123ABC",
"title": "High CPU on prod-web-03",
"status": "triggered",
"urgency": "high",
"service": { "id": "PSVC123", "name": "Production Web" },
"escalation_policy": { "name": "Production Escalation" },
"assignments": [{ "name": "Jane Doe", "escalation_level": 1 }]
}
oncall — On-Call SchedulesShows who's currently on call across all schedules and escalation policies.
pager-triage oncall
Example output:
{
"tool": "pd_oncall",
"oncalls": [
{
"user": { "name": "Jane Doe", "email": "jane@company.com" },
"schedule": { "name": "Primary SRE", "id": "PSCHED1" },
"escalation_policy": { "name": "Production Escalation" },
"escalation_level": 1,
"start": "2026-02-15T17:00:00Z",
"end": "2026-02-16T17:00:00Z"
}
],
"summary": "2 on-call assignment(s). Primary SRE: Jane Doe. Secondary SRE: Bob Smith."
services — List ServicesLists all PagerDuty services with their current operational status.
pager-triage services
Example output:
{
"tool": "pd_services",
"services": [
{
"id": "PSVC123",
"name": "Production Web",
"status": "critical",
"description": "Production web application servers",
"escalation_policy": "Production Escalation",
"integrations": ["Prometheus Alertmanager", "CloudWatch"]
}
],
"summary": "12 services: 1 critical, 1 warning, 10 active, 0 disabled"
}
recent — Recent Incident HistoryShows recent incidents for a service or across all services with summary statistics.
pager-triage recent # All services, last 24h
pager-triage recent --service PSVC123 # Specific service
pager-triage recent --since 7d # Last 7 days
pager-triage recent --service PSVC123 --since 30d
Flags:
| Flag | Default | Description |
|---|---|---|
--service <id> | all | Filter to a specific PagerDuty service ID |
--since <window> | 24h | Time window: 24h, 7d, or 30d |
Example output:
{
"tool": "pd_recent",
"period": "last 24 hours",
"service": "PSVC123",
"incidents": [ ... ],
"stats": {
"total": 5,
"by_urgency": { "high": 2, "low": 3 },
"by_status": { "resolved": 4, "triggered": 1 },
"mean_time_to_resolve_minutes": 42
}
}
--confirm)These operations modify state in PagerDuty. They require the --confirm flag AND PAGERDUTY_EMAIL to be set. Without --confirm, the tool displays what it would do and exits.
ack <incident_id> --confirm — Acknowledge IncidentAcknowledges a triggered incident, stopping further escalation.
pager-triage ack P123ABC --confirm
Without --confirm, displays:
{
"error": "confirmation_required",
"message": "⚠️ ACKNOWLEDGE INCIDENT — --confirm flag is required to proceed.",
"incident": { "id": "P123ABC", "title": "High CPU on prod-web-03", "urgency": "high" },
"hint": "Re-run with --confirm to acknowledge this incident."
}
With --confirm:
{
"tool": "pd_incident_ack",
"incident_id": "P123ABC",
"status": "acknowledged",
"acknowledged_at": "2026-02-16T03:46:00Z",
"acknowledged_by": "jane@company.com"
}
resolve <incident_id> --confirm — Resolve IncidentResolves an incident, marking it as fixed.
pager-triage resolve P123ABC --confirm
Same confirmation pattern as ack. Without --confirm, shows incident details and exits. With --confirm, resolves and returns confirmation JSON.
note <incident_id> --content "text" --confirm — Add Incident NoteAdds a permanent note to an incident's timeline.
pager-triage note P123ABC --content "Root cause: memory leak in auth-service v2.14.3. Rolling back." --confirm
Flags:
| Flag | Required | Description |
|---|---|---|
--content <text> | Yes | The note text to add |
--confirm | Yes | Confirmation gate |
Example output:
{
"tool": "pd_incident_note",
"incident_id": "P123ABC",
"note_id": "PNOTE456",
"content": "Root cause: memory leak in auth-service v2.14.3. Rolling back.",
"created_at": "2026-02-16T04:00:00Z",
"user": "Jane Doe"
}
When the user needs help triaging an incident, follow this workflow:
→ pager-triage incidents
List all active incidents. Prioritize by urgency (high first) and duration (oldest first).
→ pager-triage detail <incident_id>
Get full timeline, alerts, and notes. Identify the trigger source and escalation history.
If available, use companion skills to investigate root cause:
→ pager-triage ack <incident_id> --confirm # Stop escalation while investigating
→ pager-triage note <incident_id> --content "..." --confirm # Document findings
→ pager-triage resolve <incident_id> --confirm # Mark as fixed
incidentsdetailWhen the conversation is happening in a Discord channel:
Deep Dive IncidentAcknowledge IncidentAdd Incident Note--confirm--confirmOpsGenie integration is planned for a future release. When OPSGENIE_API_KEY is set, the same subcommands will map to OpsGenie's REST API with normalized output schemas.
Powered by Anvil AI · Built for the engineer who gets paged at 3am