Automate your SRE and incident response workflows with AI-powered PagerDuty triage and management.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install pager-triage
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install pager-triage using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is PagerDuty Incident Triage?
The PagerDuty Incident Triage skill transforms your AI agent into a high-efficiency first-responder for system outages and alerts. By integrating directly with the PagerDuty REST API v2, this addition to your library of Openclaw Skills allows engineers to query active incidents, investigate alert timelines, and monitor service health through natural language commands. It is designed to bridge the gap between receiving a page and taking action by providing a centralized interface for all incident data.
Security is a core pillar of this skill. It operates in a read-only mode by default, ensuring that sensitive write operations—such as acknowledging or resolving incidents—require explicit human confirmation and the presence of a validated user email. This makes it a safe and reliable choice for teams looking to leverage Openclaw Skills within their production environments without compromising operational integrity.
PagerDuty Incident Triage Use Cases
- Identifying high-priority incidents currently firing in production.
- Checking on-call schedules to see which engineer is responsible for an escalation policy.
- Reviewing the recent history of a specific service to identify recurring patterns or flapping alerts.
- Performing rapid triage by acknowledging incidents and adding diagnostic notes to the timeline.
- Summarizing service health and operational status across the entire organization.
How PagerDuty Incident Triage Works
- Assess: The agent uses the incidents tool to list all active triggered and acknowledged alerts, sorted by urgency.
- Deep-Dive: A specific incident ID is analyzed to retrieve a full timeline, including alert correlations and log entries.
- Correlate: The agent suggests using other Openclaw Skills, such as Prometheus or Kubernetes tools, to find the root cause.
- Act: If authorized, the user provides a confirmation flag to acknowledge, resolve, or annotate the incident in PagerDuty.
PagerDuty Incident Triage Setup
1. Generate PagerDuty API Key
Navigate to PagerDuty → Settings → API Access Keys and create a new key. Read-only access is recommended for initial setup.
2. Configure Environment Variables
Export the required credentials to your environment to enable the skill:
# Required: Your PagerDuty REST API v2 token
export PAGERDUTY_API_KEY="your_key_here"
# Optional: Required only for ack, resolve, and note operations
export PAGERDUTY_EMAIL="[email protected]"
3. Verification
Test the connection by asking the agent: "What is currently firing on PagerDuty?"
PagerDuty Incident Triage Data Schema & Taxonomy
The skill returns structured JSON responses that normalize PagerDuty API data for easy consumption by AI agents and humans alike.
| Component | Description |
|---|---|
| Incident Object | Contains ID, status, urgency, service mapping, and assignment details. |
| Timeline | A chronological list of log entries, including triggers, escalations, and user actions. |
| On-Call | Details regarding the user, schedule name, and escalation level currently active. |
| Stats | Summary metrics including total incident counts and Mean Time to Resolve (MTTR) for specific windows. |
PagerDuty Incident Triage Advanced Features
- Discord v2 Delivery Mode: Automatically formats responses for Discord with compact summaries and suggested interactive follow-ups.
- Confirmation Gates: Mandatory --confirm flag prevents accidental state changes in PagerDuty during the triage process.
- Service Health Aggregation: Provides a high-level summary of service statuses (Critical, Warning, Active) across the platform.
- Historical Windows: Support for retrieving and analyzing incident data over 24-hour, 7-day, and 30-day periods.
SKILL.md
Loading
Related Openclaw Skills
Meeting Autopilot
An operational AI skill that converts meeting transcripts into structured outputs including action items, decisions, and ready-to-send email drafts.
Log Dive
A unified log search engine that translates natural language queries into LogQL, ES DSL, or CloudWatch filter patterns across multiple backends.
kube-medic
A powerful Kubernetes diagnostic toolkit for instant AI-driven cluster triage and incident response using standard kubectl commands.
Feed Diet
Analyze and optimize your Hacker News and RSS consumption with AI-generated reports and personalized digests.
prom-query
A comprehensive bridge between natural language and Prometheus-compatible metrics servers for real-time monitoring and incident triage.
rug-checker
An automated on-chain security auditor for Solana tokens that detects rug-pull risks without requiring API keys or wallet connections.
METADATA
Featured*
