skills.rest
sjanulonoks
sjanulonoksCOMMUNITY
Explore all skills by this author →
GitHub

o11y-assistant

Manage cloud and AI resources from your command line with unified workflows and automated provisioning across multiple providers.

Updated Feb 28, 2026
Search Tags:#monitoring#logs#metrics#observability#traces#root-cause-analysis#incident
One-click install
npx skills add https://github.com/sjanulonoks/o11y --skill o11y-assistant
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: o11y-assistant
Source: https://github.com/sjanulonoks/o11y/tree/main/skills/o11y-assistant
Command: npx skills add https://github.com/sjanulonoks/o11y --skill o11y-assistant

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

ALWAYS USE when investigating incidents, checking system health, exploring services, validating hypotheses, or querying ANY observability backend (Prometheus/Mimir, Loki, Tempo, CloudWatch, ClickHouse, or any Grafana-connected datasource).

Core Features & Use Cases

  • Unified, autonomous investigation workflow across metrics, logs, traces, and alerts.
  • Evidence-based root-cause analysis with step-by-step guidance from Step 0 to Step 8.
  • Trigger-aware responses that integrate with backends and annotations to speed resolution.

Quick Start

Describe the incident and I will begin the Step 0–8 investigation.

Frequently Asked Questions about o11y-assistant

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I investigate incidents by correlating metrics, logs, and traces?▼

Incident investigation across metrics, logs, and traces requires querying observability backends and applying evidence-based reasoning. You can autonomously query connected sources like Prometheus, Loki, Tempo, and CloudWatch to execute a Step 0 to Step 8 root-cause analysis workflow.

What is the best way to perform root-cause analysis for SLO breaches?▼

Root-cause analysis for SLO breaches is handled by querying alerts and assessing system health across connected backends. This skill triggers an autonomous, sequential investigation workflow to validate hypotheses and pinpoint degradations.

Does this observability investigation workflow work with Grafana-connected datasources?▼

Yes, this observability investigation workflow supports any Grafana-connected datasource. It queries metrics, logs, traces, and alerts across backends like Mimir, ClickHouse, and CloudWatch to assess system health and resolve incidents.

Can I use autonomous observability investigations to check system health?▼

You can use autonomous observability investigations to check system health by exploring services and validating hypotheses. The skill applies front-matter-driven discovery to query observability backends and assess degradations or incidents.

How do I start an investigation when an incident or degradation occurs?▼

To start an investigation when an incident or degradation occurs, describe the incident to the skill. It will begin a Step 0 to Step 8 sequential investigation, querying relevant alerts, metrics, traces, and logs across supported backends.

Related Skills

Explore More Data & Analytics Skills→
cskirocskiro
7

otel-monitoring-setup

Automate OpenTelemetry monitoring setup for Claude Code telemetry with Docker Compose and Grafana.

Community
Advanced
abzhawabzhaw

incident-response

Apply a 7-step incident lifecycle to remediate Julia's sentinel security findings.

Community
Advanced
cosmixcosmix
53

grafana

Configures Grafana-based observability dashboards with the LGTM stack, including RBAC and alerting for logs, traces, and metrics.

Community
Advanced
devendrapratapsinghdevendrapratapsingh
1

debugger

Diagnose distributed system failures through log analysis and distributed tracing.

Community
Advanced