tsuga-investigate-errors

Count error events, cluster patterns, and detect anomalous increases for a service.

2|Updated May 28, 2026
One-click install
npx skills add https://github.com/tsuga-dev/agent-plugins --skill tsuga-investigate-errors
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tsuga-investigate-errors
Source: https://github.com/tsuga-dev/agent-plugins/tree/main/plugins/tsuga/skills/tsuga-investigate-errors
Command: npx skills add https://github.com/tsuga-dev/agent-plugins --skill tsuga-investigate-errors

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill helps you quickly determine what is failing for a specific service by measuring error volume, clustering error structures, and identifying anomalous error-pattern increases within a time window.

Core Features & Use Cases

  • Authoritative error counting: Uses an aggregation scalar to confirm whether errors are elevated in a specified time range, avoiding false assumptions from log presence.
  • Pattern-based error clustering: Groups error occurrences by structure using log pattern clustering to summarize likely causes and variants.
  • Anomaly detection for error patterns: Detects which clustered error patterns show anomalous volume changes for a team over time, so you can prioritize investigation.
  • Safe log sampling for structure: Extracts key fields (message templates, filenames, targets) from a limited number of matches for structure analysis without dumping raw log lines.

Quick Start

Ask the AI to investigate errors for service "checkout-api" over the last 2 hours and return the elevated error count, dominant error patterns, and recommended next actions.

Frequently Asked Questions about tsuga-investigate-errors

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

FAQPage Schema
How do I investigate error spikes and find the root cause for a specific service?

Error pattern clustering groups error occurrences by their structural similarities using log pattern clustering. This summarizes likely causes and variants, helping you quickly identify dominant error structures during operational incident triage.

How do I count error events to confirm if service errors are actually elevated?

You confirm elevated service errors by using an aggregation scalar to count error events in a specified time range. This authoritative error counting avoids false assumptions that can arise from merely seeing logs present.

Can I use this for operational incident triage across specific environments?

Yes, this applies to operational incident triage, error spike alerts, and exception pattern analysis across specific services and environments. It detects anomalous error-pattern volume changes over time to help prioritize investigation.

How does error pattern clustering work for log analytics?

Error pattern clustering groups error occurrences by their structural similarities using log pattern clustering. This summarizes likely causes and variants, helping you quickly identify dominant error structures during operational incident triage.

Does error investigation extract or dump raw log lines when sampling logs?

Safe log sampling extracts key fields like message templates, filenames, and targets from a limited number of matches for structure analysis. It applies safety safeguards to avoid dumping raw log lines and exposing sensitive records.