What data source does this skill use?

It primarily analyzes telemetry data stored in Loki under the job label 'claude_code_enhanced'.

Can it identify why my Claude Code sessions are slow?

Yes, it includes a detect-slowness function that flags large response patterns (over 100k characters) and groups them by tool to find bottlenecks.

How does it help with context window management?

The skill monitors context-compact events to identify frequent auto-compactions and high-utilization sessions that might require task splitting.

What kind of inefficiencies can it detect?

It identifies 'waste' patterns such as multiple reads of the same file, redundant glob operations, and repeated failed tool calls.

Does it provide project-level insights?

Yes, the detect-repo-patterns operation provides activity metrics, error rates, and tool usage distribution across different repositories.

Observability Pattern Detector

Name: Observability Pattern Detector
Author: adaptationio

byadaptationio

0•

Analytics & Monitoring

Analyzes Claude Code telemetry data to identify performance bottlenecks, error patterns, and workflow inefficiencies.

The Observability Pattern Detector is a specialized skill designed to transform raw Claude Code telemetry into actionable insights. By processing enhanced logs from Loki, it automatically identifies recurring failure signatures, detects statistical anomalies in session behavior, and highlights inefficient tool sequences. It is an essential tool for developers looking to optimize their AI-driven workflows, providing deep visibility into context window management, subagent performance, and repository-level activity trends.

Key Features

01Inefficiency identification for redundant tool operations

020 GitHub stars

03Long-term trend analysis for tool usage and error rates

04Automated failure grouping and impact ranking

05Detailed context window and auto-compaction monitoring

06Statistical anomaly detection for sessions and turn counts

Use Cases

01Auditing tool usage sequences to reduce token waste and improve subagent orchestration

02Debugging recurring tool failures and identifying root causes in automated workflows

03Optimizing Claude Code performance by identifying slow operations and oversized response patterns

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add adaptationio/skrillz observability-pattern-detector

For use in Claude.ai and ChatGPT

Key Features

01Inefficiency identification for redundant tool operations

020 GitHub stars

03Long-term trend analysis for tool usage and error rates

04Automated failure grouping and impact ranking

05Detailed context window and auto-compaction monitoring

06Statistical anomaly detection for sessions and turn counts

Use Cases

01Auditing tool usage sequences to reduce token waste and improve subagent orchestration

02Debugging recurring tool failures and identifying root causes in automated workflows

03Optimizing Claude Code performance by identifying slow operations and oversized response patterns

What are Skills?·How to Install

Install with 🐟 Skill.Fish

npx skillfish add adaptationio/skrillz observability-pattern-detector

For use in Claude.ai and ChatGPT