observability-debugger

Query SQLite events, incidents, and runtime snapshots to debug Cradle observability data.

54|7|Updated May 29, 2026
One-click install
npx skills add https://github.com/wibus-wee/cradle-app --skill observability-debugger
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: observability-debugger
Source: https://github.com/wibus-wee/cradle-app/tree/main/resources/skills/observability-debugger
Command: npx skills add https://github.com/wibus-wee/cradle-app --skill observability-debugger

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill enables the debugging of Cradle's observability data, including querying SQLite events, incidents, timelines, runtime snapshots, metrics, and server logs, to identify and address unexpected chat turn behaviors.

Core Features & Use Cases

  • Event Querying: Query and analyze structured error/warn/info events from Cradle's observability_events table.
  • Incident Analysis: Analyze deduplicated grouped events for patterns and causes.
  • Snapshot Examination: Inspect runtime snapshots and events for a deep understanding of chat run phases.
  • Live Runtime Resources: Review live server/runtime resource views for health, active runs, buffers, and more.
  • Metrics Trend Analysis: Use OpenTelemetry metrics for trend and correlation evidence during debugging.
  • Server Logs Inspection: Read pino-structured JSON logs for detailed information on server processes.
  • Use Case: If a chat turn fails unexpectedly, use this Skill to query events, incidents, and runtime snapshots to gather evidence for debugging.

Quick Start

Use the observability-debugger skill to list recent observability events.

Frequently Asked Questions about observability-debugger

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

FAQPage Schema
How do I debug unexpected chat turn behaviors using observability data?

Debug unexpected chat turn behaviors by querying SQLite observability events, incidents, and runtime snapshots to gather evidence. You can analyze structured error events and inspect runtime states to identify the root cause of the failure.

What is the best way to analyze system health and runtime resources during a chat run?

Review live server runtime resource views to monitor system health, active runs, and buffers. Combine this with OpenTelemetry metrics trend analysis to find correlations and evidence during debugging.

How do I query structured events from the observability_events table?

Query the observability_events table to retrieve structured error, warning, and info events. Analyze these events to identify patterns and causes within the chat management platform.

Can I inspect pino-structured server logs for detailed process information?

Yes, you can read pino-structured JSON server logs to inspect detailed information on server processes. This helps correlate server-side issues with runtime snapshots and observability events.

Does this debugging approach work with OpenTelemetry metrics for trend analysis?

Yes, OpenTelemetry metrics are used for trend and correlation evidence during debugging. This allows you to visualize runtime performance and correlate it with incidents from the observability data.