agent-debugger

Community

Debug AI agent sessions

Authormqzkim
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill helps developers and AI engineers diagnose and fix issues within AI agent sessions by providing tools for visualizing execution flows, replaying sessions, detecting problematic loops, and analyzing multi-agent interactions.

Core Features & Use Cases

  • Visualize Execution Flow: Understand the step-by-step process of an agent's execution.
  • Session Replay: Step through a session interactively to pinpoint errors.
  • Loop Detection: Automatically identify and report infinite or redundant loops.
  • Topology Analysis: Visualize communication patterns between multiple agents.
  • Session Comparison: Compare two sessions to identify performance improvements or regressions.
  • Use Case: Debug a complex multi-agent system that is unexpectedly looping or consuming excessive resources by replaying its execution and analyzing its decision-making process.

Quick Start

Use the agent-debugger skill to replay session 'session_abc123'.

Dependency Matrix

Required Modules

None required

Components

scriptsreferencesassets

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: agent-debugger
Download link: https://github.com/mqzkim/trading/archive/main.zip#agent-debugger

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 223,000+ vetted skills library on demand.