skills.rest
mqzkim
mqzkimCOMMUNITY
Explore all skills by this author →
GitHub

agent-debugger

Visualize execution flows, replay sessions, and detect loops in AI agent debugging.

Updated Mar 1, 2026
Search Tags:#debugging#ai agents#langgraph#performance analysis#crewai#session replay#autogen
One-click install
npx skills add https://github.com/mqzkim/trading --skill agent-debugger
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-debugger
Source: https://github.com/mqzkim/trading/tree/main/.agents/skills/agent-debugger
Command: npx skills add https://github.com/mqzkim/trading --skill agent-debugger

SYSTEM DOCUMENTATION & REQUIREMENTS

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

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'.

Frequently Asked Questions about agent-debugger

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

FAQPage Schema
How do I debug an infinite loop in a multi-agent system?▼

To debug an infinite loop in a multi-agent system, this Skill provides automatic self-correction loop detection to identify and report redundant cycles. You can interactively replay the session to analyze the agent's decision-making process and pinpoint the exact failure.

What is the best way to visualize execution flow for AI agents?▼

Visualizing execution flow for AI agents involves mapping the step-by-step process of agent decisions and actions. This Skill generates interactive debugging interfaces that display execution paths and multi-agent communication topology.

Can I replay a LangGraph session step by step to find errors?▼

You can replay a LangGraph session step by step using the interactive session replay feature. This allows you to step through the execution flow to pinpoint errors and analyze performance metrics at each stage.

Does this tool support cost attribution and performance analysis for CrewAI?▼

This tool supports detailed performance analysis and cost attribution for CrewAI sessions. It helps identify errors and track resource consumption by analyzing comparative session metrics across agent interactions.

How do I compare two AI agent sessions to check for performance regressions?▼

Comparing two AI agent sessions to check for performance regressions is done through comparative session metrics. This feature contrasts execution flows and resource usage to identify improvements or degradations between runs.

Related Skills

Explore More Software Engineering Skills→
oabdelmaksoudoabdelmaksoud
3

agi-farm

Automate multi-agent AI team setup and deployment on OpenClaw.

Community
Advanced
minicooheiminicoohei
345

agent-designer

Designs multi-agent architectures and strategies for scalable AI systems.

Community
Advanced
googlegoogle
68

dev-session-debug

Diagnose and repair inconsistencies in Capsem session telemetry data.

Official
Intermediate
Himanshu040604Himanshu040604

sentry-react-native-sdk

Integrate Sentry SDK for error monitoring, performance tracing, and session replay in React Native and Expo apps.

Community
Intermediate