trace

Analyze agent flow with event timelines and aggregate statistics.

6|Updated Apr 26, 2026
One-click install
npx skills add https://github.com/Weihong-Liu/GenericAgent_project --skill trace-weihong-liu
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace
Source: https://github.com/Weihong-Liu/GenericAgent_project/tree/main/.codex/skills/trace
Command: npx skills add https://github.com/Weihong-Liu/GenericAgent_project --skill trace-weihong-liu

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses the need for detailed trace analysis in complex agent interactions, providing a comprehensive view of the flow and performance of hooks, keywords, skills, agents, and tools.

Core Features & Use Cases

  • Timeline Visualization: Offers a chronological view of events during the session, highlighting key interactions.
  • Aggregate Statistics: Provides a summary of statistics such as hook fires, keyword detection, skill activations, and mode transitions.
  • Use Case: Ideal for debugging and performance tuning in environments where understanding the sequence and impact of different components is crucial, such as in a large-scale AI agent system.

Quick Start

Run the 'trace' skill to display the timeline and summary of the agent flow for the current session.

Frequently Asked Questions about trace

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

FAQPage Schema
How do I debug agent flow and visualize event timelines in complex AI interactions?

To debug agent flow, you trace the chronological event timeline to visualize hook fires, keyword detection, and skill activations during a session. This provides a chronological view of interactions to pinpoint sequence issues.

What is agent flow trace analysis and when do I need it for performance tuning?

Agent flow trace analysis is the examination of chronological events and aggregate statistics on hook fires and mode transitions. You need it for performance tuning and troubleshooting when understanding the sequence and impact of components in large-scale AI agent systems is crucial.

Can I get aggregate statistics on hook fires and skill activations for my current session?

Yes, you can get aggregate statistics on hook fires, keyword detection, skill activations, and mode transitions. Running a trace provides a summary of these statistics to help troubleshoot and optimize performance for the current session.

Does agent flow tracing require any external dependencies or environment setup?

Agent flow tracing requires no external dependencies or environment setup. It is designed to run directly within your current session to analyze the flow and performance of hooks, keywords, skills, agents, and tools without prerequisites.

What is the best way to analyze mode transitions and keyword detection in a large-scale AI agent system?

The best way to analyze mode transitions and keyword detection is to review aggregate statistics and timeline visualizations. This approach highlights the sequence and impact of different components, which is crucial for troubleshooting complex AI agent interactions.