trace

Visualize agent flow traces and summaries to diagnose execution paths.

6|1|Updated Apr 16, 2026
One-click install
npx skills add https://github.com/Goblin1024/oh-my-kimi --skill trace-goblin1024
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: trace
Source: https://github.com/Goblin1024/oh-my-kimi/tree/main/skills/trace
Command: npx skills add https://github.com/Goblin1024/oh-my-kimi --skill trace-goblin1024

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provide real-time visualization of how hooks, keywords, skills, agents, and tools interact, enabling quick debugging and performance analysis of Kimi Code workflows.

Core Features & Use Cases

  • Timeline visualization: display the chronological sequence of events in a session.
  • Summary metrics: present aggregated counts for hooks fired, keywords detected, skills activated, mode transitions, and tool performance.
  • Use Case: debugging a failing session by tracing the flow from keyword detection to agent actions and identifying bottlenecks.

Quick Start

Run trace_timeline with no arguments to view the latest session timeline, then run trace_summary to view the aggregate statistics.

Frequently Asked Questions about trace

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

FAQPage Schema
How do I visualize agent execution paths to debug performance bottlenecks?

You can visualize agent execution paths by generating a timeline of chronological events and a summary of aggregate statistics to debug performance bottlenecks. This reveals mode transitions and flow patterns across sessions.

What is the best way to trace hook and keyword interactions within a workflow?

To trace hook and keyword interactions, run a timeline visualization tool that displays the chronological sequence of events in a session. This tracks how hooks fired and keywords detected connect to subsequent agent actions.

How does a timeline summary help diagnose mode transitions and tool performance?

A timeline summary diagnoses mode transitions and tool performance by presenting aggregated counts for hooks fired, keywords detected, skills activated, and tool performance metrics, highlighting bottlenecks and flow patterns.

Do I need specific MCP tools to trace workflow execution and aggregate metrics?

Yes, you need the trace_timeline and trace_summary MCP tools to trace workflow execution and aggregate metrics. These tools output the chronological event timeline followed by the aggregate session statistics.

Can I review the latest session flow without manually configuring trace arguments?

Yes, you can review the latest session flow without configuring arguments by running the trace timeline tool with no parameters. Follow this by running the summary tool to view aggregated session statistics.

Why does my workflow session fail to generate a chronological execution timeline?

A workflow session fails to generate a chronological execution timeline if the required MCP tools are unavailable. Ensure these tools are active to output the timeline and summary with mode transitions and bottlenecks.