skills.rest
zmh13928433602-sys
zmh13928433602-sysCOMMUNITY
Explore all skills by this author →
GitHub

agent-tracing

Inspect agent execution snapshots to debug step-by-step LLM interactions.

Updated May 11, 2026
Search Tags:#cli#llm#debug#trace#agent-tracing#context-engine#execution-snapshots
One-click install
npx skills add https://github.com/zmh13928433602-sys/lobe-chat --skill agent-tracing-zmh13928433602-sys
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: agent-tracing
Source: https://github.com/zmh13928433602-sys/lobe-chat/tree/main/.agents/skills/agent-tracing
Command: npx skills add https://github.com/zmh13928433602-sys/lobe-chat --skill agent-tracing-zmh13928433602-sys

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Agent tracing CLI provides a dedicated workflow to observe and analyze agent execution snapshots, making it easier to debug LLM calls, inspect the context engine data, and understand step-by-step behavior.

Core Features & Use Cases

  • Collects and stores execution snapshots to disk during development
  • Exposes a CLI to inspect traces, steps, messages, context, and tool calls
  • Supports viewing in-progress partials and final completed snapshots for audit and debugging

Quick Start

Trigger agent-tracing to inspect the latest trace and drill into step-level details.

Frequently Asked Questions about agent-tracing

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

FAQPage Schema
How do I debug LLM agent executions step by step?▼

Debug LLM agent executions by collecting execution snapshots to disk and using a CLI to inspect traces, steps, messages, context data, and tool calls step by step.

What is agent tracing and when do I need it for LLM workflows?▼

Agent tracing is the process of observing and analyzing agent execution snapshots to debug LLM calls and inspect context engine data. You need it when debugging multi-step agent runs and tool usage behaviors.

How do I inspect in-progress partials and completed agent traces?▼

Inspect in-progress partials and completed agent traces by triggering the CLI to view the latest trace, then drilling into step-level details to audit stored execution snapshots on disk.

Can I trace context engine data and tool calls across multi-step agent runs?▼

Yes, you can trace context engine data and tool calls across multi-step agent runs. The CLI exposes structured snapshot data to inspect step histories, messages, and tool usage for debugging workflows.

Do I need external dependencies to inspect agent execution snapshots?▼

No external dependencies are required. The agent tracing tool provides a self-contained CLI with structured snapshot data and a guided inspection workflow for analyzing LLM interactions.

Related Skills

Explore More Software Engineering Skills→
duwenjiduwenji

agent-tracing

Inspect JSON execution snapshots and step-level traces from .agent-tracing.

Community
Advanced
PostHogPostHog
58

exploring-llm-traces

Analyze MCP-captured LLM agent traces from PostHog URLs or JSON exports.

Official
Advanced
alceupassosalceupassos

agent-tracing

Record and inspect AI agent execution snapshots with a CLI tool.

Community
Intermediate
agentuityagentuity
1

agentuity-cli-cloud-sandbox-snapshot-get

Retrieve structured JSON details for a specific cloud sandbox snapshot.

Official
Intermediate