Provides a chronological timeline and statistical summary of agent events, skills, and tool usage.
Install
mkdir -p .claude/skills/trace-yangyuan-zhen && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/17507" && unzip -o skill.zip -d .claude/skills/trace-yangyuan-zhen && rm skill.zipInstalls to .claude/skills/trace-yangyuan-zhen
Activation
This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.
[OMX] Show agent flow trace timeline and summaryKey capabilities
- →Display a chronological event timeline of agent interactions
- →Filter timeline events by type (hooks, skills, agents, keywords, tools, modes)
- →Show aggregate statistics for hook fire counts and keywords detected
- →Identify mode transitions in agent execution
- →Highlight slow tools or agents as bottlenecks
- →Analyze flow patterns like keyword-skill-agent chains
How it works
This skill uses the `trace_timeline` and `trace_summary` MCP tools to analyze session logs. It presents a chronological event timeline and aggregate statistics of agent interactions.
Inputs & outputs
When to use trace
- →Debug agent flow patterns
- →Identify tool bottlenecks
- →Verify skill activations
- →Analyze session event timeline
About this skill
Agent Flow Trace
[TRACE MODE ACTIVATED]
Objective
Display the flow trace showing how hooks, keywords, skills, agents, and tools interacted during this session.
Instructions
-
Use
trace_timelineMCP tool to show the chronological event timeline- Call with no arguments to show the latest session
- Use
filterparameter to focus on specific event types (hooks, skills, agents, keywords, tools, modes) - Use
lastparameter to limit output
-
Use
trace_summaryMCP tool to show aggregate statistics- Hook fire counts
- Keywords detected
- Skills activated
- Mode transitions
- Tool performance and bottlenecks
Output Format
Present the timeline first, then the summary. Highlight:
- Mode transitions (how execution modes changed)
- Bottlenecks (slow tools or agents)
- Flow patterns (keyword -> skill -> agent chains)
When not to use it
- →When detailed code-level debugging is required instead of agent flow analysis
Limitations
- →Analysis is based on session logs
- →Focuses on agent flow and performance, not detailed code execution
How it compares
This skill provides a structured overview of agent execution flow and performance bottlenecks, which is more efficient than manually sifting through raw session logs.
Compared to similar skills
trace side by side with the closest alternatives in the catalog.
| Skill | Installs | Updated | Safety | Difficulty |
|---|---|---|---|---|
| trace (this skill) | 0 | 3mo | No flags | Intermediate |
| langsmith-observability | 4 | 6mo | Review | Intermediate |
| error-diagnostics-smart-debug | 5 | 3mo | No flags | Advanced |
| debugging-toolkit-smart-debug | 4 | 3mo | No flags | Intermediate |
Try saying
Example prompts that trigger this skill in your AI assistant.
More by yangyuan-zhen
View all by yangyuan-zhen →You might also like
langsmith-observability
davila7
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
error-diagnostics-smart-debug
sickn33
Use when working with error diagnostics smart debug
debugging-toolkit-smart-debug
sickn33
Use when working with debugging toolkit smart debug
jaeger-analysis
incidentfox
Jaeger distributed tracing analysis. Use when investigating request latency, tracing errors across services, finding slow spans, or understanding service dependencies.
agentation
benjitaylor
Add Agentation visual feedback toolbar to a Next.js project
log-analyzer
mikopbx
Анализ логов Docker контейнера для диагностики проблем и мониторинга здоровья системы. Использовать при отладке ошибок, отслеживании процессов воркеров, исследовании проблем API или мониторинге поведения системы после тестов.