skills.rest
scooter-lacroix
scooter-lacroixCOMMUNITY
Explore all skills by this author →
Website𝕏@scooter_lacroixGitHub

braintrust-tracing

Capture Braintrust traces for Maestro AI sessions and correlate sub-agent executions.

8|1|Updated Jan 4, 2026
Search Tags:#debugging#tracing#performance analysis#braintrust#ai sessions#agent correlation
One-click install
npx skills add https://github.com/scooter-lacroix/Maestro --skill braintrust-tracing
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: braintrust-tracing
Source: https://github.com/scooter-lacroix/Maestro/tree/main/maestro/skills/quality/braintrust-tracing
Command: npx skills add https://github.com/scooter-lacroix/Maestro --skill braintrust-tracing

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

This Skill provides detailed insights into AI session execution by integrating with Braintrust for comprehensive tracing, enabling deep debugging and performance analysis of complex AI workflows.

Core Features & Use Cases

  • End-to-End Tracing: Captures session starts, user prompts, tool usage, and agent stops.
  • Sub-Agent Correlation: Links parent agent tasks to their respective sub-agent execution traces.
  • Debugging & Analysis: Facilitates identification of performance bottlenecks and errors within AI sessions.
  • Use Case: When a multi-agent workflow produces unexpected results, use Braintrust tracing to pinpoint which agent failed, what input it received, and what output it generated, allowing for precise debugging.

Quick Start

Enable Braintrust tracing by setting TRACE_TO_BRAINTRUST to true in your local settings.

Frequently Asked Questions about braintrust-tracing

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

FAQPage Schema
How do I trace AI agent sessions to find performance bottlenecks?▼

AI session tracing captures hook event flows and trace hierarchies, allowing you to pinpoint performance bottlenecks and identify which agent failed by analyzing its inputs and outputs.

What is the best way to debug multi-agent workflows and correlate sub-agent executions?▼

Sub-agent correlation links parent agent tasks to their respective sub-agent execution traces by matching agent metadata and session IDs, enabling precise debugging of multi-agent workflows.

How do I enable Braintrust tracing for AI sessions?▼

To enable Braintrust tracing, set TRACE_TO_BRAINTRUST to true in your local settings, ensuring you have the required Braintrust API key and specific environment variables configured for activation.

Does Braintrust tracing capture end-to-end AI session execution data?▼

Braintrust tracing captures end-to-end AI session data including session starts, user prompts, tool usage, and agent stops, providing comprehensive insights for deep debugging and performance analysis.

Why does multi-agent workflow debugging require correlating agent metadata?▼

Correlating agent metadata is required because multi-agent workflows produce unexpected results, and matching session IDs links parent tasks to sub-agent executions, revealing exactly which agent failed and what it generated.

Do I need a Braintrust API key to start tracing AI sessions?▼

Yes, a Braintrust API key and specific environment variables are required for activation to enable detailed Braintrust tracing of Maestro AI sessions for debugging and performance analysis.

Related Skills

Explore More Software Engineering Skills→
scooter-lacroixscooter-lacroix
8

braintrust-analyze

Analyzes Maestro AI coding sessions using Braintree tracing data for usage patterns.

Community
Intermediate
JingyiWngJingyiWng

analyzing-mlflow-trace

Analyze MLflow trace JSON files to identify errors and performance bottlenecks.

Community
Advanced
jossteijosstei
453

status

Retrieve active Maestro session metadata, phase breakdowns, and token usage.

Community
Intermediate
parcadeiparcadei
3.9k

braintrust-tracing

Trace Claude Code sessions in Braintrust to debug and analyze agent interactions.

Community
Advanced