braintrust-analyze

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

8|1|Updated Jan 4, 2026

Search Tags:#debugging #optimization #analysis #token usage #braintrust #maestro #session review

Ready to run

npx skills add https://github.com/scooter-lacroix/Maestro --skill braintrust-analyze-scooter-lacroix

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: braintrust-analyze
Source: https://github.com/scooter-lacroix/Maestro/tree/main/maestro/skills/quality/braintrust-analyze
Command: npx skills add https://github.com/scooter-lacroix/Maestro --skill braintrust-analyze-scooter-lacroix

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill helps you understand and optimize your AI coding sessions by analyzing Braintrust tracing data, identifying patterns, issues, and areas for improvement.

Core Features & Use Cases

Session Retrospective: Review past sessions to understand tool/agent/skill usage and token consumption.
Loop Detection: Identify repetitive tool call patterns that may indicate inefficiencies.
Usage Statistics: Track agent and skill activation trends over time.
Use Case: After a complex feature implementation, use this Skill to analyze the session, understand which tools were most effective, and identify any loops that could be optimized in future development cycles.

Quick Start

Analyze your last Maestro session to see a summary of tool and agent usage.

Frequently Asked Questions about braintrust-analyze

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

FAQPage Schema

How do I analyze AI coding sessions to review tool and agent usage?▼

To analyze AI coding sessions, you can use Braintrust tracing data to review tool, agent, and skill usage patterns. This provides a retrospective summary of your session's token consumption and activation trends.

What is the best way to detect repetitive tool call loops during AI development?▼

Loop detection is achieved by analyzing Braintrust tracing data to identify repetitive tool call patterns. This helps pinpoint inefficiencies in your AI coding sessions for future optimization.

Do I need a Braintrust API key to monitor token usage trends?▼

Yes, you need a Braintrust API key and enabled tracing to monitor token usage trends. The analysis relies entirely on Braintrust session data to track agent and skill activations over time.

Can I use Braintrust tracing data to debug complex feature implementations?▼

Yes, you can use Braintrust tracing data to debug complex feature implementations. It allows you to review past sessions, understand which tools were most effective, and identify areas for improvement.

What are the limitations of using Braintrust data for session review?▼

The primary limitation is the requirement for a Braintrust API key and explicitly enabled tracing. Without active tracing capturing session data, retrospective analysis and usage statistics cannot be generated.

How does session retrospective analysis work with Braintrust tracing?▼

Session retrospective analysis works by examining Braintrust tracing data to evaluate tool, agent, and skill usage. It translates session logs into actionable insights regarding token consumption and development efficiency.