geo-agent-training

Analyze geo-agent logs to diagnose inefficiencies and trace root causes.

4|1|Updated Feb 24, 2026
One-click install
npx skills add https://github.com/boettiger-lab/agent-skills --skill geo-agent-training
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: geo-agent-training
Source: https://github.com/boettiger-lab/agent-skills/tree/main/geo-agent-training
Command: npx skills add https://github.com/boettiger-lab/agent-skills --skill geo-agent-training

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyze geo-agent logs to diagnose inefficiencies and trace root causes.

Core Features & Use Cases

  • Identify STAC-first enforcement gaps, misapplied tool usage, and prompt-level artifacts across the four architectural layers.
  • Reconstruct conversations by interleaving LLM proxy and MCP server logs to reveal tool-call patterns and error sequences.
  • Provide actionable recommendations and cross-repo change suggestions to improve data workflows and tool orchestration.

Quick Start

Trace the latest LLM proxy and MCP logs to generate a root-cause report and improvement plan.

Frequently Asked Questions about geo-agent-training

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

FAQPage Schema
How do I trace geo-agent tool-use loops to their root cause in deployment logs?

Analyze geo-agent logs to diagnose inefficiencies by reconstructing conversations through interleaved LLM proxy and MCP server logs. This reveals tool-call patterns and error sequences, tracing failures to the correct architectural layer for actionable guidance.

Why does my geo-agent workflow fail STAC-first enforcement during data retrieval?

STAC-first enforcement gaps occur when geo-agents bypass required STAC queries before data access. Analyzing interleaved LLM proxy and MCP server logs identifies these structural gaps and prompt-level artifacts to provide actionable cross-repo change suggestions.

Do I need LLM proxy and MCP server logs to debug geo-agent inefficiencies?

Yes, diagnosing geo-agent inefficiencies requires access to both LLM proxy and MCP server logs. The framework relies on these logs alongside MCP tool descriptions to interleave conversations and deliver structured, actionable root-cause guidance.

What is the best way to diagnose failures across geo-agent architectural layers?

Interleave LLM proxy and MCP server logs to reconstruct tool-call sequences and trace failures to the correct architectural layer. This generates cross-repo change suggestions for tool orchestration and STAC-first enforcement improvements.

Can I use log analysis to fix MCP tool orchestration and prompt-level artifacts?

Yes, interleaving LLM proxy and MCP server logs identifies misapplied tool usage and prompt-level artifacts across four architectural layers. This provides actionable recommendations to improve data workflows and tool orchestration.