Verified:GitHub

reasoning-trace-optimizer

Analyze AI agent reasoning traces to detect failure patterns and optimize prompts.

1|Updated Jan 27, 2026

Search Tags:#context-engineering #AI-agents #prompt-optimization #agent-debugging #interleaved-thinking #reasoning-trace-optimizer

Ready to run

npx skills add https://github.com/phonowell/mimikit --skill reasoning-trace-optimizer-phonowell

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: reasoning-trace-optimizer
Source: https://github.com/phonowell/mimikit/tree/main/.agents/skills/context-engineering-collection/examples/interleaved-thinking
Command: npx skills add https://github.com/phonowell/mimikit --skill reasoning-trace-optimizer-phonowell

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Debug and optimize AI agents by analyzing their reasoning traces to surface failure patterns and improve prompts.

Core Features & Use Cases

Pattern detection: context_degradation, tool_confusion, instruction_drift, hallucination, incomplete_reasoning, tool_misuse, goal_abandonment, circular_reasoning, premature_conclusion, missing_validation.
Prompt optimization: generate improved prompts and shareable agent skills based on trace analysis.
Skill generation: convert optimization learnings into reusable Agent Skills for team collaboration and knowledge sharing.

Quick Start

Run the optimization loop to capture traces, analyze them, and produce an improved prompt.

Frequently Asked Questions about reasoning-trace-optimizer

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

FAQPage Schema

How do I debug AI agents that stop working correctly during multi-turn workflows?▼

Analyzing reasoning traces from AI agents detects failure patterns like context degradation, tool confusion, and instruction drift in multi-turn workflows. This surfaces specific breakdowns in interleaved thinking and tool usage to pinpoint why the agent failed.

What is interleaved thinking in AI agents and when does it cause problems?▼

Interleaved thinking is when an AI agent reasons between tool usages across multiple turns. It causes problems when the reasoning trace degrades, leading to patterns like hallucination, circular reasoning, or goal abandonment that derail the agent workflow.

How do I optimize prompts to fix AI agent failure patterns?▼

Optimize prompts by running an analysis loop on captured agent reasoning traces. This detects specific failure patterns and generates improved prompts that correct issues like instruction drift, missing validation, and incomplete reasoning.

Can I convert prompt optimization learnings into reusable agent skills?▼

Yes, optimization learnings can be converted into reusable Agent Skills. By analyzing reasoning traces and detecting failure patterns, you generate shareable skills that enable team collaboration and prevent repeated agent debugging issues.

What are common failure patterns in AI agent reasoning traces?▼

Common failure patterns in AI agent reasoning traces include context degradation, tool confusion, instruction drift, hallucination, incomplete reasoning, tool misuse, goal abandonment, circular reasoning, premature conclusion, and missing validation.

Does this reasoning trace optimizer require specific dependencies to run?▼

No specific dependencies are required to run the reasoning trace optimizer. It operates as a standalone skill to analyze agent workflows, requiring only the captured reasoning traces from your multi-turn AI agent interactions.