behave

Name: behave
Availability: InStock
Author: enduser123

Detect and diagnose LLM behavioral patterns in chat sessions via structured hypothesis testing.

Updated Apr 26, 2026

Search Tags:#testing #debugging #analysis #llm #session #behavior #hypothesis

Ready to run

npx skills add https://github.com/EndUser123/cc-marketplace --skill behave

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: behave
Source: https://github.com/EndUser123/cc-marketplace/tree/main/plugins/cc-skills-meta/skills/behave
Command: npx skills add https://github.com/EndUser123/cc-marketplace --skill behave

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Analyze and diagnose LLM behavioral patterns in chat sessions by applying structured hypothesis testing to surface root causes and improvement paths.

Core Features & Use Cases

Loop detection: identify repeated prompts and responses that waste cycles.
Context degradation: detect forgotten details across turns and context loss.
Decision inefficiency: surface indecision and delayed commitments.
Cognitive overload signals: flag confusion, frequent clarifications, and cognitive load indicators.
Attention drift: spot tangential or off-topic responses.
Use Case: after a session with unexpected behavior, generate a prioritized list of hypotheses and a testing plan to verify them.

Quick Start

Provide a session transcript and observed symptoms to generate hypotheses and a structured testing plan.

Frequently Asked Questions about behave

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

FAQPage Schema

How do I diagnose LLM behavioral patterns like context degradation and attention drift in chat sessions?▼

To diagnose LLM behavioral patterns, apply structured hypothesis testing to your chat session transcripts to generate explicit hypotheses, cost-ordered tests, and falsification steps. This surfaces root causes for issues like context degradation and attention drift.

What is the best way to detect loop detection and repeated responses in multi-turn LLM conversations?▼

Detect repeated prompts and responses causing loop detection by applying structured hypothesis testing to session transcripts. The analysis produces explicit hypotheses and a calibrated confidence assessment to verify wasted cycles.

How do I generate a structured testing plan for unexpected LLM behavior after a session?▼

Generate a structured testing plan for unexpected LLM behavior by providing the session transcript and observed symptoms. The workflow produces explicit hypotheses, cost-ordered tests, and falsification steps.

Can I use hypothesis testing to identify cognitive overload signals and decision inefficiency in LLM outputs?▼

Yes, you can analyze cognitive overload signals by detecting confusion, frequent clarifications, and cognitive load indicators within multi-turn conversations. Hypothesis testing evaluates these symptoms to produce a calibrated confidence assessment.

What do I need to start analyzing LLM behavior using hypothesis testing?▼

You need to provide a session transcript and observed symptoms to start analyzing LLM behavior. This input drives the frontmatter-driven workflow to generate hypotheses and a prioritized testing plan.