Can it fix the issues it finds automatically?

While it provides recommended fixes and immediate commands, it primarily functions as a diagnostic tool to provide a detailed report and actionable steps for the developer to implement.

What does the WW Diagnose skill actually do?

It analyzes World Weaver memory systems to find out why learning is failing, why memories aren't being retrieved, or why the system is performing slowly.

What should I do if the skill can't find the root cause?

The skill is designed to collect all diagnostic data and rule out common issues, then provide a recommended manual debugging approach based on the evidence gathered.

Which databases does this skill support?

It includes diagnostic commands and health checks specifically for Neo4j (graph database) and Qdrant (vector database) within the World Weaver stack.

How does it identify learning issues?

It checks bio-inspired parameters such as neuromodulators (DA/NE/ACh), analyzes eligibility traces for decay errors, and audits weight updates in the memory model.

World Weaver Memory Diagnostics

Name: World Weaver Memory Diagnostics
Author: astoreyai

byastoreyai

•

분석 및 모니터링

Diagnoses and troubleshoots complex issues within World Weaver memory systems to identify root causes in learning, performance, and data integrity.

소개

The WW Diagnose skill provides a comprehensive diagnostic framework for the World Weaver memory architecture, enabling developers to systematically troubleshoot issues related to bio-inspired learning, memory retrieval, and system performance. By analyzing neuromodulator values, eligibility traces, database health across Neo4j and Qdrant, and potential race conditions, it generates detailed diagnostic reports with actionable fixes. Whether you are dealing with stale caches, slow queries, or inconsistent learning rates, this skill streamlines the debugging process for sophisticated AI memory infrastructures by offering specialized agents and decision trees.

주요 기능

Detection of data corruption, race conditions, and cache coherence issues
Detailed diagnostic reporting with recommended immediate fixes and prevention steps
Automated diagnostic decision trees for learning and memory retrieval failures
Root cause analysis for performance bottlenecks and memory leaks
Real-time health monitoring for Neo4j and Qdrant database integrations
1 GitHub stars

사용 사례

Identifying the source of latency or high resource usage in complex memory systems
Resolving 'memory not found' errors or retrieval inaccuracies in vector databases
Troubleshooting why an AI agent's learning performance has plateaued or failed

소개

주요 기능

Detection of data corruption, race conditions, and cache coherence issues
Detailed diagnostic reporting with recommended immediate fixes and prevention steps
Automated diagnostic decision trees for learning and memory retrieval failures
Root cause analysis for performance bottlenecks and memory leaks
Real-time health monitoring for Neo4j and Qdrant database integrations
1 GitHub stars

사용 사례

Identifying the source of latency or high resource usage in complex memory systems
Resolving 'memory not found' errors or retrieval inaccuracies in vector databases
Troubleshooting why an AI agent's learning performance has plateaued or failed