Memory Audit

What it does

This skill, Memory Audit, analyzes and summarizes data within an AI agent's memory to assess its quality and identify areas for improvement. It acts as a “Memory Quality Auditor,” systematically reviewing the agent’s stored information across six key dimensions: Purity, Freshness, Coverage, Consistency, Relevance, and Completeness (although only three are detailed in the source). The audit provides a grade, scores, findings with evidence, and actionable recommendations to improve memory health.

When to use it

• To proactively identify outdated or irrelevant information within an agent's memory.
• When experiencing unexpected behavior from the AI agent that might be related to data quality issues.
• As part of a regular maintenance routine to ensure optimal agent performance.
• To understand why an agent is generating inaccurate or inconsistent responses.
• After significant changes in project scope or workflows, to assess memory coverage.

Key capabilities

• Baseline Collection: Gathers metrics using NeuralMemory tools like nmem_stats, nmem_health, and nmem_context.
• Six-Dimension Audit: Evaluates memory quality across Purity (contradictions, duplicates, outdated facts), Freshness (stale ratio, expired TODOs), and Coverage (topic balance, decision coverage).
• Prioritized Findings: Identifies issues with severity levels (CRITICAL, HIGH, MEDIUM, LOW) and references specific memories.
• Actionable Recommendations: Provides steps to improve memory quality, ordered by potential impact.
• Metrics Projection: Estimates the effect of recommendations on overall scores.

Example prompts

• "Run a Memory Audit."
• "Audit my brain's memory quality with a focus on Freshness."
• "Perform a full audit and identify any active contradictions."

Tips & gotchas

• This skill relies on NeuralMemory tools, so ensure those are properly configured and accessible.
• If a tool fails during the baseline collection phase, the audit will continue but note the failure.
• The audit prioritizes findings based on severity; focus on addressing CRITICAL issues first.