Skip to content
TrustedSkillsbeta
Back to all skills

Memory Audit

Checked
nhadaututtheky·vlatest·other·MIT

Analyzes and summarizes stored data within the agent's memory to identify outdated or irrelevant information needing review.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add nhadaututtheky/neural-memory --skill memory-audit -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

nhadaututtheky

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned nhadaututtheky/neural-memory at 2015cb9b09.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
2015cb9b09
Manifest
.claude-plugin/skills/memory-audit/SKILL.md
Scanned
2 files, 442 lines
Copies in repo
2 — all of them scanned
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

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.