skills.rest
tapanshah
tapanshahCOMMUNITY
Explore all skills by this author →
GitHub

review

Audit Claude Code auto-memory for promotion candidates, stale entries, and consolidation opportunities.

Updated Mar 7, 2026
Search Tags:#automation#code review#debugging#knowledge management#self-improvement#ai memory
One-click install
npx skills add https://github.com/tapanshah/Claude-Skills --skill review-tapanshah
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: review
Source: https://github.com/tapanshah/Claude-Skills/tree/main/engineering-team/self-improving-agent/skills/review
Command: npx skills add https://github.com/tapanshah/Claude-Skills --skill review-tapanshah

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

This Skill addresses the challenge of managing and optimizing an AI's evolving memory, ensuring it remains efficient, relevant, and free of outdated or redundant information.

Core Features & Use Cases

  • Memory Analysis: Audits auto-memory for promotion candidates, stale entries, and consolidation opportunities.
  • Conflict Detection: Identifies contradictions between memory entries and project documentation (CLAUDE.md).
  • Use Case: After a complex debugging session, use this Skill to review Claude's learned memory, identify key patterns that can be promoted to permanent rules, and prune any outdated information to maintain a lean and effective knowledge base.

Quick Start

Run the review skill to perform a full audit of the current project's auto-memory.

Frequently Asked Questions about review

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

FAQPage Schema
How do I audit AI memory files to find stale entries and consolidation opportunities?▼

To audit AI memory files, run the review skill to scan MEMORY.md, topic files, CLAUDE.md, and .claude/rules/ for stale entries, consolidation opportunities, and promotion candidates, generating actionable recommendations.

What is the best way to promote learned debugging patterns to permanent project rules?▼

The best way to promote learned debugging patterns is to run a memory audit that identifies key insights from your auto-memory and outputs actionable recommendations for promoting them to permanent rules.

Does the memory audit require any specific dependencies or external tools to run?▼

The memory audit requires no external dependencies, but it does require shell scripting capabilities to perform file system operations and text analysis on your project's auto-memory files.

How do I detect conflicts between auto-memory entries and project documentation?▼

To detect conflicts between auto-memory and project documentation, run the review skill to identify contradictions between memory entries and CLAUDE.md, ensuring your knowledge base remains accurate and conflict-free.

What health metrics are generated when analyzing Claude Code's auto-memory?▼

When analyzing Claude Code's auto-memory, the audit generates health metrics that evaluate promotion candidates, stale entries, and consolidation opportunities across MEMORY.md, topic files, and rules directories.

When should I prune outdated information from my AI's evolving memory knowledge base?▼

You should prune outdated information from your AI's memory after complex debugging sessions or when the audit identifies stale entries and contradictions, ensuring the knowledge base remains efficient and relevant.

Related Skills

Explore More Software Engineering Skills→
ano4lano4l

self-improving-agent

Analyze Claude Code auto-memory to identify promotion candidates and stale entries.

Community
Advanced
Patasse97Patasse97

review

Audit auto-memory directories and generate structured memory review reports.

Community
Advanced
NeKon69NeKon69
1

Nvim-tree.lua API Reference

Index commands and Lua API functions for the nvim-tree.lua Neovim plugin.

Community
Basic
adrozdenkoadrozdenko
6

health-check

Audit knowledge bases for stale entries, duplicates, and contradictions.

Community
Advanced