skills.rest
Kastalien-Research
Kastalien-ResearchOFFICIAL
Explore all skills by this author →
WebsiteGitHub

memory-system-expert

Query, add, and rank codebase learnings using memory CLI tools.

9|2|Updated Jan 12, 2026
Search Tags:#claude#learning#agents#memory#calibration#memory-system
One-click install
npx skills add https://github.com/Kastalien-Research/thoughtbox-dot-claude --skill memory-system-expert
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: memory-system-expert
Source: https://github.com/Kastalien-Research/thoughtbox-dot-claude/tree/main/.claude/skills/memory-system-expert
Command: npx skills add https://github.com/Kastalien-Research/thoughtbox-dot-claude --skill memory-system-expert

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill enables Claude agents to effectively leverage and contribute to a progressive learning memory system within codebases, reducing duplication and accelerating knowledge capture from interactions.

Core Features & Use Cases

  • Search and reuse learnings to accelerate development and minimize repeated mistakes.
  • Add new learnings to continually improve the memory topology and awareness of the codebase.
  • Calibrate path-specific rules so relevant context auto-loads when editing files under .claude/rules.

Quick Start

  1. Explore memory: memory-query "authentication"
  2. Rank results: memory-query "authentication" | memory-rank
  3. Capture a learning: echo '{"title":"Auth refresh","issue":"Tokens expire","solution":"Auto refresh before expiry","pattern":"proactive token refresh"}' | memory-add --domain=lessons

Frequently Asked Questions about memory-system-expert

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

FAQPage Schema
How do I store and reuse learnings for Claude agents in a codebase?▼

Store and reuse learnings for Claude agents by using memory CLI tools like memory-add to capture patterns and memory-query to search them, reducing duplicated mistakes across software projects.

What is a progressive memory system for Claude agents?▼

A progressive memory system for Claude agents captures interaction learnings within codebases, applying path-specific rules in the .claude/rules directory to auto-load relevant context and calibrate awareness.

How do I add a new learning to the memory system using command line tools?▼

Add a new learning to the memory system by piping a JSON object with title, issue, solution, and pattern fields into the memory-add tool, specifying a domain to build the memory topology.

Do I need external services to use the memory tooling with Claude agents?▼

No external services are required to use the memory tooling with Claude agents; it relies entirely on local file-system interactions and memory CLI commands within your existing codebase environment.

How does path-specific rule calibration work in the .claude/rules directory?▼

Path-specific rule calibration in the .claude/rules directory ensures relevant context auto-loads when editing files, using memory tools to rank and retrieve stored learnings for the specific path.

What's the best way to search and rank stored patterns in a codebase memory system?▼

Search and rank stored patterns by piping memory-query results into memory-rank, allowing Claude agents to prioritize the most relevant learnings for the current development context.

Related Skills

Explore More Software Engineering Skills→
TbK0ngTbK0ng

trellis-bootstrap

Initialize Trellis AI workflow scaffolding with .trellis structure, memory, and CLI hooks.

Community
Intermediate
doravidandoravidan

ralph-memory

Query and manage RALPH's persistent memory stored in .ralph/memory/*.json files.

Community
Basic
syahravisyahravi

self-improvement

Capture errors and learnings into structured .learnings markdown files.

Community
Intermediate
adeboldadebold

AgentDB Vector Search

Perform vector-based semantic search against an AgentDB index.

Community
Advanced