skills.rest
darkroomengineering
darkroomengineeringOFFICIAL
Explore all skills by this author →
Website𝕏@darkroomdevsGitHub

learn

Store and recall project-scoped learnings in learnings.json across Claude Code sessions.

41|3|Updated Jan 12, 2026
Search Tags:#automation#recall#memory#learnings#project#shell-scripts#persist
One-click install
npx skills add https://github.com/darkroomengineering/cc-settings --skill learn-darkroomengineering
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: learn
Source: https://github.com/darkroomengineering/cc-settings/tree/main/skills/learn
Command: npx skills add https://github.com/darkroomengineering/cc-settings --skill learn-darkroomengineering

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Persistent memory for Claude Code learnings, enabling you to store insights and decisions so they persist beyond a single session and inform future work.

Core Features & Use Cases

  • Automatic learning storage: Capture fixes, patterns, gotchas, tool discoveries, and configuration decisions as learnings.
  • Recall and search: Retrieve past learnings to guide current work and reduce repeat effort.
  • Project-scoped storage: Learnings are organized per project under ~/.claude/learnings/<project>/learnings.json for isolation and auditability.
  • Simple tooling: Use provided scripts to store, recall, and manage learnings with ease.

Quick Start

Run the store-learning.sh script with a category and learning text to persist a new learning for the current project.

Frequently Asked Questions about learn

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

FAQPage Schema
How do I persist learnings and memory across Claude Code sessions?▼

You can persist learnings across Claude Code sessions by storing insights, bug fixes, and architectural decisions in a local JSON file using provided shell scripts, ensuring project knowledge survives for future reference.

What is the best way to store project-specific bug fixes and architectural decisions for future reference?▼

Storing project-specific learnings in a dedicated local JSON file allows you to capture bug fixes and architectural decisions, automatically informing future work and reducing rework within that specific project context.

How do I recall past learnings to guide current development work?▼

You can recall past learnings by using the provided shell scripts to search and retrieve stored insights from the project's local JSON storage, bringing historical context into your current session.

Does persistent memory for Claude Code require any external dependencies?▼

No external dependencies are required, as the persistent memory relies solely on local shell scripts and a JSON file stored at a specific path within your local environment for project isolation.

Where are project learnings stored on my local system?▼

Project learnings are stored locally in a JSON file located at a specific path within your local directory structure, organized per project to ensure isolation and auditability of stored knowledge.

When should I use a persistent learning store instead of relying on session context?▼

You should use a persistent learning store when patterns emerge, bugs are fixed, or architectural decisions are made, ensuring these insights automatically inform future work and reduce repeat effort across sessions.

Related Skills

Explore More Software Engineering Skills→
oaustegardoaustegard
137

versioning-skills

Initialize Git repositories and commit changes for skill directories.

Community
Basic
zhanbei1zhanbei1
1

session-logs

Search and filter historical session logs stored as JSONL files.

Community
Intermediate
rongarederongarede
4

continuous-learning

Extract reusable patterns from Claude Code session transcripts via Stop hook.

Community
Intermediate
rhpdsrhpds

03-memory-mcp

Configure persistent Memory MCP knowledge graph storage for Claude Code sessions.

Official
Advanced