Claude Skills
CollectionsCompareWorkflowsNominate
Sign inSign up
© 2026 Curated Agent Skills·Learn more about Agent Skills
Back to repository

learn

verified

WHEN capturing learnings/gotchas/decisions into CLAUDE.md; NOT trivial changes; guides what to record, where it lives, and format.

View on GitHub

Marketplace

mintuz-claude-plugins

mintuz/claude-plugins

Plugin

core

Repository

mintuz/claude-plugins
14stars

plugins/core/skills/learn/SKILL.md

Last Verified

February 1, 2026

Install Skill

Select agents to install to:

Scope:
npx add-skill https://github.com/mintuz/claude-plugins/blob/main/plugins/core/skills/learn/SKILL.md -a claude-code --skill learn

Installation paths:

Claude
.claude/skills/learn/
Powered by add-skill CLI

Instructions

# CLAUDE.md Learning Integration

Use this skill to identify learning opportunities and document insights into CLAUDE.md. The goal is to ensure hard-won knowledge is preserved for future developers.

## When to Use

- User discovers a gotcha or unexpected behavior
- User completes a complex feature and wants to document learnings
- User makes an architectural decision worth preserving
- User fixes a tricky bug with insights to share
- User says "I wish I'd known this earlier"

## Philosophy

**Core Principle:** Knowledge that isn't documented is knowledge that will be lost. Every hard-won insight must be preserved for future developers.

## Identifying Learning Opportunities

Watch for these signals during development:

- Gotchas or unexpected behavior discovered
- "Aha!" moments or breakthroughs
- Architectural decisions being made
- Patterns that worked particularly well
- Anti-patterns encountered
- Tooling or setup knowledge gained

## Discovery Questions

### About the Problem

- What was unclear or surprising at the start?
- What took longer to figure out than expected?
- What assumptions were wrong?
- What would have saved time if known upfront?

### About the Solution

- What patterns or approaches worked particularly well?
- What patterns should be avoided?
- What gotchas or edge cases were discovered?
- What dependencies or relationships were not obvious?

### About the Context

- What domain knowledge is now clearer?
- What architectural decisions became apparent?
- What testing strategies were effective?
- What tooling or setup was required?

## Learning Significance Assessment

**Document if ANY of these are true:**

- Would save future developers significant time (>30 minutes)
- Prevents a class of bugs or errors
- Reveals non-obvious behavior or constraints
- Captures architectural rationale or trade-offs
- Documents domain-specific knowledge
- Identifies effective patterns or anti-patterns
- Clarifies tool setup or configuration gotchas

**Skip if AL

Validation Details

Front Matter
Required Fields
Valid Name Format
Valid Description
Has Sections
Allowed Tools
Instruction Length:
7645 chars