learn

# Learn

A continuous learning system that extracts reusable knowledge from work sessions and
codifies it into new Claude Code skills. This enables autonomous improvement over time.

## Core Principle: Skill Extraction

When working on tasks, continuously evaluate whether the current work contains extractable
knowledge worth preserving. Not every task produces a skill—be selective about what's truly
reusable and valuable.

## TDD Mapping for Skill Extraction

Skill extraction follows the same discipline as Test-Driven Development:

| TDD Concept         | Skill Extraction                                   |
| ------------------- | -------------------------------------------------- |
| **Test case**       | The problem/failure pattern you just encountered   |
| **Production code** | The skill document (.mdc file)                     |
| **RED**             | You hit the problem during work (already happened) |
| **GREEN**           | Write skill addressing that specific problem       |
| **REFACTOR**        | Verify skill clarity, iterate if needed            |

The key insight: When extracting from a session, the RED phase already happened—you discovered something non-obvious. Now write the skill (GREEN) and verify it (REFACTOR).

## When to Extract a Skill

Extract a skill when you encounter:

1. **Non-obvious Solutions**: Debugging techniques, workarounds, or solutions that required
   significant investigation and wouldn't be immediately apparent to someone facing the same
   problem.

2. **Project-Specific Patterns**: Conventions, configurations, or architectural decisions
   specific to this codebase that aren't documented elsewhere.

3. **Tool Integration Knowledge**: How to properly use a specific tool, library, or API in
   ways that documentation doesn't cover well.

4. **Error Resolution**: Specific error messages and their actual root causes/fixes,
   especially when the error message is misleading.

5. **Workflow Optimizations**: Multi-step processes tha