---
name: Learn
slug: learn-6
category: AI Engineering
description: Learn automatically evaluates OmA sessions to extract reusable patterns like error fixes, workarounds, and conventions, then saves them as rules. Use it after sessions or when configuring the SessionEnd hook and learned rules.
github: "https://github.com/Joonghyun-Lee-Frieren/oh-my-antigravity/tree/main/skills/learn"
language: JavaScript
stars: 210
forks: 27
install: "npx degit https://github.com/Joonghyun-Lee-Frieren/oh-my-antigravity/tree/main/skills/learn ~/.claude/skills/learn"
installs_to: ~/.claude/skills/learn
source_path: skills/learn/SKILL.md
collection_size: 11
category_size: 2970
collection_url: "https://dirskills.com/collections/Joonghyun-Lee-Frieren/oh-my-antigravity"
added: 2026-09-04T05:26:21.453Z
last_synced: 2026-09-04T05:26:21.453Z
canonical_url: "https://dirskills.com/skills/learn-6"
---

# Learn

Learn automatically evaluates OmA sessions to extract reusable patterns like error fixes, workarounds, and conventions, then saves them as rules. Use it after sessions or when configuring the SessionEnd hook and learned rules.

**Install:**

```bash
npx degit https://github.com/Joonghyun-Lee-Frieren/oh-my-antigravity/tree/main/skills/learn ~/.claude/skills/learn
```

## README

# Learn Skill

Automatically evaluates OmA sessions to extract reusable patterns (error resolutions, workarounds, conventions) and save them to `.omg/rules/learned/`.

## When to Activate

- Setting up automatic pattern extraction from OmA sessions.
- Configuring the `SessionEnd` hook for session evaluation.
- Reviewing or curating learned skills in `.omg/rules/learned/`.
- Adjusting extraction thresholds or pattern categories.

## How It Works

This skill runs as a **SessionEnd hook** at the end of each session:

1. **Session Evaluation**: Checks if session has enough messages (default: 10+).
2. **Pattern Detection**: Identifies extractable patterns (errors, workarounds, styles).
3. **Skill Extraction**: Saves useful patterns as new rules in `.omg/rules/learned/`.

### Interactive Selective Save

When `/oma:learn` is run, the agent will:
1. Identify high-signal reusable patterns.
2. List these patterns with unique IDs.
3. **Ask the user** whether to save all or specific ones.
4. Default to saving all if not specified.

## Extraction Focus

The `learn` skill focuses on **reusable patterns** rather than simple chat history:
- **Common Error Resolutions**: How recurring errors were fixed.
- **Environment Workarounds**: Fixes for tool or framework quirks.
- **Style/Conventions**: Project-specific rules identified during work.
- **Corrected Behaviors**: Mistakes the agent should avoid in the future.

## Configuration

Edit `.omg/rules/learn.json` to customize:

```json
{
  "min_session_length": 10,
  "extraction_threshold": "medium",
  "auto_approve": false,
  "learned_skills_path": ".omg/rules/learned/",
  "patterns_to_detect": [
    "error_resolution",
    "user_corrections",
    "workarounds",
    "debugging_techniques",
    "project_specific"
  ],
  "ignore_patterns": [
    "simple_typos",
    "one_time_fixes",
    "external_api_issues"
  ]
}
```

## Related

- `/oma:memory` - Project-level knowledge.
- `/oma:rules` - Context-aware rule application.
- `/oma:learn` - Manual pattern extraction command.