/learn
Automatically evaluates OmA sessions to extract reusable patterns (error resolutions, workarounds, conventions) and save them to `.omg/rules/learned/`.
$ npx -y skills add Joonghyun-Lee-Frieren/oh-my-antigravity --skill learn --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/learn
Context preview
The summary Claude sees to decide when to auto-load this skill.
Automatically evaluates OmA sessions to extract reusable patterns (error resolutions, workarounds, conventions) and save them to `.omg/rules/learned/`.
SKILL.md
learn.SKILL.md# REFACTORED: Integrated interactive selective save functionality into the learn skill.
# The extraction process now prioritizes common reusable patterns over simple chat logs.
# Default behavior is to save all identified patterns, allowing users to opt into selective saving.
name = "learn"
description = "Automatically extract reusable patterns from sessions and save them as learned skills/rules for future use."
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:
{
"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.
Read more
# REFACTORED: Integrated interactive selective save functionality into the learn skill. # The extraction process now prioritizes common reusable patterns over simple chat logs. # Default behavior is to save all identified patterns, allowing users to opt into selective saving. name = "learn" description = "Automatically extract reusable patterns from sessions and save them as learned skills/rules for future use."
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:
{
"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.
Antigravity CLI: Gemini CLI will be replaced by Antigravity CLI on June 18th. If you previously installed oh-my-gemini-cli in Gemini CLI, Antigravity CLI will ask whether to import plugins during installation. Check that option to bring your plugin over.
Repo: Joonghyun-Lee-Frieren/oh-my-antigravity
Other skills on oh-my-antigravity.
- /blueprint
Use this skill when a product, UI, or workflow decision needs a stable decision surface before implementation.
Open skill - /context-optimize
Use this skill when context is growing quickly or cache consistency drops.
Open skill - /deep-dive
Use this skill when requirements are incomplete, conflicting, or too vague to begin implementation safely.
Open skill - /execute
Use this skill when the task is implementation-ready and requires code changes now.
Open skill - /oma-plan
Use this skill when the request is non-trivial and should be planned before editing code.
Open skill - /plan
Use this skill when the request is non-trivial and should be planned before editing code.
Open skill

