{"id":"ebceef5f-cd48-427f-8fb5-a53d0d39ac02","shortId":"7me5FW","kind":"skill","title":"learn","tagline":"Context-engineering-powered multi-agent team workflow pack for Gemini CLI.","description":"# Learn Skill\n\nAutomatically evaluates OmG sessions to extract reusable patterns (error resolutions, workarounds, conventions) and save them to `.omg/rules/learned/`.\n\n## When to Activate\n\n- Setting up automatic pattern extraction from OmG sessions.\n- Configuring the `SessionEnd` hook for session evaluation.\n- Reviewing or curating learned skills in `.omg/rules/learned/`.\n- Adjusting extraction thresholds or pattern categories.\n\n## How It Works\n\nThis skill runs as a **SessionEnd hook** at the end of each session:\n\n1. **Session Evaluation**: Checks if session has enough messages (default: 10+).\n2. **Pattern Detection**: Identifies extractable patterns (errors, workarounds, styles).\n3. **Skill Extraction**: Saves useful patterns as new rules in `.omg/rules/learned/`.\n\n### Interactive Selective Save\n\nWhen `/omg:learn` is run, the agent will:\n1. Identify high-signal reusable patterns.\n2. List these patterns with unique IDs.\n3. **Ask the user** whether to save all or specific ones.\n4. Default to saving all if not specified.\n\n## Extraction Focus\n\nThe `learn` skill focuses on **reusable patterns** rather than simple chat history:\n- **Common Error Resolutions**: How recurring errors were fixed.\n- **Environment Workarounds**: Fixes for tool or framework quirks.\n- **Style/Conventions**: Project-specific rules identified during work.\n- **Corrected Behaviors**: Mistakes the agent should avoid in the future.\n\n## Configuration\n\nEdit `.omg/rules/learn.json` to customize:\n\n```json\n{\n  \"min_session_length\": 10,\n  \"extraction_threshold\": \"medium\",\n  \"auto_approve\": false,\n  \"learned_skills_path\": \".omg/rules/learned/\",\n  \"patterns_to_detect\": [\n    \"error_resolution\",\n    \"user_corrections\",\n    \"workarounds\",\n    \"debugging_techniques\",\n    \"project_specific\"\n  ],\n  \"ignore_patterns\": [\n    \"simple_typos\",\n    \"one_time_fixes\",\n    \"external_api_issues\"\n  ]\n}\n```\n\n## Related\n\n- `/omg:memory` - Project-level knowledge.\n- `/omg:rules` - Context-aware rule application.\n- `/omg:learn` - Manual pattern extraction command.","tags":["learn","gemini","cli","joonghyun-lee-frieren","agent-skills","agentic-ai","agentic-workflow","gemini-cli","gemini-cli-extensions","geminicli","multi-agent","skills"],"capabilities":["skill","source-joonghyun-lee-frieren","skill-learn","topic-agent-skills","topic-agentic-ai","topic-agentic-workflow","topic-gemini","topic-gemini-cli","topic-gemini-cli-extensions","topic-geminicli","topic-multi-agent","topic-skills"],"categories":["oh-my-gemini-cli"],"synonyms":[],"warnings":[],"endpointUrl":"https://skills.sh/Joonghyun-Lee-Frieren/oh-my-gemini-cli/learn","protocol":"skill","transport":"skills-sh","auth":{"type":"none","details":{"cli":"npx skills add Joonghyun-Lee-Frieren/oh-my-gemini-cli","source_repo":"https://github.com/Joonghyun-Lee-Frieren/oh-my-gemini-cli","install_from":"skills.sh"}},"qualityScore":"0.528","qualityRationale":"deterministic score 0.53 from registry signals: · indexed on github topic:agent-skills · 156 github stars · SKILL.md body (2,035 chars)","verified":false,"liveness":"unknown","lastLivenessCheck":null,"agentReviews":{"count":0,"score_avg":null,"cost_usd_avg":null,"success_rate":null,"latency_p50_ms":null,"narrative_summary":null,"summary_updated_at":null},"enrichmentModel":"deterministic:skill-github:v1","enrichmentVersion":1,"enrichedAt":"2026-05-02T12:54:42.772Z","embedding":null,"createdAt":"2026-04-18T22:09:51.593Z","updatedAt":"2026-05-02T12:54:42.772Z","lastSeenAt":"2026-05-02T12:54:42.772Z","tsv":"'/omg':116,247,253,260 '1':81,123 '10':91,213 '2':92,130 '3':101,137 '4':148 'activ':36 'adjust':59 'agent':8,121,198 'api':244 'applic':259 'approv':218 'ask':138 'auto':217 'automat':17,39 'avoid':200 'awar':257 'behavior':195 'categori':64 'chat':168 'check':84 'cli':14 'command':265 'common':170 'configur':45,204 'context':3,256 'context-awar':255 'context-engineering-pow':2 'convent':28 'correct':194,230 'curat':54 'custom':208 'debug':232 'default':90,149 'detect':94,226 'edit':205 'end':77 'engin':4 'enough':88 'environ':178 'error':25,98,171,175,227 'evalu':18,51,83 'extern':243 'extract':22,41,60,96,103,156,214,264 'fals':219 'fix':177,180,242 'focus':157,161 'framework':184 'futur':203 'gemini':13 'high':126 'high-sign':125 'histori':169 'hook':48,74 'id':136 'identifi':95,124,191 'ignor':236 'interact':112 'issu':245 'json':209 'knowledg':252 'learn':1,15,55,117,159,220,261 'length':212 'level':251 'list':131 'manual':262 'medium':216 'memori':248 'messag':89 'min':210 'mistak':196 'multi':7 'multi-ag':6 'new':108 'omg':19,43 'omg/rules/learn.json':206 'omg/rules/learned':33,58,111,223 'one':147,240 'pack':11 'path':222 'pattern':24,40,63,93,97,106,129,133,164,224,237,263 'power':5 'project':188,234,250 'project-level':249 'project-specif':187 'quirk':185 'rather':165 'recur':174 'relat':246 'resolut':26,172,228 'reusabl':23,128,163 'review':52 'rule':109,190,254,258 'run':70,119 'save':30,104,114,143,151 'select':113 'session':20,44,50,80,82,86,211 'sessionend':47,73 'set':37 'signal':127 'simpl':167,238 'skill':16,56,69,102,160,221 'skill-learn' 'source-joonghyun-lee-frieren' 'specif':146,189,235 'specifi':155 'style':100 'style/conventions':186 'team':9 'techniqu':233 'threshold':61,215 'time':241 'tool':182 'topic-agent-skills' 'topic-agentic-ai' 'topic-agentic-workflow' 'topic-gemini' 'topic-gemini-cli' 'topic-gemini-cli-extensions' 'topic-geminicli' 'topic-multi-agent' 'topic-skills' 'typo':239 'uniqu':135 'use':105 'user':140,229 'whether':141 'work':67,193 'workaround':27,99,179,231 'workflow':10","prices":[{"id":"652165dd-afed-4f51-a962-3461cb814ced","listingId":"ebceef5f-cd48-427f-8fb5-a53d0d39ac02","amountUsd":"0","unit":"free","nativeCurrency":null,"nativeAmount":null,"chain":null,"payTo":null,"paymentMethod":"skill-free","isPrimary":true,"details":{"org":"Joonghyun-Lee-Frieren","category":"oh-my-gemini-cli","install_from":"skills.sh"},"createdAt":"2026-04-18T22:09:51.593Z"}],"sources":[{"listingId":"ebceef5f-cd48-427f-8fb5-a53d0d39ac02","source":"github","sourceId":"Joonghyun-Lee-Frieren/oh-my-gemini-cli/learn","sourceUrl":"https://github.com/Joonghyun-Lee-Frieren/oh-my-gemini-cli/tree/main/skills/learn","isPrimary":false,"firstSeenAt":"2026-04-18T22:09:51.593Z","lastSeenAt":"2026-05-02T12:54:42.772Z"}],"details":{"listingId":"ebceef5f-cd48-427f-8fb5-a53d0d39ac02","quickStartSnippet":null,"exampleRequest":null,"exampleResponse":null,"schema":null,"openapiUrl":null,"agentsTxtUrl":null,"citations":[],"useCases":[],"bestFor":[],"notFor":[],"kindDetails":{"org":"Joonghyun-Lee-Frieren","slug":"learn","github":{"repo":"Joonghyun-Lee-Frieren/oh-my-gemini-cli","stars":156,"topics":["agent-skills","agentic-ai","agentic-workflow","gemini","gemini-cli","gemini-cli-extensions","geminicli","multi-agent","skills"],"license":"other","html_url":"https://github.com/Joonghyun-Lee-Frieren/oh-my-gemini-cli","pushed_at":"2026-04-28T00:36:47Z","description":"Context-engineering-powered multi-agent team workflow pack for Gemini CLI.","skill_md_sha":"fd009145ba382cd7d5118971c85e556cd6bff62e","skill_md_path":"skills/learn/SKILL.md","default_branch":"main","skill_tree_url":"https://github.com/Joonghyun-Lee-Frieren/oh-my-gemini-cli/tree/main/skills/learn"},"layout":"multi","source":"github","category":"oh-my-gemini-cli","frontmatter":{},"skills_sh_url":"https://skills.sh/Joonghyun-Lee-Frieren/oh-my-gemini-cli/learn"},"updatedAt":"2026-05-02T12:54:42.772Z"}}