[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6G25CNNFDCTTXQ22Y96KB27":3,"skill-same:01M6G25CNNFDCTTXQ22Y96KB27":49},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":21,"linkOnly":22,"markdownContent":23,"markdownBody":24,"frontMatter":25,"refName":26,"commitSha":27,"skillDirectory":28,"forksCount":29,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M6G25CNNFDCTTXQ22Y96KB27","continuous-learning",null,"Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。","oabdelmaksoud\u002FAgention","oabdelmaksoud","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F50699149?v=4","01M6D5CVVN778ZCDP1WHS816SP","Omar Abdelmaksoud","01M6D8A4TE76V3DCSH3D94VG1V",2,"MIT","https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FAgention\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fdocs\u002Fja-JP\u002Fskills\u002Fcontinuous-learning\u002FSKILL.md",[],[19,20],"learning","continuous learning","2026-11-10 10:12:30",false,"---\nname: continuous-learning\ndescription: Claude Codeセッションから再利用可能なパターンを自動的に抽出し、将来の使用のために学習済みスキルとして保存します。\n---\n\n# 継続学習スキル\n\nClaude Codeセッションを終了時に自動的に評価し、学習済みスキルとして保存できる再利用可能なパターンを抽出します。\n\n## 動作原理\n\nこのスキルは各セッション終了時に**Stopフック**として実行されます:\n\n1. **セッション評価**: セッションに十分なメッセージがあるか確認(デフォルト: 10以上)\n2. **パターン検出**: セッションから抽出可能なパターンを識別\n3. **スキル抽出**: 有用なパターンを`~\u002F.claude\u002Fskills\u002Flearned\u002F`に保存\n\n## 設定\n\n`config.json`を編集してカスタマイズ:\n\n```json\n{\n  \"min_session_length\": 10,\n  \"extraction_threshold\": \"medium\",\n  \"auto_approve\": false,\n  \"learned_skills_path\": \"~\u002F.claude\u002Fskills\u002Flearned\u002F\",\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## パターンの種類\n\n| パターン | 説明 |\n|---------|-------------|\n| `error_resolution` | 特定のエラーの解決方法 |\n| `user_corrections` | ユーザー修正からのパターン |\n| `workarounds` | フレームワーク\u002Fライブラリの癖への解決策 |\n| `debugging_techniques` | 効果的なデバッグアプローチ |\n| `project_specific` | プロジェクト固有の規約 |\n\n## フック設定\n\n`~\u002F.claude\u002Fsettings.json`に追加:\n\n```json\n{\n  \"hooks\": {\n    \"Stop\": [{\n      \"matcher\": \"*\",\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"~\u002F.claude\u002Fskills\u002Fcontinuous-learning\u002Fevaluate-session.sh\"\n      }]\n    }]\n  }\n}\n```\n\n## Stopフックを使用する理由\n\n- **軽量**: セッション終了時に1回だけ実行\n- **ノンブロッキング**: すべてのメッセージにレイテンシを追加しない\n- **完全なコンテキスト**: セッション全体のトランスクリプトにアクセス可能\n\n## 関連項目\n\n- [The Longform Guide](https:\u002F\u002Fx.com\u002Faffaanmustafa\u002Fstatus\u002F2014040193557471352) - 継続学習に関するセクション\n- `\u002Flearn`コマンド - セッション中の手動パターン抽出\n\n---\n\n## 比較ノート (調査: 2025年1月)\n\n### vs Homunculus\n\nHomunculus v2はより洗練されたアプローチを採用:\n\n| 機能 | このアプローチ | Homunculus v2 |\n|---------|--------------|---------------|\n| 観察 | Stopフック(セッション終了時) | PreToolUse\u002FPostToolUseフック(100%信頼性) |\n| 分析 | メインコンテキスト | バックグラウンドエージェント(Haiku) |\n| 粒度 | 完全なスキル | 原子的な「本能」 |\n| 信頼度 | なし | 0.3-0.9の重み付け |\n| 進化 | 直接スキルへ | 本能 → クラスタ → スキル\u002Fコマンド\u002Fエージェント |\n| 共有 | なし | 本能のエクスポート\u002Fインポート |\n\n**homunculusからの重要な洞察:**\n> \"v1はスキルに観察を依存していました。スキルは確率的で、発火率は約50-80%です。v2は観察にフック(100%信頼性)を使用し、学習された振る舞いの原子単位として本能を使用します。\"\n\n### v2の潜在的な改善\n\n1. **本能ベースの学習** - 信頼度スコアリングを持つ、より小さく原子的な振る舞い\n2. **バックグラウンド観察者** - 並行して分析するHaikuエージェント\n3. **信頼度の減衰** - 矛盾した場合に本能の信頼度が低下\n4. **ドメインタグ付け** - コードスタイル、テスト、git、デバッグなど\n5. **進化パス** - 関連する本能をスキル\u002Fコマンドにクラスタ化\n\n詳細: `docs\u002Fcontinuous-learning-v2-spec.md`を参照。\n","# 継続学習スキル\n\nClaude Codeセッションを終了時に自動的に評価し、学習済みスキルとして保存できる再利用可能なパターンを抽出します。\n\n## 動作原理\n\nこのスキルは各セッション終了時に**Stopフック**として実行されます:\n\n1. **セッション評価**: セッションに十分なメッセージがあるか確認(デフォルト: 10以上)\n2. **パターン検出**: セッションから抽出可能なパターンを識別\n3. **スキル抽出**: 有用なパターンを`~\u002F.claude\u002Fskills\u002Flearned\u002F`に保存\n\n## 設定\n\n`config.json`を編集してカスタマイズ:\n\n```json\n{\n  \"min_session_length\": 10,\n  \"extraction_threshold\": \"medium\",\n  \"auto_approve\": false,\n  \"learned_skills_path\": \"~\u002F.claude\u002Fskills\u002Flearned\u002F\",\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## パターンの種類\n\n| パターン | 説明 |\n|---------|-------------|\n| `error_resolution` | 特定のエラーの解決方法 |\n| `user_corrections` | ユーザー修正からのパターン |\n| `workarounds` | フレームワーク\u002Fライブラリの癖への解決策 |\n| `debugging_techniques` | 効果的なデバッグアプローチ |\n| `project_specific` | プロジェクト固有の規約 |\n\n## フック設定\n\n`~\u002F.claude\u002Fsettings.json`に追加:\n\n```json\n{\n  \"hooks\": {\n    \"Stop\": [{\n      \"matcher\": \"*\",\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"~\u002F.claude\u002Fskills\u002Fcontinuous-learning\u002Fevaluate-session.sh\"\n      }]\n    }]\n  }\n}\n```\n\n## Stopフックを使用する理由\n\n- **軽量**: セッション終了時に1回だけ実行\n- **ノンブロッキング**: すべてのメッセージにレイテンシを追加しない\n- **完全なコンテキスト**: セッション全体のトランスクリプトにアクセス可能\n\n## 関連項目\n\n- [The Longform Guide](https:\u002F\u002Fx.com\u002Faffaanmustafa\u002Fstatus\u002F2014040193557471352) - 継続学習に関するセクション\n- `\u002Flearn`コマンド - セッション中の手動パターン抽出\n\n---\n\n## 比較ノート (調査: 2025年1月)\n\n### vs Homunculus\n\nHomunculus v2はより洗練されたアプローチを採用:\n\n| 機能 | このアプローチ | Homunculus v2 |\n|---------|--------------|---------------|\n| 観察 | Stopフック(セッション終了時) | PreToolUse\u002FPostToolUseフック(100%信頼性) |\n| 分析 | メインコンテキスト | バックグラウンドエージェント(Haiku) |\n| 粒度 | 完全なスキル | 原子的な「本能」 |\n| 信頼度 | なし | 0.3-0.9の重み付け |\n| 進化 | 直接スキルへ | 本能 → クラスタ → スキル\u002Fコマンド\u002Fエージェント |\n| 共有 | なし | 本能のエクスポート\u002Fインポート |\n\n**homunculusからの重要な洞察:**\n> \"v1はスキルに観察を依存していました。スキルは確率的で、発火率は約50-80%です。v2は観察にフック(100%信頼性)を使用し、学習された振る舞いの原子単位として本能を使用します。\"\n\n### v2の潜在的な改善\n\n1. **本能ベースの学習** - 信頼度スコアリングを持つ、より小さく原子的な振る舞い\n2. **バックグラウンド観察者** - 並行して分析するHaikuエージェント\n3. **信頼度の減衰** - 矛盾した場合に本能の信頼度が低下\n4. **ドメインタグ付け** - コードスタイル、テスト、git、デバッグなど\n5. **進化パス** - 関連する本能をスキル\u002Fコマンドにクラスタ化\n\n詳細: `docs\u002Fcontinuous-learning-v2-spec.md`を参照。\n",{"name":5,"description":7},"main","a318f48de3c5718e8ea2e9f6fae7790e8a759e85","upstream-sync\u002Fwork\u002Fecc\u002Fdocs\u002Fja-JP\u002Fskills\u002Fcontinuous-learning",0,"https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FAgention","https:\u002F\u002Fgithub.com\u002Foabdelmaksoud","https:\u002F\u002Fwww.linkedin.com\u002Fin\u002Fo-abdelmaksoud\u002F","Full-Stack Engineer | AI Systems Architect | Building autonomous multi-agent systems","2026-03-08 21:23:03",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add oabdelmaksoud\u002FAgention --skill continuous-learning",{"tool":41,"command":42},"bunx","bunx skills add oabdelmaksoud\u002FAgention --skill continuous-learning",{"tool":44,"command":45},"pnpm","pnpm dlx skills add oabdelmaksoud\u002FAgention --skill continuous-learning","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FAgention\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fdocs\u002Fja-JP\u002Fskills\u002Fcontinuous-learning\u002FSKILL.md",true,[],[50,74,88,121,147,167],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":61,"publishedAt":21},"01M6G2QFCBNBYAJF2KTK85G9A6","visa-doc-translate","Translate visa application documents (images) to English and create a bilingual PDF with original and translation","https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FAgention\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Fvisa-doc-translate\u002FSKILL.md",[56],{"categoryNo":57,"categoryName":58,"taxonomyType":59,"taxonomyTypeDesc":60},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[62,63,64,65,66,67,68,69,70,71,72,73],"translate","doc","visa doc translate","bilingual","with","english","application","PDF","translation","documents","create","images",{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":21},"01M6G2QB09TSK6BY4ME5X20EVQ","verification-loop","A comprehensive verification system for Claude Code sessions.","https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FAgention\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[81,82,83,84,85,86,87],"verification","loop","verification loop","sessions","code","claude code sessions","system",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":105,"publishedAt":21},"01M6G2Q6V2F7G03VAAF27FXPJR","tdd-workflow","Use this skill when writing new features, fixing bugs, or refactoring code. Enforces test-driven development with 80%+ coverage including unit, integration, and E2E tests.","https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FAgention\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Ftdd-workflow\u002FSKILL.md",[94,97,100],{"categoryNo":95,"categoryName":96,"taxonomyType":59,"taxonomyTypeDesc":60},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":98,"categoryName":99,"taxonomyType":59,"taxonomyTypeDesc":60},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":101,"categoryName":102,"taxonomyType":103,"taxonomyTypeDesc":104},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[106,107,108,109,110,111,112,113,114,85,115,116,117,118,66,119,120],"workflow","tdd","tdd workflow","use","unit","coverage","refactoring","e2e","integration","development","e2e tests","tests","driven","test","writing",{"skillNo":122,"name":123,"nameZh":6,"description":124,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":125,"categories":126,"keywords":127,"publishedAt":21},"01M6G2Q359YJRWAR2PFCEQAXF3","swiftui-patterns","SwiftUI architecture patterns, state management with @Observable, view composition, navigation, performance optimization, and modern iOS\u002FmacOS UI best practices.","https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FAgention\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Fswiftui-patterns\u002FSKILL.md",[],[128,129,130,131,132,133,134,135,136,137,138,139,140,141,142,143,144,145,146,66],"patterns","swiftui","swiftui patterns","architecture","macos","performance","state management","best practices","state","ui","Optimization","ios","architecture patterns","Composition","performance optimization","view","management","swiftui architecture","navigation",{"skillNo":148,"name":149,"nameZh":6,"description":150,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":151,"categories":152,"keywords":154,"publishedAt":21},"01M6G2PY8B2FWZTWPZ84H83Y7C","swift-protocol-di-testing","Protocol-based dependency injection for testable Swift code — mock file system, network, and external APIs using focused protocols and Swift Testing.","https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FAgention\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Fswift-protocol-di-testing\u002FSKILL.md",[153],{"categoryNo":95,"categoryName":96,"taxonomyType":59,"taxonomyTypeDesc":60},[155,156,157,158,85,159,160,161,162,87,163,164,165,166],"swift protocol di testing","protocol","swift","testing","protocols","file","network","injection","dependency","swift testing","dependency injection","mock",{"skillNo":168,"name":169,"nameZh":6,"description":170,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":171,"categories":172,"keywords":173,"publishedAt":21},"01M6G2PSCN2GXV9FFZDRRRWVB6","swift-concurrency-6-2","Swift 6.2 Approachable Concurrency — single-threaded by default, @concurrent for explicit background offloading, isolated conformances for main actor types.","https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FAgention\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Fswift-concurrency-6-2\u002FSKILL.md",[],[174,175,176,157,177,26,178],"concurrency","swift concurrency","swift concurrency 6 2","default","types"]