[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6G2DV6HA790FC3CBPPD8A3D":3,"skill-same:01M6G2DV6HA790FC3CBPPD8A3D":61},{"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":32,"linkOnly":33,"markdownContent":34,"markdownBody":35,"frontMatter":36,"refName":38,"commitSha":39,"skillDirectory":40,"forksCount":41,"repositoryHtmlUrl":42,"repositoryHomepageUrl":6,"ownerHtmlUrl":43,"ownerBlogUrl":44,"ownerDescription":45,"updatedAt":46,"install":47,"resources":60},"01M6G2DV6HA790FC3CBPPD8A3D","continuous-learning-v2",null,"Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills\u002Fcommands\u002Fagents.","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\u002Fzh-TW\u002Fskills\u002Fcontinuous-learning-v2\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31],"learning","continuous learning","continuous learning v2","sessions","system","hooks","confidence scoring","scoring","commands","via","learning system","with","atomic","2026-11-10 10:12:30",false,"---\nname: continuous-learning-v2\ndescription: Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills\u002Fcommands\u002Fagents.\nversion: 2.0.0\n---\n\n# 持續學習 v2 - 基於本能的架構\n\n進階學習系統，透過原子「本能」（帶信心評分的小型學習行為）將你的 Claude Code 工作階段轉化為可重用知識。\n\n## v2 的新功能\n\n| 功能 | v1 | v2 |\n|------|----|----|\n| 觀察 | Stop hook（工作階段結束） | PreToolUse\u002FPostToolUse（100% 可靠） |\n| 分析 | 主要上下文 | 背景 agent（Haiku） |\n| 粒度 | 完整技能 | 原子「本能」 |\n| 信心 | 無 | 0.3-0.9 加權 |\n| 演化 | 直接到技能 | 本能 → 聚類 → 技能\u002F指令\u002Fagent |\n| 分享 | 無 | 匯出\u002F匯入本能 |\n\n## 本能模型\n\n本能是一個小型學習行為：\n\n```yaml\n---\nid: prefer-functional-style\ntrigger: \"when writing new functions\"\nconfidence: 0.7\ndomain: \"code-style\"\nsource: \"session-observation\"\n---\n\n# 偏好函式風格\n\n## 動作\n適當時使用函式模式而非類別。\n\n## 證據\n- 觀察到 5 次函式模式偏好\n- 使用者在 2025-01-15 將基於類別的方法修正為函式\n```\n\n**屬性：**\n- **原子性** — 一個觸發器，一個動作\n- **信心加權** — 0.3 = 試探性，0.9 = 近乎確定\n- **領域標記** — code-style、testing、git、debugging、workflow 等\n- **證據支持** — 追蹤建立它的觀察\n\n## 運作方式\n\n```\n工作階段活動\n      │\n      │ Hooks 捕獲提示 + 工具使用（100% 可靠）\n      ▼\n┌─────────────────────────────────────────┐\n│         observations.jsonl              │\n│   （提示、工具呼叫、結果）               │\n└─────────────────────────────────────────┘\n      │\n      │ Observer agent 讀取（背景、Haiku）\n      ▼\n┌─────────────────────────────────────────┐\n│          模式偵測                        │\n│   • 使用者修正 → 本能                   │\n│   • 錯誤解決 → 本能                     │\n│   • 重複工作流程 → 本能                 │\n└─────────────────────────────────────────┘\n      │\n      │ 建立\u002F更新\n      ▼\n┌─────────────────────────────────────────┐\n│         instincts\u002Fpersonal\u002F             │\n│   • prefer-functional.md (0.7)          │\n│   • always-test-first.md (0.9)          │\n│   • use-zod-validation.md (0.6)         │\n└─────────────────────────────────────────┘\n      │\n      │ \u002Fevolve 聚類\n      ▼\n┌─────────────────────────────────────────┐\n│              evolved\u002F                   │\n│   • commands\u002Fnew-feature.md             │\n│   • skills\u002Ftesting-workflow.md          │\n│   • agents\u002Frefactor-specialist.md       │\n└─────────────────────────────────────────┘\n```\n\n## 快速開始\n\n### 1. 啟用觀察 Hooks\n\n新增到你的 `~\u002F.claude\u002Fsettings.json`：\n\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [{\n      \"matcher\": \"*\",\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"~\u002F.claude\u002Fskills\u002Fcontinuous-learning-v2\u002Fhooks\u002Fobserve.sh pre\"\n      }]\n    }],\n    \"PostToolUse\": [{\n      \"matcher\": \"*\",\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"~\u002F.claude\u002Fskills\u002Fcontinuous-learning-v2\u002Fhooks\u002Fobserve.sh post\"\n      }]\n    }]\n  }\n}\n```\n\n### 2. 初始化目錄結構\n\n```bash\nmkdir -p ~\u002F.claude\u002Fhomunculus\u002F{instincts\u002F{personal,inherited},evolved\u002F{agents,skills,commands}}\ntouch ~\u002F.claude\u002Fhomunculus\u002Fobservations.jsonl\n```\n\n### 3. 執行 Observer Agent（可選）\n\n觀察者可以在背景執行並分析觀察：\n\n```bash\n# 啟動背景觀察者\n~\u002F.claude\u002Fskills\u002Fcontinuous-learning-v2\u002Fagents\u002Fstart-observer.sh\n```\n\n## 指令\n\n| 指令 | 描述 |\n|------|------|\n| `\u002Finstinct-status` | 顯示所有學習本能及其信心 |\n| `\u002Fevolve` | 將相關本能聚類為技能\u002F指令 |\n| `\u002Finstinct-export` | 匯出本能以分享 |\n| `\u002Finstinct-import \u003Cfile>` | 從他人匯入本能 |\n\n## 設定\n\n編輯 `config.json`：\n\n```json\n{\n  \"version\": \"2.0\",\n  \"observation\": {\n    \"enabled\": true,\n    \"store_path\": \"~\u002F.claude\u002Fhomunculus\u002Fobservations.jsonl\",\n    \"max_file_size_mb\": 10,\n    \"archive_after_days\": 7\n  },\n  \"instincts\": {\n    \"personal_path\": \"~\u002F.claude\u002Fhomunculus\u002Finstincts\u002Fpersonal\u002F\",\n    \"inherited_path\": \"~\u002F.claude\u002Fhomunculus\u002Finstincts\u002Finherited\u002F\",\n    \"min_confidence\": 0.3,\n    \"auto_approve_threshold\": 0.7,\n    \"confidence_decay_rate\": 0.05\n  },\n  \"observer\": {\n    \"enabled\": true,\n    \"model\": \"haiku\",\n    \"run_interval_minutes\": 5,\n    \"patterns_to_detect\": [\n      \"user_corrections\",\n      \"error_resolutions\",\n      \"repeated_workflows\",\n      \"tool_preferences\"\n    ]\n  },\n  \"evolution\": {\n    \"cluster_threshold\": 3,\n    \"evolved_path\": \"~\u002F.claude\u002Fhomunculus\u002Fevolved\u002F\"\n  }\n}\n```\n\n## 檔案結構\n\n```\n~\u002F.claude\u002Fhomunculus\u002F\n├── identity.json           # 你的個人資料、技術水平\n├── observations.jsonl      # 當前工作階段觀察\n├── observations.archive\u002F   # 已處理觀察\n├── instincts\u002F\n│   ├── personal\u002F           # 自動學習本能\n│   └── inherited\u002F          # 從他人匯入\n└── evolved\u002F\n    ├── agents\u002F             # 產生的專業 agents\n    ├── skills\u002F             # 產生的技能\n    └── commands\u002F           # 產生的指令\n```\n\n## 與 Skill Creator 整合\n\n當你使用 [Skill Creator GitHub App](https:\u002F\u002Fskill-creator.app) 時，它現在產生**兩者**：\n- 傳統 SKILL.md 檔案（用於向後相容）\n- 本能集合（用於 v2 學習系統）\n\n從倉庫分析的本能有 `source: \"repo-analysis\"` 並包含來源倉庫 URL。\n\n## 信心評分\n\n信心隨時間演化：\n\n| 分數 | 意義 | 行為 |\n|------|------|------|\n| 0.3 | 試探性 | 建議但不強制 |\n| 0.5 | 中等 | 相關時應用 |\n| 0.7 | 強烈 | 自動批准應用 |\n| 0.9 | 近乎確定 | 核心行為 |\n\n**信心增加**當：\n- 重複觀察到模式\n- 使用者不修正建議行為\n- 來自其他來源的類似本能同意\n\n**信心減少**當：\n- 使用者明確修正行為\n- 長期未觀察到模式\n- 出現矛盾證據\n\n## 為何 Hooks vs Skills 用於觀察？\n\n> \"v1 依賴技能進行觀察。技能是機率性的——它們根據 Claude 的判斷觸發約 50-80% 的時間。\"\n\nHooks **100% 的時間**確定性地觸發。這意味著：\n- 每個工具呼叫都被觀察\n- 無模式被遺漏\n- 學習是全面的\n\n## 向後相容性\n\nv2 完全相容 v1：\n- 現有 `~\u002F.claude\u002Fskills\u002Flearned\u002F` 技能仍可運作\n- Stop hook 仍執行（但現在也餵入 v2）\n- 漸進遷移路徑：兩者並行執行\n\n## 隱私\n\n- 觀察保持在你的機器**本機**\n- 只有**本能**（模式）可被匯出\n- 不會分享實際程式碼或對話內容\n- 你控制匯出內容\n\n## 相關\n\n- [Skill Creator](https:\u002F\u002Fskill-creator.app) - 從倉庫歷史產生本能\n- Homunculus - 啟發 v2 架構的社區專案（原子觀察、信心評分、本能演化管線）\n- [Longform Guide](https:\u002F\u002Fx.com\u002Faffaanmustafa\u002Fstatus\u002F2014040193557471352) - 持續學習章節\n\n---\n\n*基於本能的學習：一次一個觀察，教導 Claude 你的模式。*\n","# 持續學習 v2 - 基於本能的架構\n\n進階學習系統，透過原子「本能」（帶信心評分的小型學習行為）將你的 Claude Code 工作階段轉化為可重用知識。\n\n## v2 的新功能\n\n| 功能 | v1 | v2 |\n|------|----|----|\n| 觀察 | Stop hook（工作階段結束） | PreToolUse\u002FPostToolUse（100% 可靠） |\n| 分析 | 主要上下文 | 背景 agent（Haiku） |\n| 粒度 | 完整技能 | 原子「本能」 |\n| 信心 | 無 | 0.3-0.9 加權 |\n| 演化 | 直接到技能 | 本能 → 聚類 → 技能\u002F指令\u002Fagent |\n| 分享 | 無 | 匯出\u002F匯入本能 |\n\n## 本能模型\n\n本能是一個小型學習行為：\n\n```yaml\n---\nid: prefer-functional-style\ntrigger: \"when writing new functions\"\nconfidence: 0.7\ndomain: \"code-style\"\nsource: \"session-observation\"\n---\n\n# 偏好函式風格\n\n## 動作\n適當時使用函式模式而非類別。\n\n## 證據\n- 觀察到 5 次函式模式偏好\n- 使用者在 2025-01-15 將基於類別的方法修正為函式\n```\n\n**屬性：**\n- **原子性** — 一個觸發器，一個動作\n- **信心加權** — 0.3 = 試探性，0.9 = 近乎確定\n- **領域標記** — code-style、testing、git、debugging、workflow 等\n- **證據支持** — 追蹤建立它的觀察\n\n## 運作方式\n\n```\n工作階段活動\n      │\n      │ Hooks 捕獲提示 + 工具使用（100% 可靠）\n      ▼\n┌─────────────────────────────────────────┐\n│         observations.jsonl              │\n│   （提示、工具呼叫、結果）               │\n└─────────────────────────────────────────┘\n      │\n      │ Observer agent 讀取（背景、Haiku）\n      ▼\n┌─────────────────────────────────────────┐\n│          模式偵測                        │\n│   • 使用者修正 → 本能                   │\n│   • 錯誤解決 → 本能                     │\n│   • 重複工作流程 → 本能                 │\n└─────────────────────────────────────────┘\n      │\n      │ 建立\u002F更新\n      ▼\n┌─────────────────────────────────────────┐\n│         instincts\u002Fpersonal\u002F             │\n│   • prefer-functional.md (0.7)          │\n│   • always-test-first.md (0.9)          │\n│   • use-zod-validation.md (0.6)         │\n└─────────────────────────────────────────┘\n      │\n      │ \u002Fevolve 聚類\n      ▼\n┌─────────────────────────────────────────┐\n│              evolved\u002F                   │\n│   • commands\u002Fnew-feature.md             │\n│   • skills\u002Ftesting-workflow.md          │\n│   • agents\u002Frefactor-specialist.md       │\n└─────────────────────────────────────────┘\n```\n\n## 快速開始\n\n### 1. 啟用觀察 Hooks\n\n新增到你的 `~\u002F.claude\u002Fsettings.json`：\n\n```json\n{\n  \"hooks\": {\n    \"PreToolUse\": [{\n      \"matcher\": \"*\",\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"~\u002F.claude\u002Fskills\u002Fcontinuous-learning-v2\u002Fhooks\u002Fobserve.sh pre\"\n      }]\n    }],\n    \"PostToolUse\": [{\n      \"matcher\": \"*\",\n      \"hooks\": [{\n        \"type\": \"command\",\n        \"command\": \"~\u002F.claude\u002Fskills\u002Fcontinuous-learning-v2\u002Fhooks\u002Fobserve.sh post\"\n      }]\n    }]\n  }\n}\n```\n\n### 2. 初始化目錄結構\n\n```bash\nmkdir -p ~\u002F.claude\u002Fhomunculus\u002F{instincts\u002F{personal,inherited},evolved\u002F{agents,skills,commands}}\ntouch ~\u002F.claude\u002Fhomunculus\u002Fobservations.jsonl\n```\n\n### 3. 執行 Observer Agent（可選）\n\n觀察者可以在背景執行並分析觀察：\n\n```bash\n# 啟動背景觀察者\n~\u002F.claude\u002Fskills\u002Fcontinuous-learning-v2\u002Fagents\u002Fstart-observer.sh\n```\n\n## 指令\n\n| 指令 | 描述 |\n|------|------|\n| `\u002Finstinct-status` | 顯示所有學習本能及其信心 |\n| `\u002Fevolve` | 將相關本能聚類為技能\u002F指令 |\n| `\u002Finstinct-export` | 匯出本能以分享 |\n| `\u002Finstinct-import \u003Cfile>` | 從他人匯入本能 |\n\n## 設定\n\n編輯 `config.json`：\n\n```json\n{\n  \"version\": \"2.0\",\n  \"observation\": {\n    \"enabled\": true,\n    \"store_path\": \"~\u002F.claude\u002Fhomunculus\u002Fobservations.jsonl\",\n    \"max_file_size_mb\": 10,\n    \"archive_after_days\": 7\n  },\n  \"instincts\": {\n    \"personal_path\": \"~\u002F.claude\u002Fhomunculus\u002Finstincts\u002Fpersonal\u002F\",\n    \"inherited_path\": \"~\u002F.claude\u002Fhomunculus\u002Finstincts\u002Finherited\u002F\",\n    \"min_confidence\": 0.3,\n    \"auto_approve_threshold\": 0.7,\n    \"confidence_decay_rate\": 0.05\n  },\n  \"observer\": {\n    \"enabled\": true,\n    \"model\": \"haiku\",\n    \"run_interval_minutes\": 5,\n    \"patterns_to_detect\": [\n      \"user_corrections\",\n      \"error_resolutions\",\n      \"repeated_workflows\",\n      \"tool_preferences\"\n    ]\n  },\n  \"evolution\": {\n    \"cluster_threshold\": 3,\n    \"evolved_path\": \"~\u002F.claude\u002Fhomunculus\u002Fevolved\u002F\"\n  }\n}\n```\n\n## 檔案結構\n\n```\n~\u002F.claude\u002Fhomunculus\u002F\n├── identity.json           # 你的個人資料、技術水平\n├── observations.jsonl      # 當前工作階段觀察\n├── observations.archive\u002F   # 已處理觀察\n├── instincts\u002F\n│   ├── personal\u002F           # 自動學習本能\n│   └── inherited\u002F          # 從他人匯入\n└── evolved\u002F\n    ├── agents\u002F             # 產生的專業 agents\n    ├── skills\u002F             # 產生的技能\n    └── commands\u002F           # 產生的指令\n```\n\n## 與 Skill Creator 整合\n\n當你使用 [Skill Creator GitHub App](https:\u002F\u002Fskill-creator.app) 時，它現在產生**兩者**：\n- 傳統 SKILL.md 檔案（用於向後相容）\n- 本能集合（用於 v2 學習系統）\n\n從倉庫分析的本能有 `source: \"repo-analysis\"` 並包含來源倉庫 URL。\n\n## 信心評分\n\n信心隨時間演化：\n\n| 分數 | 意義 | 行為 |\n|------|------|------|\n| 0.3 | 試探性 | 建議但不強制 |\n| 0.5 | 中等 | 相關時應用 |\n| 0.7 | 強烈 | 自動批准應用 |\n| 0.9 | 近乎確定 | 核心行為 |\n\n**信心增加**當：\n- 重複觀察到模式\n- 使用者不修正建議行為\n- 來自其他來源的類似本能同意\n\n**信心減少**當：\n- 使用者明確修正行為\n- 長期未觀察到模式\n- 出現矛盾證據\n\n## 為何 Hooks vs Skills 用於觀察？\n\n> \"v1 依賴技能進行觀察。技能是機率性的——它們根據 Claude 的判斷觸發約 50-80% 的時間。\"\n\nHooks **100% 的時間**確定性地觸發。這意味著：\n- 每個工具呼叫都被觀察\n- 無模式被遺漏\n- 學習是全面的\n\n## 向後相容性\n\nv2 完全相容 v1：\n- 現有 `~\u002F.claude\u002Fskills\u002Flearned\u002F` 技能仍可運作\n- Stop hook 仍執行（但現在也餵入 v2）\n- 漸進遷移路徑：兩者並行執行\n\n## 隱私\n\n- 觀察保持在你的機器**本機**\n- 只有**本能**（模式）可被匯出\n- 不會分享實際程式碼或對話內容\n- 你控制匯出內容\n\n## 相關\n\n- [Skill Creator](https:\u002F\u002Fskill-creator.app) - 從倉庫歷史產生本能\n- Homunculus - 啟發 v2 架構的社區專案（原子觀察、信心評分、本能演化管線）\n- [Longform Guide](https:\u002F\u002Fx.com\u002Faffaanmustafa\u002Fstatus\u002F2014040193557471352) - 持續學習章節\n\n---\n\n*基於本能的學習：一次一個觀察，教導 Claude 你的模式。*\n",{"name":5,"version":37,"description":7},"2.0.0","main","a318f48de3c5718e8ea2e9f6fae7790e8a759e85","upstream-sync\u002Fwork\u002Fecc\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fcontinuous-learning-v2",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":48,"prompt":58,"zipAvailable":59},[49,52,55],{"tool":50,"command":51},"npx","npx skills add oabdelmaksoud\u002FAgention --skill continuous-learning-v2",{"tool":53,"command":54},"bunx","bunx skills add oabdelmaksoud\u002FAgention --skill continuous-learning-v2",{"tool":56,"command":57},"pnpm","pnpm dlx skills add oabdelmaksoud\u002FAgention --skill continuous-learning-v2","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FAgention\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fcontinuous-learning-v2\u002FSKILL.md",true,[],[62,85,97,130,156,176],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":73,"publishedAt":32},"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",[68],{"categoryNo":69,"categoryName":70,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[74,75,76,77,30,78,79,80,81,82,83,84],"translate","doc","visa doc translate","bilingual","english","application","PDF","translation","documents","create","images",{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":91,"publishedAt":32},"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",[],[92,93,94,22,95,96,23],"verification","loop","verification loop","code","claude code sessions",{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":101,"categories":102,"keywords":114,"publishedAt":32},"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",[103,106,109],{"categoryNo":104,"categoryName":105,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":107,"categoryName":108,"taxonomyType":71,"taxonomyTypeDesc":72},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[115,116,117,118,119,120,121,122,123,95,124,125,126,127,30,128,129],"workflow","tdd","tdd workflow","use","unit","coverage","refactoring","e2e","integration","development","e2e tests","tests","driven","test","writing",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":136,"publishedAt":32},"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",[],[137,138,139,140,141,142,143,144,145,146,147,148,149,150,151,152,153,154,155,30],"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":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":163,"publishedAt":32},"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",[162],{"categoryNo":104,"categoryName":105,"taxonomyType":71,"taxonomyTypeDesc":72},[164,165,166,167,95,168,169,170,171,23,172,173,174,175],"swift protocol di testing","protocol","swift","testing","protocols","file","network","injection","dependency","swift testing","dependency injection","mock",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":182,"publishedAt":32},"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",[],[183,184,185,166,186,38,187],"concurrency","swift concurrency","swift concurrency 6 2","default","types"]