[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6D81PPQQWMXVX4FNP8NFY7G":3,"skill-same:01M6D81PPQQWMXVX4FNP8NFY7G":63},{"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":34,"linkOnly":35,"markdownContent":36,"markdownBody":37,"frontMatter":38,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":47,"updatedAt":48,"install":49,"resources":62},"01M6D81PPQQWMXVX4FNP8NFY7G","eval-harness",null,"Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles","oabdelmaksoud\u002FSuperClaw","oabdelmaksoud","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F50699149?v=4","01M6D5CVVN778ZCDP1WHS816SP","Omar Abdelmaksoud","01M6D5CW1RHNSKCJR85GJACBFT",2,"MIT","https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FSuperClaw\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fdocs\u002Fzh-TW\u002Fskills\u002Feval-harness\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33],"harness","eval harness","eval","sessions","evaluation framework","development","code","framework","Evaluation","claude code sessions","Bash","grep","read","write","edit","2026-11-10 10:12:30",false,"---\nname: eval-harness\ndescription: Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles\ntools: Read, Write, Edit, Bash, Grep, Glob\n---\n\n# Eval Harness 技能\n\nClaude Code 工作階段的正式評估框架，實作 eval 驅動開發（EDD）原則。\n\n## 理念\n\nEval 驅動開發將 evals 視為「AI 開發的單元測試」：\n- 在實作前定義預期行為\n- 開發期間持續執行 evals\n- 每次變更追蹤回歸\n- 使用 pass@k 指標進行可靠性測量\n\n## Eval 類型\n\n### 能力 Evals\n測試 Claude 是否能做到以前做不到的事：\n```markdown\n[CAPABILITY EVAL: feature-name]\n任務：Claude 應完成什麼的描述\n成功標準：\n  - [ ] 標準 1\n  - [ ] 標準 2\n  - [ ] 標準 3\n預期輸出：預期結果描述\n```\n\n### 回歸 Evals\n確保變更不會破壞現有功能：\n```markdown\n[REGRESSION EVAL: feature-name]\n基準：SHA 或檢查點名稱\n測試：\n  - existing-test-1: PASS\u002FFAIL\n  - existing-test-2: PASS\u002FFAIL\n  - existing-test-3: PASS\u002FFAIL\n結果：X\u002FY 通過（先前為 Y\u002FY）\n```\n\n## 評分器類型\n\n### 1. 基於程式碼的評分器\n使用程式碼的確定性檢查：\n```bash\n# 檢查檔案是否包含預期模式\ngrep -q \"export function handleAuth\" src\u002Fauth.ts && echo \"PASS\" || echo \"FAIL\"\n\n# 檢查測試是否通過\nnpm test -- --testPathPattern=\"auth\" && echo \"PASS\" || echo \"FAIL\"\n\n# 檢查建置是否成功\nnpm run build && echo \"PASS\" || echo \"FAIL\"\n```\n\n### 2. 基於模型的評分器\n使用 Claude 評估開放式輸出：\n```markdown\n[MODEL GRADER PROMPT]\n評估以下程式碼變更：\n1. 它是否解決了陳述的問題？\n2. 結構是否良好？\n3. 邊界案例是否被處理？\n4. 錯誤處理是否適當？\n\n分數：1-5（1=差，5=優秀）\n理由：[解釋]\n```\n\n### 3. 人工評分器\n標記為手動審查：\n```markdown\n[HUMAN REVIEW REQUIRED]\n變更：變更內容的描述\n理由：為何需要人工審查\n風險等級：LOW\u002FMEDIUM\u002FHIGH\n```\n\n## 指標\n\n### pass@k\n「k 次嘗試中至少一次成功」\n- pass@1：第一次嘗試成功率\n- pass@3：3 次嘗試內成功\n- 典型目標：pass@3 > 90%\n\n### pass^k\n「所有 k 次試驗都成功」\n- 更高的可靠性標準\n- pass^3：連續 3 次成功\n- 用於關鍵路徑\n\n## Eval 工作流程\n\n### 1. 定義（編碼前）\n```markdown\n## EVAL 定義：feature-xyz\n\n### 能力 Evals\n1. 可以建立新使用者帳戶\n2. 可以驗證電子郵件格式\n3. 可以安全地雜湊密碼\n\n### 回歸 Evals\n1. 現有登入仍可運作\n2. 工作階段管理未變更\n3. 登出流程完整\n\n### 成功指標\n- 能力 evals 的 pass@3 > 90%\n- 回歸 evals 的 pass^3 = 100%\n```\n\n### 2. 實作\n撰寫程式碼以通過定義的 evals。\n\n### 3. 評估\n```bash\n# 執行能力 evals\n[執行每個能力 eval，記錄 PASS\u002FFAIL]\n\n# 執行回歸 evals\nnpm test -- --testPathPattern=\"existing\"\n\n# 產生報告\n```\n\n### 4. 報告\n```markdown\nEVAL 報告：feature-xyz\n========================\n\n能力 Evals：\n  create-user:     PASS (pass@1)\n  validate-email:  PASS (pass@2)\n  hash-password:   PASS (pass@1)\n  整體：           3\u002F3 通過\n\n回歸 Evals：\n  login-flow:      PASS\n  session-mgmt:    PASS\n  logout-flow:     PASS\n  整體：           3\u002F3 通過\n\n指標：\n  pass@1: 67% (2\u002F3)\n  pass@3: 100% (3\u002F3)\n\n狀態：準備審查\n```\n\n## 整合模式\n\n### 實作前\n```\n\u002Feval define feature-name\n```\n在 `.claude\u002Fevals\u002Ffeature-name.md` 建立 eval 定義檔案\n\n### 實作期間\n```\n\u002Feval check feature-name\n```\n執行當前 evals 並報告狀態\n\n### 實作後\n```\n\u002Feval report feature-name\n```\n產生完整 eval 報告\n\n## Eval 儲存\n\n在專案中儲存 evals：\n```\n.claude\u002F\n  evals\u002F\n    feature-xyz.md      # Eval 定義\n    feature-xyz.log     # Eval 執行歷史\n    baseline.json       # 回歸基準\n```\n\n## 最佳實務\n\n1. **編碼前定義 evals** - 強制清楚思考成功標準\n2. **頻繁執行 evals** - 及早捕捉回歸\n3. **隨時間追蹤 pass@k** - 監控可靠性趨勢\n4. **可能時使用程式碼評分器** - 確定性 > 機率性\n5. **安全性需人工審查** - 永遠不要完全自動化安全檢查\n6. **保持 evals 快速** - 慢 evals 不會被執行\n7. **與程式碼一起版本化 evals** - Evals 是一等工件\n\n## 範例：新增認證\n\n```markdown\n## EVAL：add-authentication\n\n### 階段 1：定義（10 分鐘）\n能力 Evals：\n- [ ] 使用者可以用電子郵件\u002F密碼註冊\n- [ ] 使用者可以用有效憑證登入\n- [ ] 無效憑證被拒絕並顯示適當錯誤\n- [ ] 工作階段在頁面重新載入後持續\n- [ ] 登出清除工作階段\n\n回歸 Evals：\n- [ ] 公開路由仍可存取\n- [ ] API 回應未變更\n- [ ] 資料庫 schema 相容\n\n### 階段 2：實作（視情況而定）\n[撰寫程式碼]\n\n### 階段 3：評估\n執行：\u002Feval check add-authentication\n\n### 階段 4：報告\nEVAL 報告：add-authentication\n==============================\n能力：5\u002F5 通過（pass@3：100%）\n回歸：3\u002F3 通過（pass^3：100%）\n狀態：準備發佈\n```\n","# Eval Harness 技能\n\nClaude Code 工作階段的正式評估框架，實作 eval 驅動開發（EDD）原則。\n\n## 理念\n\nEval 驅動開發將 evals 視為「AI 開發的單元測試」：\n- 在實作前定義預期行為\n- 開發期間持續執行 evals\n- 每次變更追蹤回歸\n- 使用 pass@k 指標進行可靠性測量\n\n## Eval 類型\n\n### 能力 Evals\n測試 Claude 是否能做到以前做不到的事：\n```markdown\n[CAPABILITY EVAL: feature-name]\n任務：Claude 應完成什麼的描述\n成功標準：\n  - [ ] 標準 1\n  - [ ] 標準 2\n  - [ ] 標準 3\n預期輸出：預期結果描述\n```\n\n### 回歸 Evals\n確保變更不會破壞現有功能：\n```markdown\n[REGRESSION EVAL: feature-name]\n基準：SHA 或檢查點名稱\n測試：\n  - existing-test-1: PASS\u002FFAIL\n  - existing-test-2: PASS\u002FFAIL\n  - existing-test-3: PASS\u002FFAIL\n結果：X\u002FY 通過（先前為 Y\u002FY）\n```\n\n## 評分器類型\n\n### 1. 基於程式碼的評分器\n使用程式碼的確定性檢查：\n```bash\n# 檢查檔案是否包含預期模式\ngrep -q \"export function handleAuth\" src\u002Fauth.ts && echo \"PASS\" || echo \"FAIL\"\n\n# 檢查測試是否通過\nnpm test -- --testPathPattern=\"auth\" && echo \"PASS\" || echo \"FAIL\"\n\n# 檢查建置是否成功\nnpm run build && echo \"PASS\" || echo \"FAIL\"\n```\n\n### 2. 基於模型的評分器\n使用 Claude 評估開放式輸出：\n```markdown\n[MODEL GRADER PROMPT]\n評估以下程式碼變更：\n1. 它是否解決了陳述的問題？\n2. 結構是否良好？\n3. 邊界案例是否被處理？\n4. 錯誤處理是否適當？\n\n分數：1-5（1=差，5=優秀）\n理由：[解釋]\n```\n\n### 3. 人工評分器\n標記為手動審查：\n```markdown\n[HUMAN REVIEW REQUIRED]\n變更：變更內容的描述\n理由：為何需要人工審查\n風險等級：LOW\u002FMEDIUM\u002FHIGH\n```\n\n## 指標\n\n### pass@k\n「k 次嘗試中至少一次成功」\n- pass@1：第一次嘗試成功率\n- pass@3：3 次嘗試內成功\n- 典型目標：pass@3 > 90%\n\n### pass^k\n「所有 k 次試驗都成功」\n- 更高的可靠性標準\n- pass^3：連續 3 次成功\n- 用於關鍵路徑\n\n## Eval 工作流程\n\n### 1. 定義（編碼前）\n```markdown\n## EVAL 定義：feature-xyz\n\n### 能力 Evals\n1. 可以建立新使用者帳戶\n2. 可以驗證電子郵件格式\n3. 可以安全地雜湊密碼\n\n### 回歸 Evals\n1. 現有登入仍可運作\n2. 工作階段管理未變更\n3. 登出流程完整\n\n### 成功指標\n- 能力 evals 的 pass@3 > 90%\n- 回歸 evals 的 pass^3 = 100%\n```\n\n### 2. 實作\n撰寫程式碼以通過定義的 evals。\n\n### 3. 評估\n```bash\n# 執行能力 evals\n[執行每個能力 eval，記錄 PASS\u002FFAIL]\n\n# 執行回歸 evals\nnpm test -- --testPathPattern=\"existing\"\n\n# 產生報告\n```\n\n### 4. 報告\n```markdown\nEVAL 報告：feature-xyz\n========================\n\n能力 Evals：\n  create-user:     PASS (pass@1)\n  validate-email:  PASS (pass@2)\n  hash-password:   PASS (pass@1)\n  整體：           3\u002F3 通過\n\n回歸 Evals：\n  login-flow:      PASS\n  session-mgmt:    PASS\n  logout-flow:     PASS\n  整體：           3\u002F3 通過\n\n指標：\n  pass@1: 67% (2\u002F3)\n  pass@3: 100% (3\u002F3)\n\n狀態：準備審查\n```\n\n## 整合模式\n\n### 實作前\n```\n\u002Feval define feature-name\n```\n在 `.claude\u002Fevals\u002Ffeature-name.md` 建立 eval 定義檔案\n\n### 實作期間\n```\n\u002Feval check feature-name\n```\n執行當前 evals 並報告狀態\n\n### 實作後\n```\n\u002Feval report feature-name\n```\n產生完整 eval 報告\n\n## Eval 儲存\n\n在專案中儲存 evals：\n```\n.claude\u002F\n  evals\u002F\n    feature-xyz.md      # Eval 定義\n    feature-xyz.log     # Eval 執行歷史\n    baseline.json       # 回歸基準\n```\n\n## 最佳實務\n\n1. **編碼前定義 evals** - 強制清楚思考成功標準\n2. **頻繁執行 evals** - 及早捕捉回歸\n3. **隨時間追蹤 pass@k** - 監控可靠性趨勢\n4. **可能時使用程式碼評分器** - 確定性 > 機率性\n5. **安全性需人工審查** - 永遠不要完全自動化安全檢查\n6. **保持 evals 快速** - 慢 evals 不會被執行\n7. **與程式碼一起版本化 evals** - Evals 是一等工件\n\n## 範例：新增認證\n\n```markdown\n## EVAL：add-authentication\n\n### 階段 1：定義（10 分鐘）\n能力 Evals：\n- [ ] 使用者可以用電子郵件\u002F密碼註冊\n- [ ] 使用者可以用有效憑證登入\n- [ ] 無效憑證被拒絕並顯示適當錯誤\n- [ ] 工作階段在頁面重新載入後持續\n- [ ] 登出清除工作階段\n\n回歸 Evals：\n- [ ] 公開路由仍可存取\n- [ ] API 回應未變更\n- [ ] 資料庫 schema 相容\n\n### 階段 2：實作（視情況而定）\n[撰寫程式碼]\n\n### 階段 3：評估\n執行：\u002Feval check add-authentication\n\n### 階段 4：報告\nEVAL 報告：add-authentication\n==============================\n能力：5\u002F5 通過（pass@3：100%）\n回歸：3\u002F3 通過（pass^3：100%）\n狀態：準備發佈\n```\n",{"name":5,"tools":39,"description":7},"Read, Write, Edit, Bash, Grep, Glob","main","7b610356e36623652299fa2acb477ff821b1d920","upstream-sync\u002Fwork\u002Fecc\u002Fdocs\u002Fzh-TW\u002Fskills\u002Feval-harness",0,"https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FSuperClaw","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 21:12:53",{"source":8,"skillName":5,"commands":50,"prompt":60,"zipAvailable":61},[51,54,57],{"tool":52,"command":53},"npx","npx skills add oabdelmaksoud\u002FSuperClaw --skill eval-harness",{"tool":55,"command":56},"bunx","bunx skills add oabdelmaksoud\u002FSuperClaw --skill eval-harness",{"tool":58,"command":59},"pnpm","pnpm dlx skills add oabdelmaksoud\u002FSuperClaw --skill eval-harness","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FSuperClaw\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fdocs\u002Fzh-TW\u002Fskills\u002Feval-harness\u002FSKILL.md",true,[],[64,85,96,126,152,171],{"skillNo":65,"name":66,"nameZh":6,"description":67,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":68,"categories":69,"keywords":75,"publishedAt":34},"01M6D88QCPTBZVCRED0NZ1Y8K8","visa-doc-translate","Translate visa application documents (images) to English and create a bilingual PDF with original and translation","https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FSuperClaw\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Fvisa-doc-translate\u002FSKILL.md",[70],{"categoryNo":71,"categoryName":72,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000002","文档处理","SCENARIO","使用场景",[76,77,78,79,80,81,82,83,84],"translate","doc","visa doc translate","translation","application","create","images","PDF","documents",{"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":34},"01M6D88NBM95T3TFM50CYYAP65","verification-loop","A comprehensive verification system for Claude Code sessions.","https:\u002F\u002Fgithub.com\u002Foabdelmaksoud\u002FSuperClaw\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[92,93,94,22,25,28,95],"verification","loop","verification loop","system",{"skillNo":97,"name":98,"nameZh":6,"description":99,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":100,"categories":101,"keywords":113,"publishedAt":34},"01M6D88JFZ2P996GVRHJNSZSTM","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\u002FSuperClaw\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Ftdd-workflow\u002FSKILL.md",[102,105,108],{"categoryNo":103,"categoryName":104,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":106,"categoryName":107,"taxonomyType":73,"taxonomyTypeDesc":74},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":109,"categoryName":110,"taxonomyType":111,"taxonomyTypeDesc":112},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[114,115,116,117,118,119,25,24,120,121,122,123,124,125],"tdd","workflow","tdd workflow","e2e tests","e2e","integration","use","test","refactoring","coverage","tests","writing",{"skillNo":127,"name":128,"nameZh":6,"description":129,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":130,"categories":131,"keywords":132,"publishedAt":34},"01M6D88FTHRRSVJMXF2G7MQAK3","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\u002FSuperClaw\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Fswiftui-patterns\u002FSKILL.md",[],[133,134,135,136,137,138,139,140,141,142,143,144,145,146,147,148,149,150,151],"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":153,"name":154,"nameZh":6,"description":155,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":156,"categories":157,"keywords":159,"publishedAt":34},"01M6D88D527QTQT9DKHTRFN6EA","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\u002FSuperClaw\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Fswift-protocol-di-testing\u002FSKILL.md",[158],{"categoryNo":103,"categoryName":104,"taxonomyType":73,"taxonomyTypeDesc":74},[160,161,162,163,25,164,165,166,167,95,168,169,170],"swift protocol di testing","protocol","swift","testing","protocols","file","network","injection","dependency","swift testing","dependency injection",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":177,"publishedAt":34},"01M6D88AJW8H2QNWSW5ZY82R43","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\u002FSuperClaw\u002Fblob\u002Fmain\u002Fupstream-sync\u002Fwork\u002Fecc\u002Fskills\u002Fswift-concurrency-6-2\u002FSKILL.md",[],[178,179,162,180,181,40],"concurrency","swift concurrency","swift concurrency 6 2","default"]