[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M732551EAEPHX85VMZB3FD07":3,"skill-same:01M732551EAEPHX85VMZB3FD07":48},{"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":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":32,"updatedAt":33,"install":34,"resources":47},"01M732551EAEPHX85VMZB3FD07","eval-harness",null,"Formal evaluation framework for Claude Code sessions implementing eval-driven development (EDD) principles","SriramGandhiS\u002FSkills","SriramGandhiS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F211849986?v=4","01M72WQCW12BYX71C6WN584TTA","Sriram S","01M72WQCWTJ2RD0ET1X31AF1RC",1,"MIT","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Feval-harness\u002FSKILL.md",[],[],"2026-11-11 15:11:14",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":24,"description":7},"Read, Write, Edit, Bash, Grep, Glob","master","d6ca01da0f24a3b0e26e4a8b7b66cbd25d429f5d","web-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Feval-harness",0,"https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills","https:\u002F\u002Fgithub.com\u002FSriramGandhiS","https:\u002F\u002Fsriram.website\u002F","Curious guy who keeps tinkering until something works","2026-05-20 16:21:34",{"source":8,"skillName":5,"commands":35,"prompt":45,"zipAvailable":46},[36,39,42],{"tool":37,"command":38},"npx","npx skills add SriramGandhiS\u002FSkills --skill eval-harness",{"tool":40,"command":41},"bunx","bunx skills add SriramGandhiS\u002FSkills --skill eval-harness",{"tool":43,"command":44},"pnpm","pnpm dlx skills add SriramGandhiS\u002FSkills --skill eval-harness","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Feval-harness\u002FSKILL.md",true,[],[49,56,61,67,74,81],{"skillNo":50,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":53,"categories":54,"keywords":55,"publishedAt":19},"01M732609EPJWV13PVTX3GT4TM","webgpu-threejs-tsl","Comprehensive guide for developing WebGPU-enabled Three.js applications using TSL (Three.js Shading Language). Covers WebGPU renderer setup, TSL syntax and node materials, compute shaders, post-processing effects, and WGSL integration. Use this skill when working with Three.js WebGPU, TSL shaders, node materials, or GPU compute in Three.js.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002Fskills\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":57,"name":51,"nameZh":6,"description":52,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":58,"categories":59,"keywords":60,"publishedAt":19},"01M7325XM47AGWB6K6C4VXKE6B","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fwebgpu-threejs-tsl\u002FSKILL.md",[],[],{"skillNo":62,"name":63,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":64,"categories":65,"keywords":66,"publishedAt":19},"01M7325WP6DES69JKC840VMFEP","verification-loop","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[],{"skillNo":68,"name":69,"nameZh":6,"description":70,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":71,"categories":72,"keywords":73,"publishedAt":19},"01M7325TFQF1DZTQ6J3WGQQ1VR","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\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Ftdd-workflow\u002FSKILL.md",[],[],{"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":19},"01M7325RGV9AY9PK92D2V8KKPW","strategic-compact","Suggests manual context compaction at logical intervals to preserve context through task phases rather than arbitrary auto-compaction.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fstrategic-compact\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":85,"categories":86,"keywords":87,"publishedAt":19},"01M7325MZC28SE86E7NMCNEFS4","security-review","Use this skill when adding authentication, handling user input, working with secrets, creating API endpoints, or implementing payment\u002Fsensitive features. Provides comprehensive security checklist and patterns.","https:\u002F\u002Fgithub.com\u002FSriramGandhiS\u002FSkills\u002Fblob\u002Fmaster\u002Fweb-assets\u002Fdocs\u002Fzh-TW\u002Fskills\u002Fsecurity-review\u002FSKILL.md",[],[]]