[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NTQFSK2YQCMSXMMZG5C9R9":3,"skill-same:01M6NTQFSK2YQCMSXMMZG5C9R9":50},{"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":23,"linkOnly":24,"markdownContent":25,"markdownBody":26,"frontMatter":27,"refName":28,"commitSha":29,"skillDirectory":30,"forksCount":14,"repositoryHtmlUrl":31,"repositoryHomepageUrl":6,"ownerHtmlUrl":32,"ownerBlogUrl":33,"ownerDescription":34,"updatedAt":35,"install":36,"resources":49},"01M6NTQFSK2YQCMSXMMZG5C9R9","experiment-engine",null,"Otonom deney dongusu. Kod degisikligi yap, olc, karsilastir, kabul et veya geri al. Metrik bazli karar verme ile performans, boyut veya kalite optimizasyonu. Tek basina veya agent ile kullan.","rubicanjr\u002FFinCognis","rubicanjr","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F234912519?v=4","01M6NT156NND8J474G34SB3923","Rubi","01M6NT15B70RWXE1N3YV0BZY8A",0,"MIT","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fexperiment-engine\u002FSKILL.md",[],[19,20,21,22],"engine","experiment","experiment engine","kod","2026-11-10 10:12:30",false,"---\nname: experiment-engine\ndescription: Otonom deney dongusu. Kod degisikligi yap, olc, karsilastir, kabul et veya geri al. Metrik bazli karar verme ile performans, boyut veya kalite optimizasyonu. Tek basina veya agent ile kullan.\n---\n\n# Experiment Engine\n\nBir hedef belirle, sistematik olarak deneyler yap, sadece iyilestirenleri tut.\n\n## Core Loop\n\n```\nHEDEF BELIRLE\n  └─ \"API response time'i %20 dusur\"\n  └─ \"Bundle size'i 500KB'nin altina getir\"\n  └─ \"Test coverage'i %90'a cikar\"\n\nBASELINE OLC\n  └─ Mevcut metrigi kaydet (ornek: 340ms, 720KB, %78)\n\nDENEY DONGUSU (N kez tekrarla):\n  ┌─────────────────────────────────────┐\n  │ 1. MODIFY  - Tek degisiklik yap    │\n  │ 2. VERIFY  - Metrigi olc           │\n  │ 3. COMPARE - Baseline ile kiyasla  │\n  │ 4. DECIDE  - Kabul \u002F Reddet        │\n  │    ├─ Iyilesti → COMMIT + yeni     │\n  │    │             baseline           │\n  │    └─ Kotulesti → ROLLBACK         │\n  └─────────────────────────────────────┘\n\nRAPOR OLUSTUR\n  └─ N deney, X kabul, Y red, final metrik\n```\n\n## Kullanim Alanlari\n\n### Performans Optimizasyonu\n\n```bash\n# Hedef: API response time \u003C 200ms\n# Baseline: 340ms\n\n# Deney 1: Database query'ye index ekle\ngit stash  # mevcut durumu kaydet\n# ... index ekle ...\ncurl -w \"%{time_total}\" http:\u002F\u002Flocalhost:3000\u002Fapi\u002Fusers  # 280ms\n# 340ms -> 280ms = IYILESTI → COMMIT\n\n# Deney 2: Response'u cache'le\n# ... Redis cache ekle ...\ncurl -w \"%{time_total}\" http:\u002F\u002Flocalhost:3000\u002Fapi\u002Fusers  # 45ms\n# 280ms -> 45ms = IYILESTI → COMMIT\n\n# Deney 3: JSON serializer degistir\n# ... fast-json-stringify ekle ...\ncurl -w \"%{time_total}\" http:\u002F\u002Flocalhost:3000\u002Fapi\u002Fusers  # 42ms\n# 45ms -> 42ms = MINIMAL IYILESME → REDDET (karmasiklik artmaya degmez)\n\n# Sonuc: 340ms -> 45ms (%87 iyilesme), 2\u002F3 deney kabul edildi\n```\n\n### Bundle Size Azaltma\n\n```bash\n# Hedef: \u003C 500KB\n# Baseline olc\nBASELINE=$(npx next build 2>&1 | grep \"First Load JS\" | awk '{print $4}')\n\n# Deney dongusu\nexperiments=(\n  \"lodash yerine lodash-es\"\n  \"moment yerine dayjs\"\n  \"tree-shaking acik mi kontrol\"\n  \"dynamic import lazy component'ler\"\n  \"image optimize (next\u002Fimage)\"\n)\n\nfor exp in \"${experiments[@]}\"; do\n  echo \"=== Deney: $exp ===\"\n  # degisiklik yap...\n  NEW=$(npx next build 2>&1 | grep \"First Load JS\" | awk '{print $4}')\n  if [ \"$NEW\" -lt \"$BASELINE\" ]; then\n    echo \"KABUL: $BASELINE -> $NEW\"\n    BASELINE=$NEW\n    git add -A && git stash  # kaydet\n  else\n    echo \"RED: $NEW >= $BASELINE\"\n    git checkout .  # geri al\n  fi\ndone\n```\n\n### Test Coverage Artirma\n\n```bash\n# Hedef: %90 coverage\n# Baseline\nBASELINE=$(npx jest --coverage --silent 2>&1 | grep \"All files\" | awk '{print $4}')\n\n# Her dosya icin test yaz, coverage'i olc\nfor file in $(find src -name \"*.ts\" -not -name \"*.test.*\"); do\n  echo \"=== Test: $file ===\"\n  # test yaz...\n  NEW=$(npx jest --coverage --silent 2>&1 | grep \"All files\" | awk '{print $4}')\n  if (( $(echo \"$NEW > $BASELINE\" | bc -l) )); then\n    echo \"KABUL: %$BASELINE -> %$NEW\"\n    BASELINE=$NEW\n  fi\ndone\n```\n\n## Deney Protokolu\n\n### Tek Degisiklik Kurali\n\n```\nYANLIS: Ayni anda 3 sey degistirip \"daha hizli oldu\" demek\n  → Hangi degisiklik etkili oldugunu bilemezsin\n\nDOGRU: Her seferinde TEK degisiklik yap\n  → Neyin ise yaradigini kesin bilirsin\n```\n\n### Rollback Stratejisi\n\n```bash\n# Yontem 1: git stash (basit)\ngit stash         # deney oncesi\n# ... deney ...\ngit stash pop     # basarisizsa geri al\n\n# Yontem 2: git worktree (izole)\ngit worktree add \u002Ftmp\u002Fexperiment-1 -b exp\u002Fperf-test\ncd \u002Ftmp\u002Fexperiment-1\n# ... deney ...\n# basarisizsa worktree'yi sil\n\n# Yontem 3: checkpoint (karmasik deneyler)\ngit add -A && git commit -m \"checkpoint: pre-experiment\"\n# ... deney ...\n# basarisizsa: git reset --hard HEAD~1\n```\n\n### Metrik Toplama\n\n```typescript\ninterface ExperimentResult {\n  id: string\n  description: string\n  baseline: number\n  result: number\n  improvement: number  \u002F\u002F yuzde\n  accepted: boolean\n  duration: number     \u002F\u002F saniye\n  timestamp: string\n}\n\n\u002F\u002F Deney raporu\ninterface ExperimentReport {\n  goal: string\n  metric: string\n  baselineValue: number\n  finalValue: number\n  totalExperiments: number\n  accepted: number\n  rejected: number\n  totalImprovement: number  \u002F\u002F yuzde\n  experiments: ExperimentResult[]\n}\n```\n\n## Deney Sablonu\n\n```markdown\n# Deney Raporu: [Hedef]\n\n## Ozet\n- Hedef: [metrik] \u003C [esik]\n- Baseline: [baslangic degeri]\n- Final: [son deger]\n- Iyilesme: [yuzde]\n- Deneyler: [kabul]\u002F[toplam]\n\n## Deneyler\n\n| # | Aciklama | Onceki | Sonraki | Degisim | Karar |\n|---|----------|-------:|--------:|--------:|-------|\n| 1 | Index ekle | 340ms | 280ms | -18% | KABUL |\n| 2 | Redis cache | 280ms | 45ms | -84% | KABUL |\n| 3 | JSON serializer | 45ms | 42ms | -7% | RED |\n\n## Ogrenim\n- En etkili: Redis cache (-84%)\n- Degmez: JSON serializer degisimi (karmasiklik > kazanim)\n```\n\n## Otomatik Deney Modu\n\n```bash\n# experiment-loop.sh\n# Kullanim: .\u002Fexperiment-loop.sh \"response_time\" \"200\" \"ms\" 10\n\nMETRIC=$1       # olculecek metrik\nTARGET=$2       # hedef deger\nUNIT=$3         # birim\nMAX_ROUNDS=$4   # max deney sayisi\n\nROUND=0\nBASELINE=$(measure_$METRIC)\n\nwhile [ $ROUND -lt $MAX_ROUNDS ]; do\n  ROUND=$((ROUND + 1))\n\n  # Claude'a optimize ettir\n  claude -p \"Optimize $METRIC. Current: ${BASELINE}${UNIT}. Target: \u003C${TARGET}${UNIT}. Make ONE small change.\" --no-input\n\n  # Olc\n  NEW=$(measure_$METRIC)\n\n  if [ \"$NEW\" -lt \"$BASELINE\" ]; then\n    echo \"Round $ROUND: KABUL ($BASELINE -> $NEW)\"\n    BASELINE=$NEW\n    git add -A && git commit -m \"experiment: $METRIC improved to ${NEW}${UNIT}\"\n  else\n    echo \"Round $ROUND: RED ($NEW >= $BASELINE)\"\n    git checkout .\n  fi\n\n  # Hedefe ulastik mi?\n  if [ \"$BASELINE\" -le \"$TARGET\" ]; then\n    echo \"HEDEF ULASILDI: ${BASELINE}${UNIT} \u003C= ${TARGET}${UNIT}\"\n    break\n  fi\ndone\n```\n\n## vibecosystem Entegrasyonu\n\n- **profiler agent**: Performans deneylerinde metrik toplama\n- **nitro agent**: Optimization deneylerini yonetme\n- **tdd-guide agent**: Coverage deneylerinde test yazma\n- **verifier agent**: Her deney sonrasi build\u002Ftest dogrulama\n- **self-learner agent**: Basarili deneyleri pattern olarak kaydet\n- **experiment-loop skill**: Bu skill'in mevcut complementary'si\n","# Experiment Engine\n\nBir hedef belirle, sistematik olarak deneyler yap, sadece iyilestirenleri tut.\n\n## Core Loop\n\n```\nHEDEF BELIRLE\n  └─ \"API response time'i %20 dusur\"\n  └─ \"Bundle size'i 500KB'nin altina getir\"\n  └─ \"Test coverage'i %90'a cikar\"\n\nBASELINE OLC\n  └─ Mevcut metrigi kaydet (ornek: 340ms, 720KB, %78)\n\nDENEY DONGUSU (N kez tekrarla):\n  ┌─────────────────────────────────────┐\n  │ 1. MODIFY  - Tek degisiklik yap    │\n  │ 2. VERIFY  - Metrigi olc           │\n  │ 3. COMPARE - Baseline ile kiyasla  │\n  │ 4. DECIDE  - Kabul \u002F Reddet        │\n  │    ├─ Iyilesti → COMMIT + yeni     │\n  │    │             baseline           │\n  │    └─ Kotulesti → ROLLBACK         │\n  └─────────────────────────────────────┘\n\nRAPOR OLUSTUR\n  └─ N deney, X kabul, Y red, final metrik\n```\n\n## Kullanim Alanlari\n\n### Performans Optimizasyonu\n\n```bash\n# Hedef: API response time \u003C 200ms\n# Baseline: 340ms\n\n# Deney 1: Database query'ye index ekle\ngit stash  # mevcut durumu kaydet\n# ... index ekle ...\ncurl -w \"%{time_total}\" http:\u002F\u002Flocalhost:3000\u002Fapi\u002Fusers  # 280ms\n# 340ms -> 280ms = IYILESTI → COMMIT\n\n# Deney 2: Response'u cache'le\n# ... Redis cache ekle ...\ncurl -w \"%{time_total}\" http:\u002F\u002Flocalhost:3000\u002Fapi\u002Fusers  # 45ms\n# 280ms -> 45ms = IYILESTI → COMMIT\n\n# Deney 3: JSON serializer degistir\n# ... fast-json-stringify ekle ...\ncurl -w \"%{time_total}\" http:\u002F\u002Flocalhost:3000\u002Fapi\u002Fusers  # 42ms\n# 45ms -> 42ms = MINIMAL IYILESME → REDDET (karmasiklik artmaya degmez)\n\n# Sonuc: 340ms -> 45ms (%87 iyilesme), 2\u002F3 deney kabul edildi\n```\n\n### Bundle Size Azaltma\n\n```bash\n# Hedef: \u003C 500KB\n# Baseline olc\nBASELINE=$(npx next build 2>&1 | grep \"First Load JS\" | awk '{print $4}')\n\n# Deney dongusu\nexperiments=(\n  \"lodash yerine lodash-es\"\n  \"moment yerine dayjs\"\n  \"tree-shaking acik mi kontrol\"\n  \"dynamic import lazy component'ler\"\n  \"image optimize (next\u002Fimage)\"\n)\n\nfor exp in \"${experiments[@]}\"; do\n  echo \"=== Deney: $exp ===\"\n  # degisiklik yap...\n  NEW=$(npx next build 2>&1 | grep \"First Load JS\" | awk '{print $4}')\n  if [ \"$NEW\" -lt \"$BASELINE\" ]; then\n    echo \"KABUL: $BASELINE -> $NEW\"\n    BASELINE=$NEW\n    git add -A && git stash  # kaydet\n  else\n    echo \"RED: $NEW >= $BASELINE\"\n    git checkout .  # geri al\n  fi\ndone\n```\n\n### Test Coverage Artirma\n\n```bash\n# Hedef: %90 coverage\n# Baseline\nBASELINE=$(npx jest --coverage --silent 2>&1 | grep \"All files\" | awk '{print $4}')\n\n# Her dosya icin test yaz, coverage'i olc\nfor file in $(find src -name \"*.ts\" -not -name \"*.test.*\"); do\n  echo \"=== Test: $file ===\"\n  # test yaz...\n  NEW=$(npx jest --coverage --silent 2>&1 | grep \"All files\" | awk '{print $4}')\n  if (( $(echo \"$NEW > $BASELINE\" | bc -l) )); then\n    echo \"KABUL: %$BASELINE -> %$NEW\"\n    BASELINE=$NEW\n  fi\ndone\n```\n\n## Deney Protokolu\n\n### Tek Degisiklik Kurali\n\n```\nYANLIS: Ayni anda 3 sey degistirip \"daha hizli oldu\" demek\n  → Hangi degisiklik etkili oldugunu bilemezsin\n\nDOGRU: Her seferinde TEK degisiklik yap\n  → Neyin ise yaradigini kesin bilirsin\n```\n\n### Rollback Stratejisi\n\n```bash\n# Yontem 1: git stash (basit)\ngit stash         # deney oncesi\n# ... deney ...\ngit stash pop     # basarisizsa geri al\n\n# Yontem 2: git worktree (izole)\ngit worktree add \u002Ftmp\u002Fexperiment-1 -b exp\u002Fperf-test\ncd \u002Ftmp\u002Fexperiment-1\n# ... deney ...\n# basarisizsa worktree'yi sil\n\n# Yontem 3: checkpoint (karmasik deneyler)\ngit add -A && git commit -m \"checkpoint: pre-experiment\"\n# ... deney ...\n# basarisizsa: git reset --hard HEAD~1\n```\n\n### Metrik Toplama\n\n```typescript\ninterface ExperimentResult {\n  id: string\n  description: string\n  baseline: number\n  result: number\n  improvement: number  \u002F\u002F yuzde\n  accepted: boolean\n  duration: number     \u002F\u002F saniye\n  timestamp: string\n}\n\n\u002F\u002F Deney raporu\ninterface ExperimentReport {\n  goal: string\n  metric: string\n  baselineValue: number\n  finalValue: number\n  totalExperiments: number\n  accepted: number\n  rejected: number\n  totalImprovement: number  \u002F\u002F yuzde\n  experiments: ExperimentResult[]\n}\n```\n\n## Deney Sablonu\n\n```markdown\n# Deney Raporu: [Hedef]\n\n## Ozet\n- Hedef: [metrik] \u003C [esik]\n- Baseline: [baslangic degeri]\n- Final: [son deger]\n- Iyilesme: [yuzde]\n- Deneyler: [kabul]\u002F[toplam]\n\n## Deneyler\n\n| # | Aciklama | Onceki | Sonraki | Degisim | Karar |\n|---|----------|-------:|--------:|--------:|-------|\n| 1 | Index ekle | 340ms | 280ms | -18% | KABUL |\n| 2 | Redis cache | 280ms | 45ms | -84% | KABUL |\n| 3 | JSON serializer | 45ms | 42ms | -7% | RED |\n\n## Ogrenim\n- En etkili: Redis cache (-84%)\n- Degmez: JSON serializer degisimi (karmasiklik > kazanim)\n```\n\n## Otomatik Deney Modu\n\n```bash\n# experiment-loop.sh\n# Kullanim: .\u002Fexperiment-loop.sh \"response_time\" \"200\" \"ms\" 10\n\nMETRIC=$1       # olculecek metrik\nTARGET=$2       # hedef deger\nUNIT=$3         # birim\nMAX_ROUNDS=$4   # max deney sayisi\n\nROUND=0\nBASELINE=$(measure_$METRIC)\n\nwhile [ $ROUND -lt $MAX_ROUNDS ]; do\n  ROUND=$((ROUND + 1))\n\n  # Claude'a optimize ettir\n  claude -p \"Optimize $METRIC. Current: ${BASELINE}${UNIT}. Target: \u003C${TARGET}${UNIT}. Make ONE small change.\" --no-input\n\n  # Olc\n  NEW=$(measure_$METRIC)\n\n  if [ \"$NEW\" -lt \"$BASELINE\" ]; then\n    echo \"Round $ROUND: KABUL ($BASELINE -> $NEW)\"\n    BASELINE=$NEW\n    git add -A && git commit -m \"experiment: $METRIC improved to ${NEW}${UNIT}\"\n  else\n    echo \"Round $ROUND: RED ($NEW >= $BASELINE)\"\n    git checkout .\n  fi\n\n  # Hedefe ulastik mi?\n  if [ \"$BASELINE\" -le \"$TARGET\" ]; then\n    echo \"HEDEF ULASILDI: ${BASELINE}${UNIT} \u003C= ${TARGET}${UNIT}\"\n    break\n  fi\ndone\n```\n\n## vibecosystem Entegrasyonu\n\n- **profiler agent**: Performans deneylerinde metrik toplama\n- **nitro agent**: Optimization deneylerini yonetme\n- **tdd-guide agent**: Coverage deneylerinde test yazma\n- **verifier agent**: Her deney sonrasi build\u002Ftest dogrulama\n- **self-learner agent**: Basarili deneyleri pattern olarak kaydet\n- **experiment-loop skill**: Bu skill'in mevcut complementary'si\n",{"name":5,"description":7},"main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Fexperiment-engine","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis","https:\u002F\u002Fgithub.com\u002Frubicanjr","linktr.ee\u002Ffinanskodu","Industrial Engineer & CIO @FinansKodu. Architecting AI-driven financial agents and autonomous workflows. 🏗️ Building systems, not just prompts.","2026-06-09 13:50:15",{"source":8,"skillName":5,"commands":37,"prompt":47,"zipAvailable":48},[38,41,44],{"tool":39,"command":40},"npx","npx skills add rubicanjr\u002FFinCognis --skill experiment-engine",{"tool":42,"command":43},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill experiment-engine",{"tool":45,"command":46},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill experiment-engine","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fexperiment-engine\u002FSKILL.md",true,[],[51,72,81,101,131,150],{"skillNo":52,"name":53,"nameZh":6,"description":54,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":55,"categories":56,"keywords":62,"publishedAt":23},"01M6NWS9DAXJTADT4T5MB49X8W","workflow-router","Goal-based workflow orchestration - routes tasks to specialist agents based on user goals","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fworkflow-router\u002FSKILL.md",[57],{"categoryNo":58,"categoryName":59,"taxonomyType":60,"taxonomyTypeDesc":61},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[63,64,65,66,67,68,69,70,71],"workflow router","workflow","router","orchestration","goals","goal","user","workflow orchestration","tasks",{"skillNo":73,"name":74,"nameZh":6,"description":75,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":76,"categories":77,"keywords":78,"publishedAt":23},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[74,79,80],"verification","false",{"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":90,"publishedAt":23},"01M6NWS0XW9CVQZBDA1EGW0TWC","websocket-patterns","Connection management, room patterns, reconnection strategies, message buffering, and binary protocol design.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwebsocket-patterns\u002Fskill.md",[87],{"categoryNo":88,"categoryName":89,"taxonomyType":60,"taxonomyTypeDesc":61},"01JBSEEDCAT000000000000015","视觉设计",[91,92,93,94,95,96,97,98,99,100],"websocket","patterns","websocket patterns","design","protocol","management","message","strategies","binary","connection",{"skillNo":102,"name":103,"nameZh":6,"description":104,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":105,"categories":106,"keywords":111,"publishedAt":23},"01M6NWRDQDX9ZNETAWRRMQWV52","visual-verdict","Screenshot comparison QA for frontend development. Takes a screenshot of the current implementation, scores it across multiple visual dimensions, and returns a structured PASS\u002FREVISE\u002FFAIL verdict with concrete fixes. Use when implementing UI from a design reference or verifying visual correctness.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvisual-verdict\u002FSKILL.md",[107,110],{"categoryNo":108,"categoryName":109,"taxonomyType":60,"taxonomyTypeDesc":61},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":58,"categoryName":59,"taxonomyType":60,"taxonomyTypeDesc":61},[112,113,114,115,116,117,118,119,120,121,122,123,124,94,125,126,127,128,129,130],"visual","verdict","visual verdict","ui","across","revise","comparison","correctness","implementing","for","fixes","dimensions","frontend","development","qa","screenshot","returns","use","frontend development",{"skillNo":132,"name":133,"nameZh":6,"description":134,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":135,"categories":136,"keywords":137,"publishedAt":23},"01M6NWR8HSNRS7MNDK2J02QYMN","verification-loop","Comprehensive verification system covering build, types, lint, tests, security, and diff review before a PR.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fverification-loop\u002FSKILL.md",[],[138,139,79,140,141,142,143,144,145,146,147,148,149],"verification loop","loop","lint","review","security","pr","system","diff","build","tests","diff review","types",{"skillNo":151,"name":152,"nameZh":6,"description":153,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":154,"categories":155,"keywords":156,"publishedAt":23},"01M6NWR4HHSFR0VR5EXFRWA747","vector-db-patterns","Embedding strategies, ANN algorithms, hybrid search, RAG chunking strategies, and reranking for semantic search and retrieval.","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fvector-db-patterns\u002Fskill.md",[],[157,158,159,160,92,161,162,163,164,98,165,166,167,168,169,121,170,171],"vector db patterns","vector db","db","vector","semantic search","search","embedding strategies","algorithms","chunking","semantic","retrieval","embedding","Hybrid Search","hybrid","rag"]