[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NWPH7H7HKMXF8FSKBGRJM9":3,"skill-same:01M6NWPH7H7HKMXF8FSKBGRJM9":57},{"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":23,"publishedAt":30,"linkOnly":31,"markdownContent":32,"markdownBody":33,"frontMatter":34,"refName":35,"commitSha":36,"skillDirectory":37,"forksCount":14,"repositoryHtmlUrl":38,"repositoryHomepageUrl":6,"ownerHtmlUrl":39,"ownerBlogUrl":40,"ownerDescription":41,"updatedAt":42,"install":43,"resources":56},"01M6NWPH7H7HKMXF8FSKBGRJM9","token-budget",null,"Agent basina token kullanimi takibi, maliyet optimizasyonu, butce limitleri ve ROI analizi. Session ve proje bazinda harcama raporlari. Hangi agent ne kadar token tuketiyor, hangisi verimli, hangisi israf.","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\u002Ftoken-budget\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000040","财务","PROFESSION","适用职业",[24,25,26,27,28,29],"Budget","token","token budget","roi","session","ne","2026-11-10 10:12:30",false,"---\nname: token-budget\ndescription: Agent basina token kullanimi takibi, maliyet optimizasyonu, butce limitleri ve ROI analizi. Session ve proje bazinda harcama raporlari. Hangi agent ne kadar token tuketiyor, hangisi verimli, hangisi israf.\n---\n\n# Token Budget Management\n\nHer agent cagri token harcar. Butce yonetimi olmadan maliyetler kontrolsuz buyur.\n\n## Maliyet Tablosu (2026 Q2)\n\n| Model | Input (1M token) | Output (1M token) | Cache Read (1M) |\n|-------|----------------:|------------------:|----------------:|\n| Opus 4.6 | $15.00 | $75.00 | $1.50 |\n| Sonnet 4.6 | $3.00 | $15.00 | $0.30 |\n| Haiku 4.5 | $0.80 | $4.00 | $0.08 |\n\n### Agent Basina Ortalama Maliyet\n\n| Agent Tipi | Ortalama Token\u002FCagri | Ortalama Maliyet | Notlar |\n|------------|--------------------:|------------------:|--------|\n| scout (arastirma) | 15K-50K | $0.15-0.75 | Cok dosya okur |\n| code-reviewer | 10K-30K | $0.10-0.45 | Diff boyutuna bagli |\n| architect | 20K-60K | $0.30-0.90 | Derin dusunme gerektirir |\n| spark (quick fix) | 3K-10K | $0.03-0.15 | En verimli |\n| kraken (TDD) | 30K-100K | $0.45-1.50 | Test + implement |\n| sleuth (debug) | 20K-80K | $0.30-1.20 | Bug karmasikligina bagli |\n| verifier | 5K-15K | $0.05-0.22 | Build + test calistirma |\n| security-reviewer | 10K-40K | $0.15-0.60 | Tarama derinligine bagli |\n| planner | 15K-40K | $0.22-0.60 | Plan buyuklugune bagli |\n\n## Butce Planlama\n\n### Session Butcesi\n\n```\nKUCUK IS (bug fix, kucuk feature):\n  Beklenen: 50K-150K token\n  Butce: $0.50-2.00\n  Agent sayisi: 2-4\n\nORTA IS (feature, refactoring):\n  Beklenen: 200K-500K token\n  Butce: $3.00-7.00\n  Agent sayisi: 4-8\n\nBUYUK IS (yeni modul, buyuk refactor):\n  Beklenen: 500K-2M token\n  Butce: $7.00-30.00\n  Agent sayisi: 8-15\n\nSWARM (tam ekip):\n  Beklenen: 1M-5M token\n  Butce: $15.00-75.00\n  Agent sayisi: 15-30\n```\n\n### Aylik Butce Tahmini\n\n```\nGunluk 3-5 session x 30 gun:\n\nHafif kullanim (vibe coding):\n  ~100K token\u002Fgun = $1.50\u002Fgun = ~$45\u002Fay\n\nNormal kullanim (aktif gelistirme):\n  ~500K token\u002Fgun = $7.50\u002Fgun = ~$225\u002Fay\n\nYogun kullanim (tam ekip, swarm):\n  ~2M token\u002Fgun = $30\u002Fgun = ~$900\u002Fay\n\nClaude Max abone ise:\n  Sabit $200\u002Fay -- token limiti var ama birim maliyet yok\n  ROI: Normal kullanim ustu her sey Max ile karli\n```\n\n## Maliyet Optimizasyon Stratejileri\n\n### 1. Model Routing (En Buyuk Tasarruf)\n\n```\nOpus kullan:\n  - Mimari kararlar (architect)\n  - Karmasik debug (sleuth)\n  - Guvenlik analizi (security-reviewer)\n  - Kritik code review\n\nSonnet kullan:\n  - Genel gelistirme (kraken, spark)\n  - Rutin review (code-reviewer)\n  - Dokumantasyon (technical-writer)\n  - Test yazma (tdd-guide)\n\nSonuc: %40-60 maliyet dususu, %5-10 kalite kaybı\n```\n\n### 2. Context Yonetimi\n\n```\nYAPMA: 5 dosyayi tamamen okuyup agent'a gonder\nYAP:   Sadece ilgili fonksiyonlari gonder\n\nYAPMA: Her seferinde tum CLAUDE.md'yi inject et\nYAP:   Sadece ilgili kurallari sec\n\nYAPMA: Agent'a \"her seyi kontrol et\" de\nYAP:   Spesifik kontrol listesi ver\n\nToken tasarrufu: %30-50\n```\n\n### 3. Agent Secimi\n\n```\nPAHALI YOLDAN GITME:\n  architect (60K) + kraken (100K) + verifier (15K) = 175K token\n\nVERIMLI YOL:\n  spark (10K) + verifier (10K) = 20K token\n  (Kucuk is icin spark yeterli, architect\u002Fkraken gereksiz)\n\nKural: Is buyuklugune uygun agent sec\n```\n\n### 4. Cache Kullanimi\n\n```\nAyni dosyayi tekrar tekrar okuma:\n  Ilk okuma: 10K token (tam fiyat)\n  Cache hit: 10K token (%90 indirimli)\n\nStrateji: Session basinda ilgili dosyalari bir kere oku,\nsonraki agent'lar cache'ten okusun\n```\n\n### 5. Paralel vs Sequential\n\n```\nPARALEL (daha pahali ama hizli):\n  3 agent ayni anda = 3x token ama 3x hizli\n  Kullan: Deadline varsa, bagimsiz isler\n\nSEQUENTIAL (daha ucuz):\n  Agent 1 bitir → ciktisini Agent 2'ye ver\n  Kullan: Butce kisitliysa, bagimli isler\n```\n\n## ROI Analizi\n\n### Agent Basina ROI\n\n```\nROI = (Tasarruf edilen sure x saat ucreti) \u002F Agent maliyeti\n\nOrnek: code-reviewer\n  Maliyet: ~$0.30\u002Freview\n  Tasarruf: ~15 dk\u002Freview (manual review vs)\n  Saat ucreti: $50\u002Fsaat\n  ROI: ($12.50) \u002F ($0.30) = 41x\n\nOrnek: sleuth (bug investigation)\n  Maliyet: ~$0.75\u002Finvestigation\n  Tasarruf: ~45 dk\u002Fbug (manual debug vs)\n  ROI: ($37.50) \u002F ($0.75) = 50x\n\nOrnek: architect (buyuk plan)\n  Maliyet: ~$0.90\u002Fplan\n  Tasarruf: ~2 saat (manual planning vs)\n  ROI: ($100) \u002F ($0.90) = 111x\n```\n\n### En Yuksek ROI Agent'lar\n\n| Siralama | Agent | ROI | Neden |\n|----------|-------|-----|-------|\n| 1 | architect | 111x | Buyuk zaman tasarrufu, dusuk maliyet |\n| 2 | sleuth | 50x | Bug investigation cok zaman alir |\n| 3 | code-reviewer | 41x | Her commit icin gerekli |\n| 4 | verifier | 35x | Otomatik quality gate |\n| 5 | spark | 30x | Kucuk isler icin cok verimli |\n\n### En Dusuk ROI Agent'lar\n\n| Agent | ROI | Neden | Oneri |\n|-------|-----|-------|-------|\n| scout (gereksiz arama) | 5x | Bazen cok dosya okur, az bilgi bulur | Spesifik soru sor |\n| kraken (kucuk is) | 8x | TDD overhead kucuk isler icin fazla | Kucuk is = spark |\n| designer (sadece oneri) | 3x | Oneri verir ama implement etmez | Frontend-dev yeterli |\n\n## Harcama Raporu Sablonu\n\n```markdown\n# Token Harcama Raporu - [Tarih]\n\n## Ozet\n- Toplam token: XXX,XXX\n- Tahmini maliyet: $XX.XX\n- Agent sayisi: X\n- Session suresi: X saat\n\n## Agent Bazli Dagilim\n\n| Agent | Token | Maliyet | Is | ROI |\n|-------|------:|--------:|---|----|\n| architect | 45K | $0.67 | Auth redesign plani | 111x |\n| kraken | 85K | $1.27 | Implementation | 25x |\n| code-reviewer | 20K | $0.30 | Review | 41x |\n| verifier | 12K | $0.18 | Final check | 35x |\n| **TOPLAM** | **162K** | **$2.42** | | |\n\n## Optimizasyon Onerisi\n- kraken yerine spark kullanilabilirdi (-70K token)\n- architect ciktisi daha spesifik olabilirdi (-15K token)\n- Potansiyel tasarruf: %52\n```\n\n## vibecosystem Entegrasyonu\n\n- **cost-tracker agent**: Bu skill'i kullanarak session maliyet raporu uretir\n- **smart-model-routing skill**: Model secimini maliyet\u002Fkalite dengesine gore yapar\n- **swarm-optimizer agent**: Swarm calistirmalarinda butce optimizasyonu yapar\n- **session-replay-analyzer agent**: Gecmis session'larin token verimliligini analiz eder\n","# Token Budget Management\n\nHer agent cagri token harcar. Butce yonetimi olmadan maliyetler kontrolsuz buyur.\n\n## Maliyet Tablosu (2026 Q2)\n\n| Model | Input (1M token) | Output (1M token) | Cache Read (1M) |\n|-------|----------------:|------------------:|----------------:|\n| Opus 4.6 | $15.00 | $75.00 | $1.50 |\n| Sonnet 4.6 | $3.00 | $15.00 | $0.30 |\n| Haiku 4.5 | $0.80 | $4.00 | $0.08 |\n\n### Agent Basina Ortalama Maliyet\n\n| Agent Tipi | Ortalama Token\u002FCagri | Ortalama Maliyet | Notlar |\n|------------|--------------------:|------------------:|--------|\n| scout (arastirma) | 15K-50K | $0.15-0.75 | Cok dosya okur |\n| code-reviewer | 10K-30K | $0.10-0.45 | Diff boyutuna bagli |\n| architect | 20K-60K | $0.30-0.90 | Derin dusunme gerektirir |\n| spark (quick fix) | 3K-10K | $0.03-0.15 | En verimli |\n| kraken (TDD) | 30K-100K | $0.45-1.50 | Test + implement |\n| sleuth (debug) | 20K-80K | $0.30-1.20 | Bug karmasikligina bagli |\n| verifier | 5K-15K | $0.05-0.22 | Build + test calistirma |\n| security-reviewer | 10K-40K | $0.15-0.60 | Tarama derinligine bagli |\n| planner | 15K-40K | $0.22-0.60 | Plan buyuklugune bagli |\n\n## Butce Planlama\n\n### Session Butcesi\n\n```\nKUCUK IS (bug fix, kucuk feature):\n  Beklenen: 50K-150K token\n  Butce: $0.50-2.00\n  Agent sayisi: 2-4\n\nORTA IS (feature, refactoring):\n  Beklenen: 200K-500K token\n  Butce: $3.00-7.00\n  Agent sayisi: 4-8\n\nBUYUK IS (yeni modul, buyuk refactor):\n  Beklenen: 500K-2M token\n  Butce: $7.00-30.00\n  Agent sayisi: 8-15\n\nSWARM (tam ekip):\n  Beklenen: 1M-5M token\n  Butce: $15.00-75.00\n  Agent sayisi: 15-30\n```\n\n### Aylik Butce Tahmini\n\n```\nGunluk 3-5 session x 30 gun:\n\nHafif kullanim (vibe coding):\n  ~100K token\u002Fgun = $1.50\u002Fgun = ~$45\u002Fay\n\nNormal kullanim (aktif gelistirme):\n  ~500K token\u002Fgun = $7.50\u002Fgun = ~$225\u002Fay\n\nYogun kullanim (tam ekip, swarm):\n  ~2M token\u002Fgun = $30\u002Fgun = ~$900\u002Fay\n\nClaude Max abone ise:\n  Sabit $200\u002Fay -- token limiti var ama birim maliyet yok\n  ROI: Normal kullanim ustu her sey Max ile karli\n```\n\n## Maliyet Optimizasyon Stratejileri\n\n### 1. Model Routing (En Buyuk Tasarruf)\n\n```\nOpus kullan:\n  - Mimari kararlar (architect)\n  - Karmasik debug (sleuth)\n  - Guvenlik analizi (security-reviewer)\n  - Kritik code review\n\nSonnet kullan:\n  - Genel gelistirme (kraken, spark)\n  - Rutin review (code-reviewer)\n  - Dokumantasyon (technical-writer)\n  - Test yazma (tdd-guide)\n\nSonuc: %40-60 maliyet dususu, %5-10 kalite kaybı\n```\n\n### 2. Context Yonetimi\n\n```\nYAPMA: 5 dosyayi tamamen okuyup agent'a gonder\nYAP:   Sadece ilgili fonksiyonlari gonder\n\nYAPMA: Her seferinde tum CLAUDE.md'yi inject et\nYAP:   Sadece ilgili kurallari sec\n\nYAPMA: Agent'a \"her seyi kontrol et\" de\nYAP:   Spesifik kontrol listesi ver\n\nToken tasarrufu: %30-50\n```\n\n### 3. Agent Secimi\n\n```\nPAHALI YOLDAN GITME:\n  architect (60K) + kraken (100K) + verifier (15K) = 175K token\n\nVERIMLI YOL:\n  spark (10K) + verifier (10K) = 20K token\n  (Kucuk is icin spark yeterli, architect\u002Fkraken gereksiz)\n\nKural: Is buyuklugune uygun agent sec\n```\n\n### 4. Cache Kullanimi\n\n```\nAyni dosyayi tekrar tekrar okuma:\n  Ilk okuma: 10K token (tam fiyat)\n  Cache hit: 10K token (%90 indirimli)\n\nStrateji: Session basinda ilgili dosyalari bir kere oku,\nsonraki agent'lar cache'ten okusun\n```\n\n### 5. Paralel vs Sequential\n\n```\nPARALEL (daha pahali ama hizli):\n  3 agent ayni anda = 3x token ama 3x hizli\n  Kullan: Deadline varsa, bagimsiz isler\n\nSEQUENTIAL (daha ucuz):\n  Agent 1 bitir → ciktisini Agent 2'ye ver\n  Kullan: Butce kisitliysa, bagimli isler\n```\n\n## ROI Analizi\n\n### Agent Basina ROI\n\n```\nROI = (Tasarruf edilen sure x saat ucreti) \u002F Agent maliyeti\n\nOrnek: code-reviewer\n  Maliyet: ~$0.30\u002Freview\n  Tasarruf: ~15 dk\u002Freview (manual review vs)\n  Saat ucreti: $50\u002Fsaat\n  ROI: ($12.50) \u002F ($0.30) = 41x\n\nOrnek: sleuth (bug investigation)\n  Maliyet: ~$0.75\u002Finvestigation\n  Tasarruf: ~45 dk\u002Fbug (manual debug vs)\n  ROI: ($37.50) \u002F ($0.75) = 50x\n\nOrnek: architect (buyuk plan)\n  Maliyet: ~$0.90\u002Fplan\n  Tasarruf: ~2 saat (manual planning vs)\n  ROI: ($100) \u002F ($0.90) = 111x\n```\n\n### En Yuksek ROI Agent'lar\n\n| Siralama | Agent | ROI | Neden |\n|----------|-------|-----|-------|\n| 1 | architect | 111x | Buyuk zaman tasarrufu, dusuk maliyet |\n| 2 | sleuth | 50x | Bug investigation cok zaman alir |\n| 3 | code-reviewer | 41x | Her commit icin gerekli |\n| 4 | verifier | 35x | Otomatik quality gate |\n| 5 | spark | 30x | Kucuk isler icin cok verimli |\n\n### En Dusuk ROI Agent'lar\n\n| Agent | ROI | Neden | Oneri |\n|-------|-----|-------|-------|\n| scout (gereksiz arama) | 5x | Bazen cok dosya okur, az bilgi bulur | Spesifik soru sor |\n| kraken (kucuk is) | 8x | TDD overhead kucuk isler icin fazla | Kucuk is = spark |\n| designer (sadece oneri) | 3x | Oneri verir ama implement etmez | Frontend-dev yeterli |\n\n## Harcama Raporu Sablonu\n\n```markdown\n# Token Harcama Raporu - [Tarih]\n\n## Ozet\n- Toplam token: XXX,XXX\n- Tahmini maliyet: $XX.XX\n- Agent sayisi: X\n- Session suresi: X saat\n\n## Agent Bazli Dagilim\n\n| Agent | Token | Maliyet | Is | ROI |\n|-------|------:|--------:|---|----|\n| architect | 45K | $0.67 | Auth redesign plani | 111x |\n| kraken | 85K | $1.27 | Implementation | 25x |\n| code-reviewer | 20K | $0.30 | Review | 41x |\n| verifier | 12K | $0.18 | Final check | 35x |\n| **TOPLAM** | **162K** | **$2.42** | | |\n\n## Optimizasyon Onerisi\n- kraken yerine spark kullanilabilirdi (-70K token)\n- architect ciktisi daha spesifik olabilirdi (-15K token)\n- Potansiyel tasarruf: %52\n```\n\n## vibecosystem Entegrasyonu\n\n- **cost-tracker agent**: Bu skill'i kullanarak session maliyet raporu uretir\n- **smart-model-routing skill**: Model secimini maliyet\u002Fkalite dengesine gore yapar\n- **swarm-optimizer agent**: Swarm calistirmalarinda butce optimizasyonu yapar\n- **session-replay-analyzer agent**: Gecmis session'larin token verimliligini analiz eder\n",{"name":5,"description":7},"main","70e1c350500ee750987420bbae48837afa906b7e","skills\u002Ftoken-budget","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":44,"prompt":54,"zipAvailable":55},[45,48,51],{"tool":46,"command":47},"npx","npx skills add rubicanjr\u002FFinCognis --skill token-budget",{"tool":49,"command":50},"bunx","bunx skills add rubicanjr\u002FFinCognis --skill token-budget",{"tool":52,"command":53},"pnpm","pnpm dlx skills add rubicanjr\u002FFinCognis --skill token-budget","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Ftoken-budget\u002FSKILL.md",true,[],[58,79,88,108,138,157],{"skillNo":59,"name":60,"nameZh":6,"description":61,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":62,"categories":63,"keywords":69,"publishedAt":30},"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",[64],{"categoryNo":65,"categoryName":66,"taxonomyType":67,"taxonomyTypeDesc":68},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[70,71,72,73,74,75,76,77,78],"workflow router","workflow","router","orchestration","goals","goal","user","workflow orchestration","tasks",{"skillNo":80,"name":81,"nameZh":6,"description":82,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":83,"categories":84,"keywords":85,"publishedAt":30},"01M6NWS3RETSC0SHP16HP66E14","wiring","Wiring Verification","https:\u002F\u002Fgithub.com\u002Frubicanjr\u002FFinCognis\u002Fblob\u002Fmain\u002Fskills\u002Fwiring\u002FSKILL.md",[],[81,86,87],"verification","false",{"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":97,"publishedAt":30},"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",[94],{"categoryNo":95,"categoryName":96,"taxonomyType":67,"taxonomyTypeDesc":68},"01JBSEEDCAT000000000000015","视觉设计",[98,99,100,101,102,103,104,105,106,107],"websocket","patterns","websocket patterns","design","protocol","management","message","strategies","binary","connection",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":118,"publishedAt":30},"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",[114,117],{"categoryNo":115,"categoryName":116,"taxonomyType":67,"taxonomyTypeDesc":68},"01JBSEEDCAT000000000000009","前端开发",{"categoryNo":65,"categoryName":66,"taxonomyType":67,"taxonomyTypeDesc":68},[119,120,121,122,123,124,125,126,127,128,129,130,131,101,132,133,134,135,136,137],"visual","verdict","visual verdict","ui","across","revise","comparison","correctness","implementing","for","fixes","dimensions","frontend","development","qa","screenshot","returns","use","frontend development",{"skillNo":139,"name":140,"nameZh":6,"description":141,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":142,"categories":143,"keywords":144,"publishedAt":30},"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",[],[145,146,86,147,148,149,150,151,152,153,154,155,156],"verification loop","loop","lint","review","security","pr","system","diff","build","tests","diff review","types",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":163,"publishedAt":30},"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",[],[164,165,166,167,99,168,169,170,171,105,172,173,174,175,176,128,177,178],"vector db patterns","vector db","db","vector","semantic search","search","embedding strategies","algorithms","chunking","semantic","retrieval","embedding","Hybrid Search","hybrid","rag"]