[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7CSWFT69BM74R0F5GSPN04X":3,"skill-same:01M7CSWFT69BM74R0F5GSPN04X":49},{"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":27,"commitSha":28,"skillDirectory":29,"forksCount":14,"repositoryHtmlUrl":30,"repositoryHomepageUrl":6,"ownerHtmlUrl":31,"ownerBlogUrl":32,"ownerDescription":33,"updatedAt":34,"install":35,"resources":48},"01M7CSWFT69BM74R0F5GSPN04X","healthcare-cdss-patterns",null,"Clinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows.","Henrique1601\u002FSkiilsToIAs","Henrique1601","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F92006691?v=4","01M7CRXVT0GVXVK80JT1GR687S","Henrique Bezerra Dos Santos","01M7CRXVTN5Y8TMWJ1MDSKCQ1T",0,"MIT","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fbusiness-management\u002Fhealthcare-cdss-patterns\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: healthcare-cdss-patterns\ndescription: Clinical Decision Support System (CDSS) development patterns. Drug interaction checking, dose validation, clinical scoring (NEWS2, qSOFA), alert severity classification, and integration into EMR workflows.\nmetadata:\n  origin: Health1 Super Speciality Hospitals — contributed by Dr. Keyur Patel\nversion: \"1.0.0\"\n---\n\n# Healthcare CDSS Development Patterns\n\nPatterns for building Clinical Decision Support Systems that integrate into EMR workflows. CDSS modules are patient safety critical — zero tolerance for false negatives.\n\n## When to Use\n\n- Implementing drug interaction checking\n- Building dose validation engines\n- Implementing clinical scoring systems (NEWS2, qSOFA, APACHE, GCS)\n- Designing alert systems for abnormal clinical values\n- Building medication order entry with safety checks\n- Integrating lab result interpretation with clinical context\n\n## How It Works\n\nThe CDSS engine is a **pure function library with zero side effects**. Input clinical data, output alerts. This makes it fully testable.\n\nThree primary modules:\n\n1. **`checkInteractions(newDrug, currentMeds, allergies)`** — Checks a new drug against current medications and known allergies. Returns severity-sorted `InteractionAlert[]`. Uses `DrugInteractionPair` data model.\n2. **`validateDose(drug, dose, route, weight, age, renalFunction)`** — Validates a prescribed dose against weight-based, age-adjusted, and renal-adjusted rules. Returns `DoseValidationResult`.\n3. **`calculateNEWS2(vitals)`** — National Early Warning Score 2 from `NEWS2Input`. Returns `NEWS2Result` with total score, risk level, and escalation guidance.\n\n```\nEMR UI\n  ↓ (user enters data)\nCDSS Engine (pure functions, no side effects)\n  ├── Drug Interaction Checker\n  ├── Dose Validator\n  ├── Clinical Scoring (NEWS2, qSOFA, etc.)\n  └── Alert Classifier\n  ↓ (returns alerts)\nEMR UI (displays alerts inline, blocks if critical)\n```\n\n### Drug Interaction Checking\n\n```typescript\ninterface DrugInteractionPair {\n  drugA: string;           \u002F\u002F generic name\n  drugB: string;           \u002F\u002F generic name\n  severity: 'critical' | 'major' | 'minor';\n  mechanism: string;\n  clinicalEffect: string;\n  recommendation: string;\n}\n\nfunction checkInteractions(\n  newDrug: string,\n  currentMedications: string[],\n  allergyList: string[]\n): InteractionAlert[] {\n  if (!newDrug) return [];\n  const alerts: InteractionAlert[] = [];\n  for (const current of currentMedications) {\n    const interaction = findInteraction(newDrug, current);\n    if (interaction) {\n      alerts.push({ severity: interaction.severity, pair: [newDrug, current],\n        message: interaction.clinicalEffect, recommendation: interaction.recommendation });\n    }\n  }\n  for (const allergy of allergyList) {\n    if (isCrossReactive(newDrug, allergy)) {\n      alerts.push({ severity: 'critical', pair: [newDrug, allergy],\n        message: `Cross-reactivity with documented allergy: ${allergy}`,\n        recommendation: 'Do not prescribe without allergy consultation' });\n    }\n  }\n  return alerts.sort((a, b) => severityOrder(a.severity) - severityOrder(b.severity));\n}\n```\n\nInteraction pairs must be **bidirectional**: if Drug A interacts with Drug B, then Drug B interacts with Drug A.\n\n### Dose Validation\n\n```typescript\ninterface DoseValidationResult {\n  valid: boolean;\n  message: string;\n  suggestedRange: { min: number; max: number; unit: string } | null;\n  factors: string[];\n}\n\nfunction validateDose(\n  drug: string,\n  dose: number,\n  route: 'oral' | 'iv' | 'im' | 'sc' | 'topical',\n  patientWeight?: number,\n  patientAge?: number,\n  renalFunction?: number\n): DoseValidationResult {\n  const rules = getDoseRules(drug, route);\n  if (!rules) return { valid: true, message: 'No validation rules available', suggestedRange: null, factors: [] };\n  const factors: string[] = [];\n\n  \u002F\u002F SAFETY: if rules require weight but weight missing, BLOCK (not pass)\n  if (rules.weightBased) {\n    if (!patientWeight || patientWeight \u003C= 0) {\n      return { valid: false, message: `Weight required for ${drug} (mg\u002Fkg drug)`,\n        suggestedRange: null, factors: ['weight_missing'] };\n    }\n    factors.push('weight');\n    const maxDose = rules.maxPerKg * patientWeight;\n    if (dose > maxDose) {\n      return { valid: false, message: `Dose exceeds max for ${patientWeight}kg`,\n        suggestedRange: { min: rules.minPerKg * patientWeight, max: maxDose, unit: rules.unit }, factors };\n    }\n  }\n\n  \u002F\u002F Age-based adjustment (when rules define age brackets and age is provided)\n  if (rules.ageAdjusted && patientAge !== undefined) {\n    factors.push('age');\n    const ageMax = rules.getAgeAdjustedMax(patientAge);\n    if (dose > ageMax) {\n      return { valid: false, message: `Exceeds age-adjusted max for ${patientAge}yr`,\n        suggestedRange: { min: rules.typicalMin, max: ageMax, unit: rules.unit }, factors };\n    }\n  }\n\n  \u002F\u002F Renal adjustment (when rules define eGFR brackets and eGFR is provided)\n  if (rules.renalAdjusted && renalFunction !== undefined) {\n    factors.push('renal');\n    const renalMax = rules.getRenalAdjustedMax(renalFunction);\n    if (dose > renalMax) {\n      return { valid: false, message: `Exceeds renal-adjusted max for eGFR ${renalFunction}`,\n        suggestedRange: { min: rules.typicalMin, max: renalMax, unit: rules.unit }, factors };\n    }\n  }\n\n  \u002F\u002F Absolute max\n  if (dose > rules.absoluteMax) {\n    return { valid: false, message: `Exceeds absolute max ${rules.absoluteMax}${rules.unit}`,\n      suggestedRange: { min: rules.typicalMin, max: rules.absoluteMax, unit: rules.unit },\n      factors: [...factors, 'absolute_max'] };\n  }\n  return { valid: true, message: 'Within range',\n    suggestedRange: { min: rules.typicalMin, max: rules.typicalMax, unit: rules.unit }, factors };\n}\n```\n\n### Clinical Scoring: NEWS2\n\n```typescript\ninterface NEWS2Input {\n  respiratoryRate: number; oxygenSaturation: number; supplementalOxygen: boolean;\n  temperature: number; systolicBP: number; heartRate: number;\n  consciousness: 'alert' | 'voice' | 'pain' | 'unresponsive';\n}\ninterface NEWS2Result {\n  total: number;           \u002F\u002F 0-20\n  risk: 'low' | 'low-medium' | 'medium' | 'high';\n  components: Record\u003Cstring, number>;\n  escalation: string;\n}\n```\n\nScoring tables must match the Royal College of Physicians specification exactly.\n\n### Alert Severity and UI Behavior\n\n| Severity | UI Behavior | Clinician Action Required |\n|----------|-------------|--------------------------|\n| Critical | Block action. Non-dismissable modal. Red. | Must document override reason to proceed |\n| Major | Warning banner inline. Orange. | Must acknowledge before proceeding |\n| Minor | Info note inline. Yellow. | Awareness only, no action required |\n\nCritical alerts must NEVER be auto-dismissed or implemented as toast notifications. Override reasons must be stored in the audit trail.\n\n### Testing CDSS (Zero Tolerance for False Negatives)\n\n```typescript\ndescribe('CDSS — Patient Safety', () => {\n  INTERACTION_PAIRS.forEach(({ drugA, drugB, severity }) => {\n    it(`detects ${drugA} + ${drugB} (${severity})`, () => {\n      const alerts = checkInteractions(drugA, [drugB], []);\n      expect(alerts.length).toBeGreaterThan(0);\n      expect(alerts[0].severity).toBe(severity);\n    });\n    it(`detects ${drugB} + ${drugA} (reverse)`, () => {\n      const alerts = checkInteractions(drugB, [drugA], []);\n      expect(alerts.length).toBeGreaterThan(0);\n    });\n  });\n  it('blocks mg\u002Fkg drug when weight is missing', () => {\n    const result = validateDose('gentamicin', 300, 'iv');\n    expect(result.valid).toBe(false);\n    expect(result.factors).toContain('weight_missing');\n  });\n  it('handles malformed drug data gracefully', () => {\n    expect(() => checkInteractions('', [], [])).not.toThrow();\n  });\n});\n```\n\nPass criteria: 100%. A single missed interaction is a patient safety event.\n\n### Anti-Patterns\n\n- Making CDSS checks optional or skippable without documented reason\n- Implementing interaction checks as toast notifications\n- Using `any` types for drug or clinical data\n- Hardcoding interaction pairs instead of using a maintainable data structure\n- Silently catching errors in CDSS engine (must surface failures loudly)\n- Skipping weight-based validation when weight is not available (must block, not pass)\n\n## Examples\n\n### Example 1: Drug Interaction Check\n\n```typescript\nconst alerts = checkInteractions('warfarin', ['aspirin', 'metformin'], ['penicillin']);\n\u002F\u002F [{ severity: 'critical', pair: ['warfarin', 'aspirin'],\n\u002F\u002F    message: 'Increased bleeding risk', recommendation: 'Avoid combination' }]\n```\n\n### Example 2: Dose Validation\n\n```typescript\nconst ok = validateDose('paracetamol', 1000, 'oral', 70, 45);\n\u002F\u002F { valid: true, suggestedRange: { min: 500, max: 4000, unit: 'mg' } }\n\nconst bad = validateDose('paracetamol', 5000, 'oral', 70, 45);\n\u002F\u002F { valid: false, message: 'Exceeds absolute max 4000mg' }\n\nconst noWeight = validateDose('gentamicin', 300, 'iv');\n\u002F\u002F { valid: false, factors: ['weight_missing'] }\n```\n\n### Example 3: NEWS2 Scoring\n\n```typescript\nconst result = calculateNEWS2({\n  respiratoryRate: 24, oxygenSaturation: 93, supplementalOxygen: true,\n  temperature: 38.5, systolicBP: 100, heartRate: 110, consciousness: 'voice'\n});\n\u002F\u002F { total: 13, risk: 'high', escalation: 'Urgent clinical review. Consider ICU.' }\n```\n","# Healthcare CDSS Development Patterns\n\nPatterns for building Clinical Decision Support Systems that integrate into EMR workflows. CDSS modules are patient safety critical — zero tolerance for false negatives.\n\n## When to Use\n\n- Implementing drug interaction checking\n- Building dose validation engines\n- Implementing clinical scoring systems (NEWS2, qSOFA, APACHE, GCS)\n- Designing alert systems for abnormal clinical values\n- Building medication order entry with safety checks\n- Integrating lab result interpretation with clinical context\n\n## How It Works\n\nThe CDSS engine is a **pure function library with zero side effects**. Input clinical data, output alerts. This makes it fully testable.\n\nThree primary modules:\n\n1. **`checkInteractions(newDrug, currentMeds, allergies)`** — Checks a new drug against current medications and known allergies. Returns severity-sorted `InteractionAlert[]`. Uses `DrugInteractionPair` data model.\n2. **`validateDose(drug, dose, route, weight, age, renalFunction)`** — Validates a prescribed dose against weight-based, age-adjusted, and renal-adjusted rules. Returns `DoseValidationResult`.\n3. **`calculateNEWS2(vitals)`** — National Early Warning Score 2 from `NEWS2Input`. Returns `NEWS2Result` with total score, risk level, and escalation guidance.\n\n```\nEMR UI\n  ↓ (user enters data)\nCDSS Engine (pure functions, no side effects)\n  ├── Drug Interaction Checker\n  ├── Dose Validator\n  ├── Clinical Scoring (NEWS2, qSOFA, etc.)\n  └── Alert Classifier\n  ↓ (returns alerts)\nEMR UI (displays alerts inline, blocks if critical)\n```\n\n### Drug Interaction Checking\n\n```typescript\ninterface DrugInteractionPair {\n  drugA: string;           \u002F\u002F generic name\n  drugB: string;           \u002F\u002F generic name\n  severity: 'critical' | 'major' | 'minor';\n  mechanism: string;\n  clinicalEffect: string;\n  recommendation: string;\n}\n\nfunction checkInteractions(\n  newDrug: string,\n  currentMedications: string[],\n  allergyList: string[]\n): InteractionAlert[] {\n  if (!newDrug) return [];\n  const alerts: InteractionAlert[] = [];\n  for (const current of currentMedications) {\n    const interaction = findInteraction(newDrug, current);\n    if (interaction) {\n      alerts.push({ severity: interaction.severity, pair: [newDrug, current],\n        message: interaction.clinicalEffect, recommendation: interaction.recommendation });\n    }\n  }\n  for (const allergy of allergyList) {\n    if (isCrossReactive(newDrug, allergy)) {\n      alerts.push({ severity: 'critical', pair: [newDrug, allergy],\n        message: `Cross-reactivity with documented allergy: ${allergy}`,\n        recommendation: 'Do not prescribe without allergy consultation' });\n    }\n  }\n  return alerts.sort((a, b) => severityOrder(a.severity) - severityOrder(b.severity));\n}\n```\n\nInteraction pairs must be **bidirectional**: if Drug A interacts with Drug B, then Drug B interacts with Drug A.\n\n### Dose Validation\n\n```typescript\ninterface DoseValidationResult {\n  valid: boolean;\n  message: string;\n  suggestedRange: { min: number; max: number; unit: string } | null;\n  factors: string[];\n}\n\nfunction validateDose(\n  drug: string,\n  dose: number,\n  route: 'oral' | 'iv' | 'im' | 'sc' | 'topical',\n  patientWeight?: number,\n  patientAge?: number,\n  renalFunction?: number\n): DoseValidationResult {\n  const rules = getDoseRules(drug, route);\n  if (!rules) return { valid: true, message: 'No validation rules available', suggestedRange: null, factors: [] };\n  const factors: string[] = [];\n\n  \u002F\u002F SAFETY: if rules require weight but weight missing, BLOCK (not pass)\n  if (rules.weightBased) {\n    if (!patientWeight || patientWeight \u003C= 0) {\n      return { valid: false, message: `Weight required for ${drug} (mg\u002Fkg drug)`,\n        suggestedRange: null, factors: ['weight_missing'] };\n    }\n    factors.push('weight');\n    const maxDose = rules.maxPerKg * patientWeight;\n    if (dose > maxDose) {\n      return { valid: false, message: `Dose exceeds max for ${patientWeight}kg`,\n        suggestedRange: { min: rules.minPerKg * patientWeight, max: maxDose, unit: rules.unit }, factors };\n    }\n  }\n\n  \u002F\u002F Age-based adjustment (when rules define age brackets and age is provided)\n  if (rules.ageAdjusted && patientAge !== undefined) {\n    factors.push('age');\n    const ageMax = rules.getAgeAdjustedMax(patientAge);\n    if (dose > ageMax) {\n      return { valid: false, message: `Exceeds age-adjusted max for ${patientAge}yr`,\n        suggestedRange: { min: rules.typicalMin, max: ageMax, unit: rules.unit }, factors };\n    }\n  }\n\n  \u002F\u002F Renal adjustment (when rules define eGFR brackets and eGFR is provided)\n  if (rules.renalAdjusted && renalFunction !== undefined) {\n    factors.push('renal');\n    const renalMax = rules.getRenalAdjustedMax(renalFunction);\n    if (dose > renalMax) {\n      return { valid: false, message: `Exceeds renal-adjusted max for eGFR ${renalFunction}`,\n        suggestedRange: { min: rules.typicalMin, max: renalMax, unit: rules.unit }, factors };\n    }\n  }\n\n  \u002F\u002F Absolute max\n  if (dose > rules.absoluteMax) {\n    return { valid: false, message: `Exceeds absolute max ${rules.absoluteMax}${rules.unit}`,\n      suggestedRange: { min: rules.typicalMin, max: rules.absoluteMax, unit: rules.unit },\n      factors: [...factors, 'absolute_max'] };\n  }\n  return { valid: true, message: 'Within range',\n    suggestedRange: { min: rules.typicalMin, max: rules.typicalMax, unit: rules.unit }, factors };\n}\n```\n\n### Clinical Scoring: NEWS2\n\n```typescript\ninterface NEWS2Input {\n  respiratoryRate: number; oxygenSaturation: number; supplementalOxygen: boolean;\n  temperature: number; systolicBP: number; heartRate: number;\n  consciousness: 'alert' | 'voice' | 'pain' | 'unresponsive';\n}\ninterface NEWS2Result {\n  total: number;           \u002F\u002F 0-20\n  risk: 'low' | 'low-medium' | 'medium' | 'high';\n  components: Record\u003Cstring, number>;\n  escalation: string;\n}\n```\n\nScoring tables must match the Royal College of Physicians specification exactly.\n\n### Alert Severity and UI Behavior\n\n| Severity | UI Behavior | Clinician Action Required |\n|----------|-------------|--------------------------|\n| Critical | Block action. Non-dismissable modal. Red. | Must document override reason to proceed |\n| Major | Warning banner inline. Orange. | Must acknowledge before proceeding |\n| Minor | Info note inline. Yellow. | Awareness only, no action required |\n\nCritical alerts must NEVER be auto-dismissed or implemented as toast notifications. Override reasons must be stored in the audit trail.\n\n### Testing CDSS (Zero Tolerance for False Negatives)\n\n```typescript\ndescribe('CDSS — Patient Safety', () => {\n  INTERACTION_PAIRS.forEach(({ drugA, drugB, severity }) => {\n    it(`detects ${drugA} + ${drugB} (${severity})`, () => {\n      const alerts = checkInteractions(drugA, [drugB], []);\n      expect(alerts.length).toBeGreaterThan(0);\n      expect(alerts[0].severity).toBe(severity);\n    });\n    it(`detects ${drugB} + ${drugA} (reverse)`, () => {\n      const alerts = checkInteractions(drugB, [drugA], []);\n      expect(alerts.length).toBeGreaterThan(0);\n    });\n  });\n  it('blocks mg\u002Fkg drug when weight is missing', () => {\n    const result = validateDose('gentamicin', 300, 'iv');\n    expect(result.valid).toBe(false);\n    expect(result.factors).toContain('weight_missing');\n  });\n  it('handles malformed drug data gracefully', () => {\n    expect(() => checkInteractions('', [], [])).not.toThrow();\n  });\n});\n```\n\nPass criteria: 100%. A single missed interaction is a patient safety event.\n\n### Anti-Patterns\n\n- Making CDSS checks optional or skippable without documented reason\n- Implementing interaction checks as toast notifications\n- Using `any` types for drug or clinical data\n- Hardcoding interaction pairs instead of using a maintainable data structure\n- Silently catching errors in CDSS engine (must surface failures loudly)\n- Skipping weight-based validation when weight is not available (must block, not pass)\n\n## Examples\n\n### Example 1: Drug Interaction Check\n\n```typescript\nconst alerts = checkInteractions('warfarin', ['aspirin', 'metformin'], ['penicillin']);\n\u002F\u002F [{ severity: 'critical', pair: ['warfarin', 'aspirin'],\n\u002F\u002F    message: 'Increased bleeding risk', recommendation: 'Avoid combination' }]\n```\n\n### Example 2: Dose Validation\n\n```typescript\nconst ok = validateDose('paracetamol', 1000, 'oral', 70, 45);\n\u002F\u002F { valid: true, suggestedRange: { min: 500, max: 4000, unit: 'mg' } }\n\nconst bad = validateDose('paracetamol', 5000, 'oral', 70, 45);\n\u002F\u002F { valid: false, message: 'Exceeds absolute max 4000mg' }\n\nconst noWeight = validateDose('gentamicin', 300, 'iv');\n\u002F\u002F { valid: false, factors: ['weight_missing'] }\n```\n\n### Example 3: NEWS2 Scoring\n\n```typescript\nconst result = calculateNEWS2({\n  respiratoryRate: 24, oxygenSaturation: 93, supplementalOxygen: true,\n  temperature: 38.5, systolicBP: 100, heartRate: 110, consciousness: 'voice'\n});\n\u002F\u002F { total: 13, risk: 'high', escalation: 'Urgent clinical review. Consider ICU.' }\n```\n",{"name":5,"version":24,"metadata":25,"description":7},"1.0.0",{"origin":26},"Health1 Super Speciality Hospitals — contributed by Dr. Keyur Patel","main","a73152352c0612252131e5cf84e91312a6cf17dc","business-management\u002Fhealthcare-cdss-patterns","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs","https:\u002F\u002Fgithub.com\u002FHenrique1601","https:\u002F\u002Fbezerraportifolio.netlify.app\u002F","Full Stack Developer | React, Next.js, TypeScript, Node.js & IA | Construindo produtos digitais e soluções SaaS","2026-11-15 02:56:04",{"source":8,"skillName":5,"commands":36,"prompt":46,"zipAvailable":47},[37,40,43],{"tool":38,"command":39},"npx","npx skills add Henrique1601\u002FSkiilsToIAs --skill healthcare-cdss-patterns",{"tool":41,"command":42},"bunx","bunx skills add Henrique1601\u002FSkiilsToIAs --skill healthcare-cdss-patterns",{"tool":44,"command":45},"pnpm","pnpm dlx skills add Henrique1601\u002FSkiilsToIAs --skill healthcare-cdss-patterns","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fbusiness-management\u002Fhealthcare-cdss-patterns\u002FSKILL.md",true,[],[50,57,64,72,79,86],{"skillNo":51,"name":52,"nameZh":6,"description":53,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":54,"categories":55,"keywords":56,"publishedAt":19},"01M7E2ANBW9V6AVX5JXNCEAWF8","rag-architect-agent","Agente Arquiteto de RAG, Embeddings & Busca Vetorial. Especialista em design e implementação de pipelines de Retrieval-Augmented Generation de alta fidelidade: chunking semântico, modelagem pgvector no PostgreSQL (Neon\u002FSupabase), busca híbrida (cosseno + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fcustom-agents\u002Frag-architect-agent\u002FSKILL.md",[],[],{"skillNo":58,"name":59,"nameZh":6,"description":60,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":61,"categories":62,"keywords":63,"publishedAt":19},"01M7E29KKF8R02ZRGYE2MJM67G","rag-architecture-patterns","Padrões arquiteturais e implementação de pipelines RAG (Retrieval-Augmented Generation) de alta fidelidade para qualquer projeto ou sistema. Cobre chunking semântico, embeddings, busca híbrida (pgvector + BM25), reranking, validação via TypeSafe AI e filosofia Ponytail (anti-overengineering).","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Fai-agents\u002Frag-architecture-patterns\u002FSKILL.md",[],[],{"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":68,"licenseFileUrl":6,"sourceHtmlUrl":69,"categories":70,"keywords":71,"publishedAt":19},"01M7CWRA8E3BJ7CPY8N8EG28J1","skill-repair","Use this to fix and re-install agent skills that have failed installation.\nThis skill provides the necessary context and permissions to surgically update\nthe `manifest.json` after a fix has been applied.","Apache-2.0","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fskill-repair\u002FSKILL.md",[],[],{"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":19},"01M7CWR66FZP8FA47WVZ4Z2EXC","security-scan","Scan your Claude Code configuration (.claude\u002F directory) for security vulnerabilities, misconfigurations, and injection risks using AgentShield. Checks CLAUDE.md, settings.json, MCP servers, hooks, and agent definitions.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-scan\u002FSKILL.md",[],[],{"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":19},"01M7CWR0QPY58QPTR1P759TFNG","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\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-review\u002FSKILL.md",[],[],{"skillNo":87,"name":88,"nameZh":6,"description":89,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":90,"categories":91,"keywords":92,"publishedAt":19},"01M7CWQXCE40XWT4FZ3VWZFGDP","security-bounty-hunter","Hunt for exploitable, bounty-worthy security issues in repositories. Focuses on remotely reachable vulnerabilities that qualify for real reports instead of noisy local-only findings.","https:\u002F\u002Fgithub.com\u002FHenrique1601\u002FSkiilsToIAs\u002Fblob\u002Fmain\u002Futilities\u002Fsecurity-bounty-hunter\u002FSKILL.md",[],[]]