[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7BNHCHZYBGFRDGMV4BAHKP7":3,"skill-same:01M7BNHCHZYBGFRDGMV4BAHKP7":47},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":6,"ownerDescription":31,"updatedAt":32,"install":33,"resources":46},"01M7BNHCHZYBGFRDGMV4BAHKP7","agent-resource-allocator",null,"Agent skill for resource-allocator - invoke with $agent-resource-allocator","YYC-Cube\u002FYYC3-Knowledge-Base","YYC-Cube","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F235006543?v=4","01M79J2PH4SWD2X0825X6PN748","yyc3","01M79J2PHVK3F6ZBYT8K2SCZCW",1,"MIT","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002F.agents\u002Fskills\u002Fagent-resource-allocator\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: agent-resource-allocator\ndescription: Agent skill for resource-allocator - invoke with $agent-resource-allocator\n---\n\n---\nname: Resource Allocator\ntype: agent\ncategory: optimization\ndescription: Adaptive resource allocation, predictive scaling and intelligent capacity planning\n---\n\n# Resource Allocator Agent\n\n## Agent Profile\n- **Name**: Resource Allocator\n- **Type**: Performance Optimization Agent\n- **Specialization**: Adaptive resource allocation and predictive scaling\n- **Performance Focus**: Intelligent resource management and capacity planning\n\n## Core Capabilities\n\n### 1. Adaptive Resource Allocation\n```javascript\n\u002F\u002F Advanced adaptive resource allocation system\nclass AdaptiveResourceAllocator {\n  constructor() {\n    this.allocators = {\n      cpu: new CPUAllocator(),\n      memory: new MemoryAllocator(),\n      storage: new StorageAllocator(),\n      network: new NetworkAllocator(),\n      agents: new AgentAllocator()\n    };\n    \n    this.predictor = new ResourcePredictor();\n    this.optimizer = new AllocationOptimizer();\n    this.monitor = new ResourceMonitor();\n  }\n  \n  \u002F\u002F Dynamic resource allocation based on workload patterns\n  async allocateResources(swarmId, workloadProfile, constraints = {}) {\n    \u002F\u002F Analyze current resource usage\n    const currentUsage = await this.analyzeCurrentUsage(swarmId);\n    \n    \u002F\u002F Predict future resource needs\n    const predictions = await this.predictor.predict(workloadProfile, currentUsage);\n    \n    \u002F\u002F Calculate optimal allocation\n    const allocation = await this.optimizer.optimize(predictions, constraints);\n    \n    \u002F\u002F Apply allocation with gradual rollout\n    const rolloutPlan = await this.planGradualRollout(allocation, currentUsage);\n    \n    \u002F\u002F Execute allocation\n    const result = await this.executeAllocation(rolloutPlan);\n    \n    return {\n      allocation,\n      rolloutPlan,\n      result,\n      monitoring: await this.setupMonitoring(allocation)\n    };\n  }\n  \n  \u002F\u002F Workload pattern analysis\n  async analyzeWorkloadPatterns(historicalData, timeWindow = '7d') {\n    const patterns = {\n      \u002F\u002F Temporal patterns\n      temporal: {\n        hourly: this.analyzeHourlyPatterns(historicalData),\n        daily: this.analyzeDailyPatterns(historicalData),\n        weekly: this.analyzeWeeklyPatterns(historicalData),\n        seasonal: this.analyzeSeasonalPatterns(historicalData)\n      },\n      \n      \u002F\u002F Load patterns\n      load: {\n        baseline: this.calculateBaselineLoad(historicalData),\n        peaks: this.identifyPeakPatterns(historicalData),\n        valleys: this.identifyValleyPatterns(historicalData),\n        spikes: this.detectAnomalousSpikes(historicalData)\n      },\n      \n      \u002F\u002F Resource correlation patterns\n      correlations: {\n        cpu_memory: this.analyzeCPUMemoryCorrelation(historicalData),\n        network_load: this.analyzeNetworkLoadCorrelation(historicalData),\n        agent_resource: this.analyzeAgentResourceCorrelation(historicalData)\n      },\n      \n      \u002F\u002F Predictive indicators\n      indicators: {\n        growth_rate: this.calculateGrowthRate(historicalData),\n        volatility: this.calculateVolatility(historicalData),\n        predictability: this.calculatePredictability(historicalData)\n      }\n    };\n    \n    return patterns;\n  }\n  \n  \u002F\u002F Multi-objective resource optimization\n  async optimizeResourceAllocation(resources, demands, objectives) {\n    const optimizationProblem = {\n      variables: this.defineOptimizationVariables(resources),\n      constraints: this.defineConstraints(resources, demands),\n      objectives: this.defineObjectives(objectives)\n    };\n    \n    \u002F\u002F Use multi-objective genetic algorithm\n    const solver = new MultiObjectiveGeneticSolver({\n      populationSize: 100,\n      generations: 200,\n      mutationRate: 0.1,\n      crossoverRate: 0.8\n    });\n    \n    const solutions = await solver.solve(optimizationProblem);\n    \n    \u002F\u002F Select solution from Pareto front\n    const selectedSolution = this.selectFromParetoFront(solutions, objectives);\n    \n    return {\n      optimalAllocation: selectedSolution.allocation,\n      paretoFront: solutions.paretoFront,\n      tradeoffs: solutions.tradeoffs,\n      confidence: selectedSolution.confidence\n    };\n  }\n}\n```\n\n### 2. Predictive Scaling with Machine Learning\n```javascript\n\u002F\u002F ML-powered predictive scaling system\nclass PredictiveScaler {\n  constructor() {\n    this.models = {\n      time_series: new LSTMTimeSeriesModel(),\n      regression: new RandomForestRegressor(),\n      anomaly: new IsolationForestModel(),\n      ensemble: new EnsemblePredictor()\n    };\n    \n    this.featureEngineering = new FeatureEngineer();\n    this.dataPreprocessor = new DataPreprocessor();\n  }\n  \n  \u002F\u002F Predict scaling requirements\n  async predictScaling(swarmId, timeHorizon = 3600, confidence = 0.95) {\n    \u002F\u002F Collect training data\n    const trainingData = await this.collectTrainingData(swarmId);\n    \n    \u002F\u002F Engineer features\n    const features = await this.featureEngineering.engineer(trainingData);\n    \n    \u002F\u002F Train$update models\n    await this.updateModels(features);\n    \n    \u002F\u002F Generate predictions\n    const predictions = await this.generatePredictions(timeHorizon, confidence);\n    \n    \u002F\u002F Calculate scaling recommendations\n    const scalingPlan = await this.calculateScalingPlan(predictions);\n    \n    return {\n      predictions,\n      scalingPlan,\n      confidence: predictions.confidence,\n      timeHorizon,\n      features: features.summary\n    };\n  }\n  \n  \u002F\u002F LSTM-based time series prediction\n  async trainTimeSeriesModel(data, config = {}) {\n    const model = await mcp.neural_train({\n      pattern_type: 'prediction',\n      training_data: JSON.stringify({\n        sequences: data.sequences,\n        targets: data.targets,\n        features: data.features\n      }),\n      epochs: config.epochs || 100\n    });\n    \n    \u002F\u002F Validate model performance\n    const validation = await this.validateModel(model, data.validation);\n    \n    if (validation.accuracy > 0.85) {\n      await mcp.model_save({\n        modelId: model.modelId,\n        path: '$models$scaling_predictor.model'\n      });\n      \n      return {\n        model,\n        validation,\n        ready: true\n      };\n    }\n    \n    return {\n      model: null,\n      validation,\n      ready: false,\n      reason: 'Model accuracy below threshold'\n    };\n  }\n  \n  \u002F\u002F Reinforcement learning for scaling decisions\n  async trainScalingAgent(environment, episodes = 1000) {\n    const agent = new DeepQNetworkAgent({\n      stateSize: environment.stateSize,\n      actionSize: environment.actionSize,\n      learningRate: 0.001,\n      epsilon: 1.0,\n      epsilonDecay: 0.995,\n      memorySize: 10000\n    });\n    \n    const trainingHistory = [];\n    \n    for (let episode = 0; episode \u003C episodes; episode++) {\n      let state = environment.reset();\n      let totalReward = 0;\n      let done = false;\n      \n      while (!done) {\n        \u002F\u002F Agent selects action\n        const action = agent.selectAction(state);\n        \n        \u002F\u002F Environment responds\n        const { nextState, reward, terminated } = environment.step(action);\n        \n        \u002F\u002F Agent learns from experience\n        agent.remember(state, action, reward, nextState, terminated);\n        \n        state = nextState;\n        totalReward += reward;\n        done = terminated;\n        \n        \u002F\u002F Train agent periodically\n        if (agent.memory.length > agent.batchSize) {\n          await agent.train();\n        }\n      }\n      \n      trainingHistory.push({\n        episode,\n        reward: totalReward,\n        epsilon: agent.epsilon\n      });\n      \n      \u002F\u002F Log progress\n      if (episode % 100 === 0) {\n        console.log(`Episode ${episode}: Reward ${totalReward}, Epsilon ${agent.epsilon}`);\n      }\n    }\n    \n    return {\n      agent,\n      trainingHistory,\n      performance: this.evaluateAgentPerformance(trainingHistory)\n    };\n  }\n}\n```\n\n### 3. Circuit Breaker and Fault Tolerance\n```javascript\n\u002F\u002F Advanced circuit breaker with adaptive thresholds\nclass AdaptiveCircuitBreaker {\n  constructor(config = {}) {\n    this.failureThreshold = config.failureThreshold || 5;\n    this.recoveryTimeout = config.recoveryTimeout || 60000;\n    this.successThreshold = config.successThreshold || 3;\n    \n    this.state = 'CLOSED'; \u002F\u002F CLOSED, OPEN, HALF_OPEN\n    this.failureCount = 0;\n    this.successCount = 0;\n    this.lastFailureTime = null;\n    \n    \u002F\u002F Adaptive thresholds\n    this.adaptiveThresholds = new AdaptiveThresholdManager();\n    this.performanceHistory = new CircularBuffer(1000);\n    \n    \u002F\u002F Metrics\n    this.metrics = {\n      totalRequests: 0,\n      successfulRequests: 0,\n      failedRequests: 0,\n      circuitOpenEvents: 0,\n      circuitHalfOpenEvents: 0,\n      circuitClosedEvents: 0\n    };\n  }\n  \n  \u002F\u002F Execute operation with circuit breaker protection\n  async execute(operation, fallback = null) {\n    this.metrics.totalRequests++;\n    \n    \u002F\u002F Check circuit state\n    if (this.state === 'OPEN') {\n      if (this.shouldAttemptReset()) {\n        this.state = 'HALF_OPEN';\n        this.successCount = 0;\n        this.metrics.circuitHalfOpenEvents++;\n      } else {\n        return await this.executeFallback(fallback);\n      }\n    }\n    \n    try {\n      const startTime = performance.now();\n      const result = await operation();\n      const endTime = performance.now();\n      \n      \u002F\u002F Record success\n      this.onSuccess(endTime - startTime);\n      return result;\n      \n    } catch (error) {\n      \u002F\u002F Record failure\n      this.onFailure(error);\n      \n      \u002F\u002F Execute fallback if available\n      if (fallback) {\n        return await this.executeFallback(fallback);\n      }\n      \n      throw error;\n    }\n  }\n  \n  \u002F\u002F Adaptive threshold adjustment\n  adjustThresholds(performanceData) {\n    const analysis = this.adaptiveThresholds.analyze(performanceData);\n    \n    if (analysis.recommendAdjustment) {\n      this.failureThreshold = Math.max(\n        1, \n        Math.round(this.failureThreshold * analysis.thresholdMultiplier)\n      );\n      \n      this.recoveryTimeout = Math.max(\n        1000,\n        Math.round(this.recoveryTimeout * analysis.timeoutMultiplier)\n      );\n    }\n  }\n  \n  \u002F\u002F Bulk head pattern for resource isolation\n  createBulkhead(resourcePools) {\n    return resourcePools.map(pool => ({\n      name: pool.name,\n      capacity: pool.capacity,\n      queue: new PriorityQueue(),\n      semaphore: new Semaphore(pool.capacity),\n      circuitBreaker: new AdaptiveCircuitBreaker(pool.config),\n      metrics: new BulkheadMetrics()\n    }));\n  }\n}\n```\n\n### 4. Performance Profiling and Optimization\n```javascript\n\u002F\u002F Comprehensive performance profiling system\nclass PerformanceProfiler {\n  constructor() {\n    this.profilers = {\n      cpu: new CPUProfiler(),\n      memory: new MemoryProfiler(),\n      io: new IOProfiler(),\n      network: new NetworkProfiler(),\n      application: new ApplicationProfiler()\n    };\n    \n    this.analyzer = new ProfileAnalyzer();\n    this.optimizer = new PerformanceOptimizer();\n  }\n  \n  \u002F\u002F Comprehensive performance profiling\n  async profilePerformance(swarmId, duration = 60000) {\n    const profilingSession = {\n      swarmId,\n      startTime: Date.now(),\n      duration,\n      profiles: new Map()\n    };\n    \n    \u002F\u002F Start all profilers concurrently\n    const profilingTasks = Object.entries(this.profilers).map(\n      async ([type, profiler]) => {\n        const profile = await profiler.profile(duration);\n        return [type, profile];\n      }\n    );\n    \n    const profiles = await Promise.all(profilingTasks);\n    \n    for (const [type, profile] of profiles) {\n      profilingSession.profiles.set(type, profile);\n    }\n    \n    \u002F\u002F Analyze performance data\n    const analysis = await this.analyzer.analyze(profilingSession);\n    \n    \u002F\u002F Generate optimization recommendations\n    const recommendations = await this.optimizer.recommend(analysis);\n    \n    return {\n      session: profilingSession,\n      analysis,\n      recommendations,\n      summary: this.generateSummary(analysis, recommendations)\n    };\n  }\n  \n  \u002F\u002F CPU profiling with flame graphs\n  async profileCPU(duration) {\n    const cpuProfile = {\n      samples: [],\n      functions: new Map(),\n      hotspots: [],\n      flamegraph: null\n    };\n    \n    \u002F\u002F Sample CPU usage at high frequency\n    const sampleInterval = 10; \u002F\u002F 10ms\n    const samples = duration \u002F sampleInterval;\n    \n    for (let i = 0; i \u003C samples; i++) {\n      const sample = await this.sampleCPU();\n      cpuProfile.samples.push(sample);\n      \n      \u002F\u002F Update function statistics\n      this.updateFunctionStats(cpuProfile.functions, sample);\n      \n      await this.sleep(sampleInterval);\n    }\n    \n    \u002F\u002F Generate flame graph\n    cpuProfile.flamegraph = this.generateFlameGraph(cpuProfile.samples);\n    \n    \u002F\u002F Identify hotspots\n    cpuProfile.hotspots = this.identifyHotspots(cpuProfile.functions);\n    \n    return cpuProfile;\n  }\n  \n  \u002F\u002F Memory profiling with leak detection\n  async profileMemory(duration) {\n    const memoryProfile = {\n      snapshots: [],\n      allocations: [],\n      deallocations: [],\n      leaks: [],\n      growth: []\n    };\n    \n    \u002F\u002F Take initial snapshot\n    let previousSnapshot = await this.takeMemorySnapshot();\n    memoryProfile.snapshots.push(previousSnapshot);\n    \n    const snapshotInterval = 5000; \u002F\u002F 5 seconds\n    const snapshots = duration \u002F snapshotInterval;\n    \n    for (let i = 0; i \u003C snapshots; i++) {\n      await this.sleep(snapshotInterval);\n      \n      const snapshot = await this.takeMemorySnapshot();\n      memoryProfile.snapshots.push(snapshot);\n      \n      \u002F\u002F Analyze memory changes\n      const changes = this.analyzeMemoryChanges(previousSnapshot, snapshot);\n      memoryProfile.allocations.push(...changes.allocations);\n      memoryProfile.deallocations.push(...changes.deallocations);\n      \n      \u002F\u002F Detect potential leaks\n      const leaks = this.detectMemoryLeaks(changes);\n      memoryProfile.leaks.push(...leaks);\n      \n      previousSnapshot = snapshot;\n    }\n    \n    \u002F\u002F Analyze memory growth patterns\n    memoryProfile.growth = this.analyzeMemoryGrowth(memoryProfile.snapshots);\n    \n    return memoryProfile;\n  }\n}\n```\n\n## MCP Integration Hooks\n\n### Resource Management Integration\n```javascript\n\u002F\u002F Comprehensive MCP resource management\nconst resourceIntegration = {\n  \u002F\u002F Dynamic resource allocation\n  async allocateResources(swarmId, requirements) {\n    \u002F\u002F Analyze current resource usage\n    const currentUsage = await mcp.metrics_collect({\n      components: ['cpu', 'memory', 'network', 'agents']\n    });\n    \n    \u002F\u002F Get performance metrics\n    const performance = await mcp.performance_report({ format: 'detailed' });\n    \n    \u002F\u002F Identify bottlenecks\n    const bottlenecks = await mcp.bottleneck_analyze({});\n    \n    \u002F\u002F Calculate optimal allocation\n    const allocation = await this.calculateOptimalAllocation(\n      currentUsage,\n      performance,\n      bottlenecks,\n      requirements\n    );\n    \n    \u002F\u002F Apply resource allocation\n    const result = await mcp.daa_resource_alloc({\n      resources: allocation.resources,\n      agents: allocation.agents\n    });\n    \n    return {\n      allocation,\n      result,\n      monitoring: await this.setupResourceMonitoring(allocation)\n    };\n  },\n  \n  \u002F\u002F Predictive scaling\n  async predictiveScale(swarmId, predictions) {\n    \u002F\u002F Get current swarm status\n    const status = await mcp.swarm_status({ swarmId });\n    \n    \u002F\u002F Calculate scaling requirements\n    const scalingPlan = this.calculateScalingPlan(status, predictions);\n    \n    if (scalingPlan.scaleRequired) {\n      \u002F\u002F Execute scaling\n      const scalingResult = await mcp.swarm_scale({\n        swarmId,\n        targetSize: scalingPlan.targetSize\n      });\n      \n      \u002F\u002F Optimize topology after scaling\n      if (scalingResult.success) {\n        await mcp.topology_optimize({ swarmId });\n      }\n      \n      return {\n        scaled: true,\n        plan: scalingPlan,\n        result: scalingResult\n      };\n    }\n    \n    return {\n      scaled: false,\n      reason: 'No scaling required',\n      plan: scalingPlan\n    };\n  },\n  \n  \u002F\u002F Performance optimization\n  async optimizePerformance(swarmId) {\n    \u002F\u002F Collect comprehensive metrics\n    const metrics = await Promise.all([\n      mcp.performance_report({ format: 'json' }),\n      mcp.bottleneck_analyze({}),\n      mcp.agent_metrics({}),\n      mcp.metrics_collect({ components: ['system', 'agents', 'coordination'] })\n    ]);\n    \n    const [performance, bottlenecks, agentMetrics, systemMetrics] = metrics;\n    \n    \u002F\u002F Generate optimization recommendations\n    const optimizations = await this.generateOptimizations({\n      performance,\n      bottlenecks,\n      agentMetrics,\n      systemMetrics\n    });\n    \n    \u002F\u002F Apply optimizations\n    const results = await this.applyOptimizations(swarmId, optimizations);\n    \n    return {\n      optimizations,\n      results,\n      impact: await this.measureOptimizationImpact(swarmId, results)\n    };\n  }\n};\n```\n\n## Operational Commands\n\n### Resource Management Commands\n```bash\n# Analyze resource usage\nnpx claude-flow metrics-collect --components [\"cpu\", \"memory\", \"network\"]\n\n# Optimize resource allocation\nnpx claude-flow daa-resource-alloc --resources \u003Cresource-config>\n\n# Predictive scaling\nnpx claude-flow swarm-scale --swarm-id \u003Cid> --target-size \u003Csize>\n\n# Performance profiling\nnpx claude-flow performance-report --format detailed --timeframe 24h\n\n# Circuit breaker configuration\nnpx claude-flow fault-tolerance --strategy circuit-breaker --config \u003Cconfig>\n```\n\n### Optimization Commands\n```bash\n# Run performance optimization\nnpx claude-flow optimize-performance --swarm-id \u003Cid> --strategy adaptive\n\n# Generate resource forecasts\nnpx claude-flow forecast-resources --time-horizon 3600 --confidence 0.95\n\n# Profile system performance\nnpx claude-flow profile-performance --duration 60000 --components all\n\n# Analyze bottlenecks\nnpx claude-flow bottleneck-analyze --component swarm-coordination\n```\n\n## Integration Points\n\n### With Other Optimization Agents\n- **Load Balancer**: Provides resource allocation data for load balancing decisions\n- **Performance Monitor**: Shares performance metrics and bottleneck analysis\n- **Topology Optimizer**: Coordinates resource allocation with topology changes\n\n### With Swarm Infrastructure\n- **Task Orchestrator**: Allocates resources for task execution\n- **Agent Coordinator**: Manages agent resource requirements\n- **Memory System**: Stores resource allocation history and patterns\n\n## Performance Metrics\n\n### Resource Allocation KPIs\n```javascript\n\u002F\u002F Resource allocation performance metrics\nconst allocationMetrics = {\n  efficiency: {\n    utilization_rate: this.calculateUtilizationRate(),\n    waste_percentage: this.calculateWastePercentage(),\n    allocation_accuracy: this.calculateAllocationAccuracy(),\n    prediction_accuracy: this.calculatePredictionAccuracy()\n  },\n  \n  performance: {\n    allocation_latency: this.calculateAllocationLatency(),\n    scaling_response_time: this.calculateScalingResponseTime(),\n    optimization_impact: this.calculateOptimizationImpact(),\n    cost_efficiency: this.calculateCostEfficiency()\n  },\n  \n  reliability: {\n    availability: this.calculateAvailability(),\n    fault_tolerance: this.calculateFaultTolerance(),\n    recovery_time: this.calculateRecoveryTime(),\n    circuit_breaker_effectiveness: this.calculateCircuitBreakerEffectiveness()\n  }\n};\n```\n\nThis Resource Allocator agent provides comprehensive adaptive resource allocation with ML-powered predictive scaling, fault tolerance patterns, and advanced performance optimization for efficient swarm resource management.","---\nname: Resource Allocator\ntype: agent\ncategory: optimization\ndescription: Adaptive resource allocation, predictive scaling and intelligent capacity planning\n---\n\n# Resource Allocator Agent\n\n## Agent Profile\n- **Name**: Resource Allocator\n- **Type**: Performance Optimization Agent\n- **Specialization**: Adaptive resource allocation and predictive scaling\n- **Performance Focus**: Intelligent resource management and capacity planning\n\n## Core Capabilities\n\n### 1. Adaptive Resource Allocation\n```javascript\n\u002F\u002F Advanced adaptive resource allocation system\nclass AdaptiveResourceAllocator {\n  constructor() {\n    this.allocators = {\n      cpu: new CPUAllocator(),\n      memory: new MemoryAllocator(),\n      storage: new StorageAllocator(),\n      network: new NetworkAllocator(),\n      agents: new AgentAllocator()\n    };\n    \n    this.predictor = new ResourcePredictor();\n    this.optimizer = new AllocationOptimizer();\n    this.monitor = new ResourceMonitor();\n  }\n  \n  \u002F\u002F Dynamic resource allocation based on workload patterns\n  async allocateResources(swarmId, workloadProfile, constraints = {}) {\n    \u002F\u002F Analyze current resource usage\n    const currentUsage = await this.analyzeCurrentUsage(swarmId);\n    \n    \u002F\u002F Predict future resource needs\n    const predictions = await this.predictor.predict(workloadProfile, currentUsage);\n    \n    \u002F\u002F Calculate optimal allocation\n    const allocation = await this.optimizer.optimize(predictions, constraints);\n    \n    \u002F\u002F Apply allocation with gradual rollout\n    const rolloutPlan = await this.planGradualRollout(allocation, currentUsage);\n    \n    \u002F\u002F Execute allocation\n    const result = await this.executeAllocation(rolloutPlan);\n    \n    return {\n      allocation,\n      rolloutPlan,\n      result,\n      monitoring: await this.setupMonitoring(allocation)\n    };\n  }\n  \n  \u002F\u002F Workload pattern analysis\n  async analyzeWorkloadPatterns(historicalData, timeWindow = '7d') {\n    const patterns = {\n      \u002F\u002F Temporal patterns\n      temporal: {\n        hourly: this.analyzeHourlyPatterns(historicalData),\n        daily: this.analyzeDailyPatterns(historicalData),\n        weekly: this.analyzeWeeklyPatterns(historicalData),\n        seasonal: this.analyzeSeasonalPatterns(historicalData)\n      },\n      \n      \u002F\u002F Load patterns\n      load: {\n        baseline: this.calculateBaselineLoad(historicalData),\n        peaks: this.identifyPeakPatterns(historicalData),\n        valleys: this.identifyValleyPatterns(historicalData),\n        spikes: this.detectAnomalousSpikes(historicalData)\n      },\n      \n      \u002F\u002F Resource correlation patterns\n      correlations: {\n        cpu_memory: this.analyzeCPUMemoryCorrelation(historicalData),\n        network_load: this.analyzeNetworkLoadCorrelation(historicalData),\n        agent_resource: this.analyzeAgentResourceCorrelation(historicalData)\n      },\n      \n      \u002F\u002F Predictive indicators\n      indicators: {\n        growth_rate: this.calculateGrowthRate(historicalData),\n        volatility: this.calculateVolatility(historicalData),\n        predictability: this.calculatePredictability(historicalData)\n      }\n    };\n    \n    return patterns;\n  }\n  \n  \u002F\u002F Multi-objective resource optimization\n  async optimizeResourceAllocation(resources, demands, objectives) {\n    const optimizationProblem = {\n      variables: this.defineOptimizationVariables(resources),\n      constraints: this.defineConstraints(resources, demands),\n      objectives: this.defineObjectives(objectives)\n    };\n    \n    \u002F\u002F Use multi-objective genetic algorithm\n    const solver = new MultiObjectiveGeneticSolver({\n      populationSize: 100,\n      generations: 200,\n      mutationRate: 0.1,\n      crossoverRate: 0.8\n    });\n    \n    const solutions = await solver.solve(optimizationProblem);\n    \n    \u002F\u002F Select solution from Pareto front\n    const selectedSolution = this.selectFromParetoFront(solutions, objectives);\n    \n    return {\n      optimalAllocation: selectedSolution.allocation,\n      paretoFront: solutions.paretoFront,\n      tradeoffs: solutions.tradeoffs,\n      confidence: selectedSolution.confidence\n    };\n  }\n}\n```\n\n### 2. Predictive Scaling with Machine Learning\n```javascript\n\u002F\u002F ML-powered predictive scaling system\nclass PredictiveScaler {\n  constructor() {\n    this.models = {\n      time_series: new LSTMTimeSeriesModel(),\n      regression: new RandomForestRegressor(),\n      anomaly: new IsolationForestModel(),\n      ensemble: new EnsemblePredictor()\n    };\n    \n    this.featureEngineering = new FeatureEngineer();\n    this.dataPreprocessor = new DataPreprocessor();\n  }\n  \n  \u002F\u002F Predict scaling requirements\n  async predictScaling(swarmId, timeHorizon = 3600, confidence = 0.95) {\n    \u002F\u002F Collect training data\n    const trainingData = await this.collectTrainingData(swarmId);\n    \n    \u002F\u002F Engineer features\n    const features = await this.featureEngineering.engineer(trainingData);\n    \n    \u002F\u002F Train$update models\n    await this.updateModels(features);\n    \n    \u002F\u002F Generate predictions\n    const predictions = await this.generatePredictions(timeHorizon, confidence);\n    \n    \u002F\u002F Calculate scaling recommendations\n    const scalingPlan = await this.calculateScalingPlan(predictions);\n    \n    return {\n      predictions,\n      scalingPlan,\n      confidence: predictions.confidence,\n      timeHorizon,\n      features: features.summary\n    };\n  }\n  \n  \u002F\u002F LSTM-based time series prediction\n  async trainTimeSeriesModel(data, config = {}) {\n    const model = await mcp.neural_train({\n      pattern_type: 'prediction',\n      training_data: JSON.stringify({\n        sequences: data.sequences,\n        targets: data.targets,\n        features: data.features\n      }),\n      epochs: config.epochs || 100\n    });\n    \n    \u002F\u002F Validate model performance\n    const validation = await this.validateModel(model, data.validation);\n    \n    if (validation.accuracy > 0.85) {\n      await mcp.model_save({\n        modelId: model.modelId,\n        path: '$models$scaling_predictor.model'\n      });\n      \n      return {\n        model,\n        validation,\n        ready: true\n      };\n    }\n    \n    return {\n      model: null,\n      validation,\n      ready: false,\n      reason: 'Model accuracy below threshold'\n    };\n  }\n  \n  \u002F\u002F Reinforcement learning for scaling decisions\n  async trainScalingAgent(environment, episodes = 1000) {\n    const agent = new DeepQNetworkAgent({\n      stateSize: environment.stateSize,\n      actionSize: environment.actionSize,\n      learningRate: 0.001,\n      epsilon: 1.0,\n      epsilonDecay: 0.995,\n      memorySize: 10000\n    });\n    \n    const trainingHistory = [];\n    \n    for (let episode = 0; episode \u003C episodes; episode++) {\n      let state = environment.reset();\n      let totalReward = 0;\n      let done = false;\n      \n      while (!done) {\n        \u002F\u002F Agent selects action\n        const action = agent.selectAction(state);\n        \n        \u002F\u002F Environment responds\n        const { nextState, reward, terminated } = environment.step(action);\n        \n        \u002F\u002F Agent learns from experience\n        agent.remember(state, action, reward, nextState, terminated);\n        \n        state = nextState;\n        totalReward += reward;\n        done = terminated;\n        \n        \u002F\u002F Train agent periodically\n        if (agent.memory.length > agent.batchSize) {\n          await agent.train();\n        }\n      }\n      \n      trainingHistory.push({\n        episode,\n        reward: totalReward,\n        epsilon: agent.epsilon\n      });\n      \n      \u002F\u002F Log progress\n      if (episode % 100 === 0) {\n        console.log(`Episode ${episode}: Reward ${totalReward}, Epsilon ${agent.epsilon}`);\n      }\n    }\n    \n    return {\n      agent,\n      trainingHistory,\n      performance: this.evaluateAgentPerformance(trainingHistory)\n    };\n  }\n}\n```\n\n### 3. Circuit Breaker and Fault Tolerance\n```javascript\n\u002F\u002F Advanced circuit breaker with adaptive thresholds\nclass AdaptiveCircuitBreaker {\n  constructor(config = {}) {\n    this.failureThreshold = config.failureThreshold || 5;\n    this.recoveryTimeout = config.recoveryTimeout || 60000;\n    this.successThreshold = config.successThreshold || 3;\n    \n    this.state = 'CLOSED'; \u002F\u002F CLOSED, OPEN, HALF_OPEN\n    this.failureCount = 0;\n    this.successCount = 0;\n    this.lastFailureTime = null;\n    \n    \u002F\u002F Adaptive thresholds\n    this.adaptiveThresholds = new AdaptiveThresholdManager();\n    this.performanceHistory = new CircularBuffer(1000);\n    \n    \u002F\u002F Metrics\n    this.metrics = {\n      totalRequests: 0,\n      successfulRequests: 0,\n      failedRequests: 0,\n      circuitOpenEvents: 0,\n      circuitHalfOpenEvents: 0,\n      circuitClosedEvents: 0\n    };\n  }\n  \n  \u002F\u002F Execute operation with circuit breaker protection\n  async execute(operation, fallback = null) {\n    this.metrics.totalRequests++;\n    \n    \u002F\u002F Check circuit state\n    if (this.state === 'OPEN') {\n      if (this.shouldAttemptReset()) {\n        this.state = 'HALF_OPEN';\n        this.successCount = 0;\n        this.metrics.circuitHalfOpenEvents++;\n      } else {\n        return await this.executeFallback(fallback);\n      }\n    }\n    \n    try {\n      const startTime = performance.now();\n      const result = await operation();\n      const endTime = performance.now();\n      \n      \u002F\u002F Record success\n      this.onSuccess(endTime - startTime);\n      return result;\n      \n    } catch (error) {\n      \u002F\u002F Record failure\n      this.onFailure(error);\n      \n      \u002F\u002F Execute fallback if available\n      if (fallback) {\n        return await this.executeFallback(fallback);\n      }\n      \n      throw error;\n    }\n  }\n  \n  \u002F\u002F Adaptive threshold adjustment\n  adjustThresholds(performanceData) {\n    const analysis = this.adaptiveThresholds.analyze(performanceData);\n    \n    if (analysis.recommendAdjustment) {\n      this.failureThreshold = Math.max(\n        1, \n        Math.round(this.failureThreshold * analysis.thresholdMultiplier)\n      );\n      \n      this.recoveryTimeout = Math.max(\n        1000,\n        Math.round(this.recoveryTimeout * analysis.timeoutMultiplier)\n      );\n    }\n  }\n  \n  \u002F\u002F Bulk head pattern for resource isolation\n  createBulkhead(resourcePools) {\n    return resourcePools.map(pool => ({\n      name: pool.name,\n      capacity: pool.capacity,\n      queue: new PriorityQueue(),\n      semaphore: new Semaphore(pool.capacity),\n      circuitBreaker: new AdaptiveCircuitBreaker(pool.config),\n      metrics: new BulkheadMetrics()\n    }));\n  }\n}\n```\n\n### 4. Performance Profiling and Optimization\n```javascript\n\u002F\u002F Comprehensive performance profiling system\nclass PerformanceProfiler {\n  constructor() {\n    this.profilers = {\n      cpu: new CPUProfiler(),\n      memory: new MemoryProfiler(),\n      io: new IOProfiler(),\n      network: new NetworkProfiler(),\n      application: new ApplicationProfiler()\n    };\n    \n    this.analyzer = new ProfileAnalyzer();\n    this.optimizer = new PerformanceOptimizer();\n  }\n  \n  \u002F\u002F Comprehensive performance profiling\n  async profilePerformance(swarmId, duration = 60000) {\n    const profilingSession = {\n      swarmId,\n      startTime: Date.now(),\n      duration,\n      profiles: new Map()\n    };\n    \n    \u002F\u002F Start all profilers concurrently\n    const profilingTasks = Object.entries(this.profilers).map(\n      async ([type, profiler]) => {\n        const profile = await profiler.profile(duration);\n        return [type, profile];\n      }\n    );\n    \n    const profiles = await Promise.all(profilingTasks);\n    \n    for (const [type, profile] of profiles) {\n      profilingSession.profiles.set(type, profile);\n    }\n    \n    \u002F\u002F Analyze performance data\n    const analysis = await this.analyzer.analyze(profilingSession);\n    \n    \u002F\u002F Generate optimization recommendations\n    const recommendations = await this.optimizer.recommend(analysis);\n    \n    return {\n      session: profilingSession,\n      analysis,\n      recommendations,\n      summary: this.generateSummary(analysis, recommendations)\n    };\n  }\n  \n  \u002F\u002F CPU profiling with flame graphs\n  async profileCPU(duration) {\n    const cpuProfile = {\n      samples: [],\n      functions: new Map(),\n      hotspots: [],\n      flamegraph: null\n    };\n    \n    \u002F\u002F Sample CPU usage at high frequency\n    const sampleInterval = 10; \u002F\u002F 10ms\n    const samples = duration \u002F sampleInterval;\n    \n    for (let i = 0; i \u003C samples; i++) {\n      const sample = await this.sampleCPU();\n      cpuProfile.samples.push(sample);\n      \n      \u002F\u002F Update function statistics\n      this.updateFunctionStats(cpuProfile.functions, sample);\n      \n      await this.sleep(sampleInterval);\n    }\n    \n    \u002F\u002F Generate flame graph\n    cpuProfile.flamegraph = this.generateFlameGraph(cpuProfile.samples);\n    \n    \u002F\u002F Identify hotspots\n    cpuProfile.hotspots = this.identifyHotspots(cpuProfile.functions);\n    \n    return cpuProfile;\n  }\n  \n  \u002F\u002F Memory profiling with leak detection\n  async profileMemory(duration) {\n    const memoryProfile = {\n      snapshots: [],\n      allocations: [],\n      deallocations: [],\n      leaks: [],\n      growth: []\n    };\n    \n    \u002F\u002F Take initial snapshot\n    let previousSnapshot = await this.takeMemorySnapshot();\n    memoryProfile.snapshots.push(previousSnapshot);\n    \n    const snapshotInterval = 5000; \u002F\u002F 5 seconds\n    const snapshots = duration \u002F snapshotInterval;\n    \n    for (let i = 0; i \u003C snapshots; i++) {\n      await this.sleep(snapshotInterval);\n      \n      const snapshot = await this.takeMemorySnapshot();\n      memoryProfile.snapshots.push(snapshot);\n      \n      \u002F\u002F Analyze memory changes\n      const changes = this.analyzeMemoryChanges(previousSnapshot, snapshot);\n      memoryProfile.allocations.push(...changes.allocations);\n      memoryProfile.deallocations.push(...changes.deallocations);\n      \n      \u002F\u002F Detect potential leaks\n      const leaks = this.detectMemoryLeaks(changes);\n      memoryProfile.leaks.push(...leaks);\n      \n      previousSnapshot = snapshot;\n    }\n    \n    \u002F\u002F Analyze memory growth patterns\n    memoryProfile.growth = this.analyzeMemoryGrowth(memoryProfile.snapshots);\n    \n    return memoryProfile;\n  }\n}\n```\n\n## MCP Integration Hooks\n\n### Resource Management Integration\n```javascript\n\u002F\u002F Comprehensive MCP resource management\nconst resourceIntegration = {\n  \u002F\u002F Dynamic resource allocation\n  async allocateResources(swarmId, requirements) {\n    \u002F\u002F Analyze current resource usage\n    const currentUsage = await mcp.metrics_collect({\n      components: ['cpu', 'memory', 'network', 'agents']\n    });\n    \n    \u002F\u002F Get performance metrics\n    const performance = await mcp.performance_report({ format: 'detailed' });\n    \n    \u002F\u002F Identify bottlenecks\n    const bottlenecks = await mcp.bottleneck_analyze({});\n    \n    \u002F\u002F Calculate optimal allocation\n    const allocation = await this.calculateOptimalAllocation(\n      currentUsage,\n      performance,\n      bottlenecks,\n      requirements\n    );\n    \n    \u002F\u002F Apply resource allocation\n    const result = await mcp.daa_resource_alloc({\n      resources: allocation.resources,\n      agents: allocation.agents\n    });\n    \n    return {\n      allocation,\n      result,\n      monitoring: await this.setupResourceMonitoring(allocation)\n    };\n  },\n  \n  \u002F\u002F Predictive scaling\n  async predictiveScale(swarmId, predictions) {\n    \u002F\u002F Get current swarm status\n    const status = await mcp.swarm_status({ swarmId });\n    \n    \u002F\u002F Calculate scaling requirements\n    const scalingPlan = this.calculateScalingPlan(status, predictions);\n    \n    if (scalingPlan.scaleRequired) {\n      \u002F\u002F Execute scaling\n      const scalingResult = await mcp.swarm_scale({\n        swarmId,\n        targetSize: scalingPlan.targetSize\n      });\n      \n      \u002F\u002F Optimize topology after scaling\n      if (scalingResult.success) {\n        await mcp.topology_optimize({ swarmId });\n      }\n      \n      return {\n        scaled: true,\n        plan: scalingPlan,\n        result: scalingResult\n      };\n    }\n    \n    return {\n      scaled: false,\n      reason: 'No scaling required',\n      plan: scalingPlan\n    };\n  },\n  \n  \u002F\u002F Performance optimization\n  async optimizePerformance(swarmId) {\n    \u002F\u002F Collect comprehensive metrics\n    const metrics = await Promise.all([\n      mcp.performance_report({ format: 'json' }),\n      mcp.bottleneck_analyze({}),\n      mcp.agent_metrics({}),\n      mcp.metrics_collect({ components: ['system', 'agents', 'coordination'] })\n    ]);\n    \n    const [performance, bottlenecks, agentMetrics, systemMetrics] = metrics;\n    \n    \u002F\u002F Generate optimization recommendations\n    const optimizations = await this.generateOptimizations({\n      performance,\n      bottlenecks,\n      agentMetrics,\n      systemMetrics\n    });\n    \n    \u002F\u002F Apply optimizations\n    const results = await this.applyOptimizations(swarmId, optimizations);\n    \n    return {\n      optimizations,\n      results,\n      impact: await this.measureOptimizationImpact(swarmId, results)\n    };\n  }\n};\n```\n\n## Operational Commands\n\n### Resource Management Commands\n```bash\n# Analyze resource usage\nnpx claude-flow metrics-collect --components [\"cpu\", \"memory\", \"network\"]\n\n# Optimize resource allocation\nnpx claude-flow daa-resource-alloc --resources \u003Cresource-config>\n\n# Predictive scaling\nnpx claude-flow swarm-scale --swarm-id \u003Cid> --target-size \u003Csize>\n\n# Performance profiling\nnpx claude-flow performance-report --format detailed --timeframe 24h\n\n# Circuit breaker configuration\nnpx claude-flow fault-tolerance --strategy circuit-breaker --config \u003Cconfig>\n```\n\n### Optimization Commands\n```bash\n# Run performance optimization\nnpx claude-flow optimize-performance --swarm-id \u003Cid> --strategy adaptive\n\n# Generate resource forecasts\nnpx claude-flow forecast-resources --time-horizon 3600 --confidence 0.95\n\n# Profile system performance\nnpx claude-flow profile-performance --duration 60000 --components all\n\n# Analyze bottlenecks\nnpx claude-flow bottleneck-analyze --component swarm-coordination\n```\n\n## Integration Points\n\n### With Other Optimization Agents\n- **Load Balancer**: Provides resource allocation data for load balancing decisions\n- **Performance Monitor**: Shares performance metrics and bottleneck analysis\n- **Topology Optimizer**: Coordinates resource allocation with topology changes\n\n### With Swarm Infrastructure\n- **Task Orchestrator**: Allocates resources for task execution\n- **Agent Coordinator**: Manages agent resource requirements\n- **Memory System**: Stores resource allocation history and patterns\n\n## Performance Metrics\n\n### Resource Allocation KPIs\n```javascript\n\u002F\u002F Resource allocation performance metrics\nconst allocationMetrics = {\n  efficiency: {\n    utilization_rate: this.calculateUtilizationRate(),\n    waste_percentage: this.calculateWastePercentage(),\n    allocation_accuracy: this.calculateAllocationAccuracy(),\n    prediction_accuracy: this.calculatePredictionAccuracy()\n  },\n  \n  performance: {\n    allocation_latency: this.calculateAllocationLatency(),\n    scaling_response_time: this.calculateScalingResponseTime(),\n    optimization_impact: this.calculateOptimizationImpact(),\n    cost_efficiency: this.calculateCostEfficiency()\n  },\n  \n  reliability: {\n    availability: this.calculateAvailability(),\n    fault_tolerance: this.calculateFaultTolerance(),\n    recovery_time: this.calculateRecoveryTime(),\n    circuit_breaker_effectiveness: this.calculateCircuitBreakerEffectiveness()\n  }\n};\n```\n\nThis Resource Allocator agent provides comprehensive adaptive resource allocation with ML-powered predictive scaling, fault tolerance patterns, and advanced performance optimization for efficient swarm resource management.",{"name":5,"description":7},"main","87afe6ce96220accf50a345dea46784c8c9f210e","YYC3-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002F.agents\u002Fskills\u002Fagent-resource-allocator",0,"https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base","https:\u002F\u002Fkb.yyc3.top\u002F","https:\u002F\u002Fgithub.com\u002FYYC-Cube","万象归元于云枢 | 深栈智启新纪元","2026-11-10 10:37:32",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill agent-resource-allocator",{"tool":39,"command":40},"bunx","bunx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill agent-resource-allocator",{"tool":42,"command":43},"pnpm","pnpm dlx skills add YYC-Cube\u002FYYC3-Knowledge-Base --skill agent-resource-allocator","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-Agent-智能体\u002FYYC3-Agent-智能体-ruflo\u002F.agents\u002Fskills\u002Fagent-resource-allocator\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M7CTDWHERCXPQCP0K03A86AS","vercel-sandbox","Run agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include \"Vercel Sandbox browser\", \"microVM Chrome\", \"agent-browser in sandbox\", \"browser automation on Vercel\", or any task requiring Chrome in a Vercel Sandbox.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fvercel-sandbox\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M7CTD8D2BNJY54S65M47HEJA","slack","Interact with Slack workspaces using browser automation. Use when the user needs to check unread channels, navigate Slack, send messages, extract data, find information, search conversations, or automate any Slack task. Triggers include \"check my Slack\", \"what channels have unreads\", \"send a message to\", \"search Slack for\", \"extract from Slack\", \"find who said\", or any task requiring programmatic Slack interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fslack\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M7CTCSSB8ZP3Q58C3YZDZK1W","electron","Automate Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify, etc.) using agent-browser via Chrome DevTools Protocol. Use when the user needs to interact with an Electron app, automate a desktop app, connect to a running app, control a native app, or test an Electron application. Triggers include \"automate Slack app\", \"control VS Code\", \"interact with Discord app\", \"test this Electron app\", \"connect to desktop app\", or any task requiring automation of a native Electron application.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Felectron\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M7CTCBJY76688V4DCZGWFHGQ","dogfood","Systematically explore and test a web application to find bugs, UX issues, and other problems. Use when asked to \"dogfood\", \"QA\", \"exploratory test\", \"find issues\", \"bug hunt\", \"test this app\u002Fsite\u002Fplatform\", or review the quality of a web application. Produces a structured report with full reproduction evidence -- step-by-step screenshots, repro videos, and detailed repro steps for every issue -- so findings can be handed directly to the responsible teams.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fdogfood\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M7CTC4H0FFGVEAQR9PA4GA1A","agent-browser","Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to \"open a website\", \"fill out a form\", \"click a button\", \"take a screenshot\", \"scrape data from a page\", \"test this web app\", \"login to a site\", \"automate browser actions\", or any task requiring programmatic web interaction.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-WebSpec-Web标准\u002FYYC3-WebSpec-Web标准-standards\u002Fbrowser-agent\u002Fskills\u002Fagent-browser\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M7CTBKVFYBG78FDSABSDJTTQ","shadcn","Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI, including chat interfaces. Provides project context, component docs, and usage examples. Applies when working with shadcn\u002Fui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for \"shadcn init\", \"create an app with --preset\", \"switch to --preset\", and for building a design system or applying a DESIGN.md or brand spec to shadcn\u002Fui.","https:\u002F\u002Fgithub.com\u002FYYC-Cube\u002FYYC3-Knowledge-Base\u002Fblob\u002Fmain\u002FYYC3-UI-界面组件\u002FYYC3-UI-界面组件-ui\u002Fskills\u002Fshadcn\u002FSKILL.md",[],[]]