Skip to main content Skills Marketplace Descubra e explore skills de IA criadas pela comunidade.
Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.
Mostrar detalhes do prompt Um comando direto ignora o prompt de revisão. Verifique a origem antes de executá-lo.
npx skills add https://github.com/majiayu000/claude-skill-registry --skill cloud-neuralO comando permanece em uma só linha. Role horizontalmente para revisá-lo antes de copiar.
Prefere uma cópia local? Baixe os arquivos disponíveis atualmente no SkillsMP.
Baixar Zip Baixando... Ocupações relacionadas SOC
Baseado na classificação ocupacional SOC
Explorador de arquivos
2 arquivos name cloud-neural description Neural network training and deployment in Flow Nexus cloud. Use for distributed ML training, model inference, and neural network lifecycle management. version 1.0.0 category cloud type skill capabilities ["neural_network_training","distributed_training","model_inference","cluster_management","template_deployment","model_validation"] tools ["mcp__flow-nexus__neural_train","mcp__flow-nexus__neural_predict","mcp__flow-nexus__neural_cluster_init","mcp__flow-nexus__neural_node_deploy","mcp__flow-nexus__neural_cluster_connect","mcp__flow-nexus__neural_train_distributed","mcp__flow-nexus__neural_cluster_status","mcp__flow-nexus__neural_predict_distributed","mcp__flow-nexus__neural_cluster_terminate","mcp__flow-nexus__neural_list_templates","mcp__flow-nexus__neural_deploy_template","mcp__flow-nexus__neural_training_status","mcp__flow-nexus__neural_list_models","mcp__flow-nexus__neural_validation_workflow","mcp__flow-nexus__neural_publish_template","mcp__flow-nexus__neural_rate_template","mcp__flow-nexus__neural_performance_benchmark"] related_skills ["cloud-swarm","cloud-sandbox","cloud-workflow"]
Cloud Neural Network
Train, deploy, and manage neural networks at scale using Flow Nexus cloud-powered distributed computing.
Quick Start
mcp__flow-nexus__neural_train ({
config : {
architecture : {
type : "feedforward" ,
layers : [
{ type : "dense" , units : 128 , activation : "relu" },
{ type : "dropout" , rate : 0.2 },
{ type : "dense" , units : 10 , activation : "softmax" }
]
},
training : { epochs : 100 , batch_size : 32 , learning_rate : 0.001 }
},
tier : "small"
})
mcp__flow-nexus__neural_predict ({
model_id : "trained_model_id" ,
input : [[0.5 , 0.3 , 0.2 ]]
})
When to Use
Training neural networks for classification, regression, or generation tasks
Deploying distributed training across multiple cloud sandboxes
Running model inference on trained models
Managing model lifecycle from training to production deployment
Implementing federated learning or ensemble methods
Fine-tuning pre-trained models for specific domains
Prerequisites
Flow Nexus account with active session
MCP server flow-nexus configured
Sufficient rUv credits for training tier selected
Core Concepts
Neural Architectures Type Use Case Feedforward Classification, regression LSTM/RNN Time series, NLP sequences Transformer Advanced NLP, multimodal CNN Computer vision, image processing GAN Data generation, augmentation Autoencoder Dimensionality reduction, anomaly detection
Training Tiers Tier Resources Cost nanoMinimal, quick tests Low miniSmall models Low smallStandard training Medium mediumLarge models High largeProduction scale Highest
Distributed Consensus Protocols
proof-of-learning : Training contribution verificationbyzantine : Fault-tolerant distributed consensusraft : Leader-based coordinationgossip : Decentralized information propagation
MCP Tools Reference
Single-Node Training mcp__flow-nexus__neural_train ({
config : {
architecture : {
type : "feedforward" ,
layers : [
{ type : "dense" , units : 128 , activation : "relu" },
{ type : "dropout" , rate : 0.2 },
{ type : "dense" , units : 10 , activation : "softmax" }
]
},
training : {
epochs : 100 ,
batch_size : 32 ,
learning_rate : 0.001 ,
optimizer : "adam"
},
divergent : {
enabled : false ,
pattern : "lateral" ,
factor : 0.1
}
},
tier : "small" ,
user_id : "user_id"
})
Distributed Cluster Training
mcp__flow-nexus__neural_cluster_init ({
name : "training-cluster" ,
architecture : "transformer" ,
topology : "mesh" ,
consensus : "proof-of-learning" ,
daaEnabled : true ,
wasmOptimization : true
})
mcp__flow-nexus__neural_node_deploy ({
cluster_id : "cluster_id" ,
node_type : "worker" ,
model : "base" ,
capabilities : ["training" , "inference" ],
autonomy : 0.8
})
mcp__flow-nexus__neural_cluster_connect ({
cluster_id : "cluster_id" ,
topology : "mesh"
})
mcp__flow-nexus__neural_train_distributed ({
cluster_id : "cluster_id" ,
dataset : "dataset_id" ,
epochs : 10 ,
batch_size : 32 ,
learning_rate : 0.001 ,
optimizer : "adam" ,
federated : false
})
mcp__flow-nexus__neural_cluster_status ({ cluster_id : "cluster_id" })
mcp__flow-nexus__neural_cluster_terminate ({ cluster_id : "cluster_id" })
Inference
mcp__flow-nexus__neural_predict ({
model_id : "model_id" ,
input : [[0.5 , 0.3 , 0.2 ]],
user_id : "user_id"
})
mcp__flow-nexus__neural_predict_distributed ({
cluster_id : "cluster_id" ,
input_data : "[0.5, 0.3, 0.2]" ,
aggregation : "mean"
})
Template Management
mcp__flow-nexus__neural_list_templates ({
category : "classification" ,
tier : "free" ,
search : "sentiment" ,
limit : 20
})
mcp__flow-nexus__neural_deploy_template ({
template_id : "template_id" ,
custom_config : { epochs : 50 },
user_id : "user_id"
})
mcp__flow-nexus__neural_publish_template ({
model_id : "model_id" ,
name : "Sentiment Analyzer" ,
description : "LSTM-based sentiment analysis model" ,
category : "nlp" ,
price : 0 ,
user_id : "user_id"
})
mcp__flow-nexus__neural_rate_template ({
template_id : "template_id" ,
rating : 5 ,
review : "Excellent model, fast and accurate" ,
user_id : "user_id"
})
Model Management
mcp__flow-nexus__neural_list_models ({
user_id : "user_id" ,
include_public : false
})
mcp__flow-nexus__neural_training_status ({ job_id : "job_id" })
mcp__flow-nexus__neural_validation_workflow ({
model_id : "model_id" ,
validation_type : "comprehensive" ,
user_id : "user_id"
})
mcp__flow-nexus__neural_performance_benchmark ({
model_id : "model_id" ,
benchmark_type : "comprehensive"
})
Usage Examples
Example 1: Classification Model Training
const trainingJob = await mcp__flow-nexus__neural_train ({
config : {
architecture : {
type : "feedforward" ,
layers : [
{ type : "dense" , units : 256 , activation : "relu" },
{ type : "batch_norm" },
{ type : "dropout" , rate : 0.3 },
{ type : "dense" , units : 128 , activation : "relu" },
{ type : "dropout" , rate : 0.2 },
{ type : "dense" , units : 10 , activation : "softmax" }
]
},
training : {
epochs : 100 ,
batch_size : 64 ,
learning_rate : 0.001 ,
optimizer : "adam"
}
},
tier : "small"
});
const status = await mcp__flow-nexus__neural_training_status ({
job_id : trainingJob.job_id
});
console .log (`Epoch: ${status.current_epoch} , Loss: ${status.loss} ` );
const prediction = await mcp__flow-nexus__neural_predict ({
model_id : trainingJob.model_id ,
input : [[0.1 , 0.2 , 0.3 , 0.4 , 0.5 ]]
});
Example 2: Distributed Transformer Training
const cluster = await mcp__flow-nexus__neural_cluster_init ({
name : "transformer-cluster" ,
architecture : "transformer" ,
topology : "mesh" ,
consensus : "proof-of-learning" ,
daaEnabled : true ,
wasmOptimization : true
});
for (let i = 0 ; i < 4 ; i++) {
await mcp__flow-nexus__neural_node_deploy ({
cluster_id : cluster.cluster_id ,
node_type : "worker" ,
model : "large" ,
capabilities : ["training" , "inference" ]
});
}
await mcp__flow-nexus__neural_node_deploy ({
cluster_id : cluster.cluster_id ,
node_type : "parameter_server" ,
model : "base"
});
await mcp__flow-nexus__neural_cluster_connect ({
cluster_id : cluster.cluster_id
});
await mcp__flow-nexus__neural_train_distributed ({
cluster_id : cluster.cluster_id ,
dataset : "large_nlp_dataset" ,
epochs : 50 ,
batch_size : 128 ,
learning_rate : 0.0001 ,
optimizer : "adam"
});
const clusterStatus = await mcp__flow-nexus__neural_cluster_status ({
cluster_id : cluster.cluster_id
});
await mcp__flow-nexus__neural_cluster_terminate ({
cluster_id : cluster.cluster_id
});
Example 3: Using Pre-built Templates
const templates = await mcp__flow-nexus__neural_list_templates ({
category : "nlp" ,
tier : "free" ,
search : "sentiment"
});
const deployment = await mcp__flow-nexus__neural_deploy_template ({
template_id : templates.templates [0 ].id ,
custom_config : {
epochs : 25 ,
learning_rate : 0.0005
}
});
await mcp__flow-nexus__neural_validation_workflow ({
model_id : deployment.model_id ,
validation_type : "comprehensive"
});
const benchmark = await mcp__flow-nexus__neural_performance_benchmark ({
model_id : deployment.model_id ,
benchmark_type : "comprehensive"
});
console .log (`Inference latency: ${benchmark.inference_latency_ms} ms` );
Execution Checklist
Best Practices
Start Small : Begin with nano or mini tier for testing, scale up for productionProper Validation : Always run validation workflow before production deploymentHyperparameter Tuning : Use grid search or Bayesian optimization for best resultsDistributed Training : Use for large models; single-node for smaller experimentsCheckpoint Frequently : Enable checkpointing for long training runsMonitor Drift : Implement drift detection for production models
Error Handling Error Cause Solution training_failedInvalid architecture config Verify layer compatibility and types cluster_init_failedInvalid topology or architecture Check supported combinations insufficient_creditsTraining tier exceeds balance Reduce tier or add credits model_not_foundInvalid model_id Use neural_list_models to verify node_deploy_failedCluster capacity reached Terminate unused nodes
Metrics & Success Criteria
Training Convergence : Loss decreasing over epochsValidation Accuracy : Target >90% for classificationInference Latency : <100ms for productionMemory Efficiency : <80% resource utilizationModel Size : Appropriate for deployment target
Integration Points
With Swarms
await mcp__flow-nexus__agent_spawn ({
type : "analyst" ,
name : "ML Analyst" ,
capabilities : ["neural_training" , "model_evaluation" ]
});
With Workflows
await mcp__flow-nexus__workflow_create ({
name : "ML Training Pipeline" ,
steps : [
{ id : "preprocess" , action : "data_prep" },
{ id : "train" , action : "neural_train" , depends : ["preprocess" ] },
{ id : "validate" , action : "neural_validate" , depends : ["train" ] },
{ id : "deploy" , action : "neural_deploy" , depends : ["validate" ] }
]
});
Related Skills
References
Version History
1.0.0 (2026-01-02): Initial release - converted from flow-nexus-neural agent 