a5c-ai/babysitter / library/specializations/data-science-ml/skills/bentoml-model-packager
bentoml-model-packager
VerifiedBentoML skill for model packaging, serving, and containerization.
bentoml-model-packager
Overview
BentoML skill for model packaging, serving, and containerization with support for multiple ML frameworks.
Capabilities
- Bento creation and versioning
- Multi-framework model support (sklearn, PyTorch, TensorFlow, etc.)
- API endpoint definition with validation
- Docker containerization
- Kubernetes deployment YAML generation
- Adaptive batching configuration
- Model signatures and runners
- Service composition
Target Processes
- Model Deployment Pipeline with Canary Release
- Model Training Pipeline
- ML System Integration Testing
Tools and Libraries
- BentoML
- Docker
- Kubernetes
Input Schema
{
"type": "object",
"required": ["action"],
"properties": {
"action": {
"type": "string",
"enum": ["save", "build", "serve", "containerize", "push", "list"],
"description": "BentoML action to perform"
},
"modelConfig": {
"type": "object",
"properties": {
"name": { "type": "string" },
"framework": { "type": "string" },
"modelPath": { "type": "string" },
"signatures": { "type": "object" }
}
},
"serviceConfig": {
"type": "object",
"properties": {
"servicePath": { "type": "string" },
"port": { "type": "integer" },
"workers": { "type": "integer" },
"batchConfig": {
"type": "object",
"properties": {
"maxBatchSize": { "type": "integer" },
"maxLatencyMs": { "type": "integer" }
}
}
}
},
"buildConfig": {
"type": "object",
"properties": {
"bentoName": { "type": "string" },
"version": { "type": "string" },
"includeFiles": { "type": "array", "items": { "type": "string" } },
"pythonRequirements": { "type": "string" }
}
},
"containerConfig": {
"type": "object",
"properties": {
"imageName": { "type": "string" },
"registry": { "type": "string" },
"dockerOptions": { "type": "object" }
}
}
}
}
Output Schema
{
"type": "object",
"required": ["status", "action"],
"properties": {
"status": {
"type": "string",
"enum": ["success", "error"]
},
"action": {
"type": "string"
},
"modelTag": {
"type": "string"
},
"bentoTag": {
"type": "string"
},
"imageTag": {
"type": "string"
},
"endpoint": {
"type": "string"
},
"kubernetesYaml": {
"type": "string"
}
}
}
Usage Example
{
kind: 'skill',
title: 'Package and containerize model',
skill: {
name: 'bentoml-model-packager',
context: {
action: 'containerize',
modelConfig: {
name: 'fraud_classifier',
framework: 'sklearn',
modelPath: 'models/fraud_model.pkl'
},
buildConfig: {
bentoName: 'fraud-service',
version: '1.0.0',
pythonRequirements: 'requirements.txt'
},
containerConfig: {
imageName: 'fraud-service',
registry: 'gcr.io/my-project'
}
}
}
}
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis. | Stars: 470k | Updated | Claude CodeCodex | Verified | Install |
| diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness. | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |