Model Deployment

Covers the full production deployment stack for ML models: FastAPI server setup, Docker containerization, Kubernetes orchestration, and monitoring. The real value is in the troubleshooting section, which walks through eight common failure modes like missing health checks causing 503s, OOM kills from missing resource limits, and silent model drift. Includes a practical six-step quickstart and a deployment checklist. If you're moving models from notebooks to production and keep hitting the same infrastructure problems, this gives you working patterns for API endpoints, batch processing, rollback procedures, and CI/CD validation. Less about the ML theory, more about keeping services up and catching issues before users do.

skills.sh installs: 393
GitHub stars: 248
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add secondsky/claude-skills --skill model-deployment --agent claude-code

Installs into .claude/skills of the current project.

Files

ML Model Deployment

Deploy trained models to production with proper serving and monitoring.

Deployment Options

Method	Use Case	Latency
REST API	Web services	Medium
Batch	Large-scale processing	N/A
Streaming	Real-time	Low
Edge	On-device	Very low

FastAPI Model Server

from fastapi import FastAPI
from pydantic import BaseModel
import joblib
import numpy as np

app = FastAPI()
model = joblib.load('model.pkl')

class PredictionRequest(BaseModel):
    features: list[float]

class PredictionResponse(BaseModel):
    prediction: float
    probability: float

@app.get('/health')
def health():
    return {'status': 'healthy'}

@app.post('/predict', response_model=PredictionResponse)
def predict(request: PredictionRequest):
    features = np.array(request.features).reshape(1, -1)
    prediction = model.predict(features)[0]
    probability = model.predict_proba(features)[0].max()
    return PredictionResponse(prediction=prediction, probability=probability)