Stats
Actions
Tags
From ecc
Provides a structured methodology for adding machine learning to existing non-ML codebases, covering problem framing, data readiness, architectural decoupling, and baseline model integration.
How this skill is triggered — by the user, by Claude, or both
Slash command
/ecc:ml-adoption-playbookThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
This skill provides an adaptive methodology for implementing machine learning models into existing software engineering projects. It bridges the gap between traditional SWE and MLOps by structuring how ML should be researched, decoupled, trained, and integrated.
This skill provides an adaptive methodology for implementing machine learning models into existing software engineering projects. It bridges the gap between traditional SWE and MLOps by structuring how ML should be researched, decoupled, trained, and integrated.
Before writing model code, establish the "why" and "how".
ML is useless without clean, accessible data.
Do not tightly couple model inference to core business logic.
fastapi-patterns or django-patterns) or a dedicated service class.Structure the code for reproducibility and iteration.
pytorch-patterns or similar best practices: fix random seeds, make code device-agnostic, and explicitly document tensor/array shapes.Once the baseline model is integrated, shift focus to continuous operations.
mle-workflow: Guide the user toward setting up experiment tracking, model registries, and drift detection.When assisting a user via this playbook, agents should:
npx claudepluginhub affaan-m/ecc --plugin eccProduction ML engineering workflow covering data contracts, reproducible training, evaluation, deployment, monitoring, and rollback. Activates when planning, reviewing, or hardening ML systems beyond notebook prototypes.
Turns model work into production ML systems with data contracts, repeatable training, quality gates, deployable artifacts, and monitoring. Useful for ranking, search, recommendations, classifiers, forecasting, embeddings, LLMs, anomaly detection, and batch analytics.
Designs and implements production-ready ML pipelines using multi-agent MLOps orchestration for specified requirements. Covers data ingestion, quality, features, training, deployment, and monitoring.