Ml Adoption Playbook
- 902 installs
- 238k repo stars
- Updated August 5, 2026
- affaan-m/everything-claude-code
ml-adoption-playbook is a Claude Code skill that provides a five-phase methodology for integrating a machine learning model into an existing non-ML codebase.
About
ml-adoption-playbook is a Claude Code skill giving an end-to-end methodology for adding machine learning to an existing non-ML codebase. It structures the work into five phases: problem framing and feasibility, data readiness and leakage prevention, architectural decoupling behind an API or service boundary, baseline model implementation and training, and handoff to MLOps. A developer uses it when asked to add a model such as recommendation, classification, or forecasting to a traditional software project without tightly coupling inference to core logic.
- Five-phase methodology for adding a machine learning model to an existing non-ML codebase
- Covers problem framing, data readiness and leakage prevention, architectural decoupling, and baseline model integration
- Pushes a heuristic-first check, an API/service boundary with fallbacks and feature flags, then handoff to MLOps
Ml Adoption Playbook by the numbers
- 902 all-time installs (skills.sh)
- Ranked #328 of 2,064 Data Science & ML skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
ml-adoption-playbook capabilities & compatibility
- Capabilities
- ml integration · data readiness · model decoupling · baseline modeling
- Use cases
- data analysis · api development · planning
What ml-adoption-playbook says it does
End-to-end methodology for AI agents and software engineers to add machine learning algorithms to existing non-ML codebases.
It bridges the gap between traditional SWE and MLOps by structuring how ML should be researched, decoupled, trained, and integrated.
npx skills add https://github.com/affaan-m/everything-claude-code --skill ml-adoption-playbookAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 902 |
|---|---|
| repo stars | ★ 238k |
| Last updated | August 5, 2026 |
| Repository | affaan-m/everything-claude-code ↗ |
What it does
Plan and integrate a baseline ML model into an existing non-ML codebase with decoupling, fallbacks, and reproducibility.
Who is it for?
Framing, decoupling, training, and integrating a baseline ML model into a traditional software project.
Skip if: Problems a simple heuristic (regex or rule-based sorting) could solve faster.
When should I use this skill?
A user asks to add ML or an algorithm to their existing codebase or to integrate a recommendation, classification, or forecasting model.
What you get
A phased plan with a data contract, a decoupled inference boundary with fallbacks and feature flags, and a reproducible baseline model.
- Data contract
- decoupled inference API/service with fallbacks
- reproducible baseline training script with evaluation
By the numbers
- 5-phase methodology
- Phase 4 starts with a baseline model before iteration
Files
ML Adoption Playbook
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.
When to Activate
- A user asks to "add ML" or "add an algorithm" to their existing codebase.
- Planning the integration of a new model (e.g., recommendation, classification, forecasting) into a non-ML application.
- Structuring a workflow for an agent to build, train, and deploy an ML component adaptively.
Phase 1: Problem Framing & Feasibility
Before writing model code, establish the "why" and "how".
- Heuristic Check: Ask the user if a simple heuristic (e.g., regex, rule-based sorting) could solve the problem faster. If yes, start there.
- Metric Definition: Define what business metric the ML model is trying to improve (e.g., click-through rate, reduced latency).
- Mistake Budget: Define what a "bad" prediction looks like and how the system should handle it.
Phase 2: Data Readiness
ML is useless without clean, accessible data.
- Audit Data Sources: Identify where the training data lives. Is it a live database, a static CSV, or an API?
- Data Contract: Establish a schema for the input data. What features are required? What happens if a feature is missing?
- Leakage Prevention: Ensure the user's proposed data split does not accidentally leak future information into the training set (e.g., chronological splitting for time-series data).
Phase 3: Architectural Integration & Decoupling
Do not tightly couple model inference to core business logic.
- API Boundary: Suggest placing the model behind an API endpoint (e.g., using
fastapi-patternsordjango-patterns) or a dedicated service class. - Fallback Mechanisms: Design a default state. If the model takes too long to respond or throws an error, the system must gracefully fall back to a hardcoded rule.
- Feature Flags: Wrap the new ML inference call in a feature flag so it can be rolled out (or rolled back) safely.
Phase 4: Model Implementation & Training
Structure the code for reproducibility and iteration.
- Start Simple: Build a baseline model first (e.g., a simple scikit-learn Logistic Regression or a barebones PyTorch linear layer).
- Reproducibility: Apply
pytorch-patternsor similar best practices: fix random seeds, make code device-agnostic, and explicitly document tensor/array shapes. - Automated Evidence: Require tests for the data transforms and inference schema. Do not accept a model without an evaluation script comparing it against the baseline.
Phase 5: Handoff to MLOps
Once the baseline model is integrated, shift focus to continuous operations.
- Refer to `mle-workflow`: Guide the user toward setting up experiment tracking, model registries, and drift detection.
- CI/CD: Add the model evaluation step to the existing CI pipeline to ensure future commits do not degrade model performance.
Iterative Agent Workflow
When assisting a user via this playbook, agents should: 1. Ask clarifying questions to complete Phase 1 before proposing architectures. 2. Draft a data contract in Phase 2 for user approval. 3. Write the decoupling interface (API/Service) in Phase 3 before writing the training loop. 4. Deliver a reproducible script in Phase 4 that trains the model and saves the artifact.
Related skills
Microsoft FoundryDeploy, evaluate, and continuously improve Microsoft Foundry agents from a single agent interface.490k1.3k
Ai Research ReproductionOrchestrate trustworthy, auditable reproduction of deep learning repositories directly from their READMEs.176k511Run TrainSafely execute selected deep learning training commands with standardized evidence capture.176k511Explore RunSafely run isolated exploratory experiments with clear recording and conservative selection before committing changes.176k511Paper Context ResolverFetch precise reproduction-critical details like dataset splits, preprocessing steps, or evaluation protocols from the original academic paper when the repo README leav141k511Repo Intake And PlanScan unfamiliar AI research repositories and receive a minimal, trustworthy reproduction target before investing significant time.140k511FAQ
Should I always use ML?
No. It starts with a heuristic check: if a simple regex or rule-based solution works faster, start there.
How should inference be integrated?
Behind an API endpoint or service class with a hardcoded-rule fallback and a feature flag for safe rollout and rollback.