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-patterns or django-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-patterns or 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:
- Ask clarifying questions to complete Phase 1 before proposing architectures.
- Draft a data contract in Phase 2 for user approval.
- Write the decoupling interface (API/Service) in Phase 3 before writing the training loop.
- Deliver a reproducible script in Phase 4 that trains the model and saves the artifact.
1---2name: ml-adoption-playbook3description: End-to-end methodology for AI agents and software engineers to add machine learning algorithms to existing non-ML codebases. Covers problem framing, data readiness, architectural decoupling, and baseline model integration. Use when adding a machine learning capability to a codebase that has none, from problem framing through a baseline model.4---56# ML Adoption Playbook78This 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.910## When to Activate1112- A user asks to "add ML" or "add an algorithm" to their existing codebase.13- Planning the integration of a new model (e.g., recommendation, classification, forecasting) into a non-ML application.14- Structuring a workflow for an agent to build, train, and deploy an ML component adaptively.1516## Phase 1: Problem Framing & Feasibility1718Before writing model code, establish the "why" and "how".19- **Heuristic Check:** Ask the user if a simple heuristic (e.g., regex, rule-based sorting) could solve the problem faster. If yes, start there.20- **Metric Definition:** Define what business metric the ML model is trying to improve (e.g., click-through rate, reduced latency).21- **Mistake Budget:** Define what a "bad" prediction looks like and how the system should handle it.2223## Phase 2: Data Readiness2425ML is useless without clean, accessible data.26- **Audit Data Sources:** Identify where the training data lives. Is it a live database, a static CSV, or an API?27- **Data Contract:** Establish a schema for the input data. What features are required? What happens if a feature is missing?28- **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).2930## Phase 3: Architectural Integration & Decoupling3132Do not tightly couple model inference to core business logic.33- **API Boundary:** Suggest placing the model behind an API endpoint (e.g., using `fastapi-patterns` or `django-patterns`) or a dedicated service class.34- **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.35- **Feature Flags:** Wrap the new ML inference call in a feature flag so it can be rolled out (or rolled back) safely.3637## Phase 4: Model Implementation & Training3839Structure the code for reproducibility and iteration.40- **Start Simple:** Build a baseline model first (e.g., a simple scikit-learn Logistic Regression or a barebones PyTorch linear layer).41- **Reproducibility:** Apply `pytorch-patterns` or similar best practices: fix random seeds, make code device-agnostic, and explicitly document tensor/array shapes.42- **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.4344## Phase 5: Handoff to MLOps4546Once the baseline model is integrated, shift focus to continuous operations.47- **Refer to `mle-workflow`:** Guide the user toward setting up experiment tracking, model registries, and drift detection.48- **CI/CD:** Add the model evaluation step to the existing CI pipeline to ensure future commits do not degrade model performance.4950## Iterative Agent Workflow5152When assisting a user via this playbook, agents should:531. **Ask clarifying questions** to complete Phase 1 before proposing architectures.542. **Draft a data contract** in Phase 2 for user approval.553. **Write the decoupling interface** (API/Service) in Phase 3 *before* writing the training loop.564. **Deliver a reproducible script** in Phase 4 that trains the model and saves the artifact.
JunMystery