mcaf-ml-ai-delivery
The mcaf-ml-ai-delivery skill applies structured guidance for machine learning and AI projects across data exploration, experimentation, training, inference, and operational stages. Use this skill when a repository contains model training, data-science workflows, or inference components that require explicit process guidance, testing strategies, or responsible-AI considerations integrated throughout delivery rather than as afterthoughts.
git clone --depth 1 https://github.com/managedcode/dotnet-skills /tmp/mcaf-ml-ai-delivery && cp -r /tmp/mcaf-ml-ai-delivery/catalog/Platform/MCAF/skills/mcaf-ml-ai-delivery ~/.claude/skills/mcaf-ml-ai-deliverySKILL.md
# MCAF: ML/AI Delivery ## Trigger On - the repo contains model training, inference, experimentation, or data-science workflow - ML work needs explicit process, testing, or responsible-AI guidance - delivery discussion is mixing product, data, and model concerns ## Value - produce a concrete project delta: code, docs, config, tests, CI, or review artifact - reduce ambiguity through explicit planning, verification, and final validation skills - leave reusable project context so future tasks are faster and safer ## Do Not Use For - generic software delivery with no ML or data-science component - loading all ML references when only one stage is active ## Inputs - the current ML stage: framing, data exploration, experimentation, training, inference, or operations - product assumptions, data assumptions, and model assumptions - current verification and responsible-AI expectations ## Quick Start 1. Read the nearest `AGENTS.md` and confirm scope and constraints. 2. Run this skill's `Workflow` through the `Ralph Loop` until outcomes are acceptable. 3. Return the `Required Result Format` with concrete artifacts and verification evidence. ## Workflow 1. Separate product assumptions, data assumptions, and model assumptions. 2. Keep experimentation traceable and testable. 3. Treat responsible AI, data quality, and ML-specific verification as first-class requirements. 4. Load only the references that match the current ML stage. ## Deliver - clearer ML/AI delivery guidance - better links between data, experimentation, verification, and responsible AI - docs that match how the ML system is built and validated ## Validate - the active ML stage is explicit - experimentation and evaluation are traceable - responsible-AI and data-quality requirements are not bolted on at the end ## Ralph Loop Use the Ralph Loop for every task, including docs, architecture, testing, and tooling work. 1. Brainstorm first (mandatory): - analyze current state - define the problem, target outcome, constraints, and risks - generate options and think through trade-offs before committing - capture the recommended direction and open questions 2. Plan second (mandatory): - write a detailed execution plan from the chosen direction - list final validation skills to run at the end, with order and reason 3. Execute one planned step and produce a concrete delta. 4. Review the result and capture findings with actionable next fixes. 5. Apply fixes in small batches and rerun the relevant checks or review steps. 6. Update the plan after each iteration. 7. Repeat until outcomes are acceptable or only explicit exceptions remain. 8. If a dependency is missing, bootstrap it or return `status: not_applicable` with explicit reason and fallback path. ### Required Result Format - `status`: `complete` | `clean` | `improved` | `configured` | `not_applicable` | `blocked` - `plan`: concise plan and current iteration step - `actions_taken`: concrete changes made - `validation_skills`: final skills run, or skipped with reasons - `verification`: commands, checks, or review evidence summary - `remaining`: top unresolved items or `none` For setup-only requests with no execution, return `status: configured` and exact next commands. ## Load References - read [references/ml-ai-projects.md](references/ml-ai-projects.md) first - open [references/data-exploration.md](references/data-exploration.md), [references/feasibility-studies.md](references/feasibility-studies.md), [references/ml-fundamentals-checklist.md](references/ml-fundamentals-checklist.md), [references/model-experimentation.md](references/model-experimentation.md), [references/testing-data-science-and-mlops-code.md](references/testing-data-science-and-mlops-code.md), [references/responsible-ai.md](references/responsible-ai.md), or [references/ml-model-checklist.md](references/ml-model-checklist.md) only when that stage is active ## Example Requests - "Define the delivery workflow for this ML feature." - "We need responsible-AI and testing guidance for this model." - "Separate product, data, and model decisions in our docs."
Build, debug, modernize, or review ASP.NET Core applications with correct hosting, middleware, security, configuration, logging, and deployment patterns on current .NET. USE FOR: working on ASP.NET Core apps, services, or middleware; changing auth, routing, configuration, hosting, or deployment behavior; deciding between ASP.NET Core sub-stacks. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Build, upgrade, and operate .NET Aspire 13.3.x application hosts with current CLI, AppHost, ServiceDefaults, integrations, dashboard, testing, and Azure deployment patterns for distributed apps. USE FOR: Aspire.AppHost.Sdk, Aspire.Hosting.*, DistributedApplication.CreateBuilder, WithReference, WaitFor, AddProject, AddRedis, AddPostgres, aspire run, aspire init, aspire. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Build, review, or migrate Azure Functions in .NET with correct execution model, isolated worker setup, bindings, DI, and Durable Functions patterns. USE FOR: working on Azure Functions in .NET; migrating from the in-process model to the isolated worker model; adding Durable Functions, bindings, or host configuration. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Build and review Blazor applications across server, WebAssembly, web app, and hybrid scenarios with correct component design, state flow, rendering, and hosting choices. USE FOR: building interactive web UIs with C# instead of JavaScript; choosing between Server, WebAssembly, or Auto render modes; designing component hierarchies and state. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Maintain or migrate EF6-based applications with realistic guidance on what to keep, what to modernize, and when EF Core is or is not the right next step. USE FOR: EF6 codebases; runtime versus ORM migration decisions; EDMX, code-first, ObjectContext, and legacy data-access review. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Design, tune, or review EF Core data access with proper modeling, migrations, query translation, performance, and lifetime management for modern .NET applications. USE FOR: DbContext, migrations, model configuration, EF queries, tracking, loading, performance, transactions, and EF6 migration decisions. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Build, review, or migrate .NET MAUI applications across Android, iOS, macOS, and Windows with correct cross-platform UI, platform integration, and native packaging assumptions. USE FOR: working on cross-platform mobile or desktop UI in .NET MAUI; integrating device capabilities, navigation, or platform-specific code; migrating Xamarin.Forms or aligning. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.
Use ML.NET to train, evaluate, or integrate machine-learning models into .NET applications with realistic data preparation, inference, and deployment expectations. USE FOR: ML.NET integration; local model training or retraining; inference pipelines, model loading, evaluation, and deployment review. DO NOT USE FOR: unrelated stacks; generic tasks that do not need this specific guidance. INVOKES: inspect the repository context, edit targeted files, and run relevant build, test, lint, or validation commands when changes are made.