technology-selection

Name: technology-selection
Author: managedcode

461stars35forks

How to install technology-selection?

managedcode/dotnet-skills/technology-selection

$npx -y skills add managedcode/dotnet-skills --skill technology-selection

Installs into the current project.

Summary

Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework (MAF), GitHub Copilot SDK, ONNX Runtime, and OllamaSharp. Covers the full spectrum from classic ML through modern L

Files · 1

View on GitHub

SKILL.md

1	# .NET AI and Machine Learning
2
3	## Inputs
4
5	\| Input \| Required \| Description \|
6	\|-------\|----------\|-------------\|
7	\| Task description \| Yes \| What the AI/ML feature should accomplish (e.g., "classify support tickets", "summarize documents") \|
8	\| Data description \| Yes \| Type and shape of input data (structured/tabular, unstructured text, images, mixed) \|
9	\| Deployment constraints \| No \| Cloud vs. local, latency SLO, cost budget, offline requirements \|
10	\| Existing project context \| No \| Current .csproj, existing packages, target framework \|
11
12	## Workflow
13
14	### Step 1: Classify the task using the decision tree
15
16	Evaluate the developer's task against this decision tree and select the appropriate technology. State which branch applies and why.
17
18	\| Task type \| Technology \| Rationale \|
19	\|-----------\|-----------\|-----------\|
20	\| Structured/tabular data: classification, regression, clustering, anomaly detection, recommendation \| ML.NET (`Microsoft.ML`) \| Reproducible (given a fixed seed and dataset), no cloud dependency, purpose-built models for these tasks \|
21	\| Natural language understanding, generation, summarization, reasoning over unstructured text (single prompt → response, no tool calling) \| LLM via Microsoft.Extensions.AI (`IChatClient`) \| Requires language model capabilities beyond pattern matching; no orchestration needed \|
22	\| Agentic workflows: tool/function calling, multi-step reasoning, agent loops, multi-agent collaboration \| Microsoft Agent Framework (`Microsoft.Agents.AI`) built on top of Microsoft.Extensions.AI \| Requires orchestration, tool dispatch, iteration control, and guardrails that `IChatClient` alone does not provide \|
23	\| Building GitHub Copilot extensions, custom agents, or developer workflow tools \| GitHub Copilot SDK (`GitHub.Copilot.SDK`) \| Integrates with the Copilot agent runtime for IDE and CLI extensibility \|
24	\| Running a pre-trained or fine-tuned custom model in production \| ONNX Runtime (`Microsoft.ML.OnnxRuntime`) \| Hardware-accelerated inference, model-format agnostic \|
25	\| Local/offline LLM inference with no cloud dependency \| OllamaSharp with local [AI models supported by Ollama](https://ollama.com/search) \| Privacy-sensitive, air-gapped, or cost-constrained scenarios \|
26	\| Semantic search, RAG, or embedding storage \| Microsoft.Extensions.VectorData.Abstractions + a vector database provider (e.g., Azure AI Search, Milvus, MongoDB, pgvector, Pinecone, Qdrant, Redis, SQL) \| Provider-agnostic abstractions for vector similarity search; pair with a database-specific connector package (many are moving to community toolkits) \|
27	\| Ingesting, chunking, and loading documents into a vector store \| Microsoft.Extensions.AI.DataIngestion (preview) + Microsoft.Extensions.VectorData.Abstractions (MEVD) \| Handles document parsing, text chunking, embedding generation, and upserting into a vector database; pairs with Microsoft.Extensions.VectorData.Abstractions \|
28	\| Both structured ML predictions AND natural language reasoning \| Hybrid: ML.NET for predictions + LLM for reasoning layer \| Keep loosely coupled; ML.NET handles reproducible scoring, LLM adds explanation \|
29
30	Critical rule: Do NOT use an LLM for tasks that ML.NET handles well (classification on tabular data, regression, clustering). LLMs are slower, more expensive, and non-deterministic for these tasks.
31
32	### Step 1b: Select the correct library layer
33
34	After identifying the task type, select the right library layer. These libraries form a stack — each builds on the one below it. Using the wrong layer is a major source of non-deterministic agent behavior.
35
36	\| Layer \| Library \| NuGet package \| Use when \|
37	\|-------\|---------\|---------------\|----------\|
38	\| Abstraction \| Microsoft.Extensions.AI (MEAI) \| `Microsoft.Extensions.AI` \| You need a provider-agnostic interface for chat, embeddings, or tool calling. This is the foundation — always include it. Use `IChatClient` directly only for simple prompt-in/response-out scenarios with no tool calling or agentic loops. If the task

People who liked this also viewed

6 picks

Type

technology-selection

461stars35forks

View on GitHub

How to install technology-selection?

managedcode/dotnet-skills/technology-selection

$npx -y skills add managedcode/dotnet-skills --skill technology-selection

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# .NET AI and Machine Learning
2
3	## Inputs
4
5	\| Input \| Required \| Description \|
6	\|-------\|----------\|-------------\|
7	\| Task description \| Yes \| What the AI/ML feature should accomplish (e.g., "classify support tickets", "summarize documents") \|
8	\| Data description \| Yes \| Type and shape of input data (structured/tabular, unstructured text, images, mixed) \|
9	\| Deployment constraints \| No \| Cloud vs. local, latency SLO, cost budget, offline requirements \|
10	\| Existing project context \| No \| Current .csproj, existing packages, target framework \|
11
12	## Workflow
13
14	### Step 1: Classify the task using the decision tree
15
16	Evaluate the developer's task against this decision tree and select the appropriate technology. State which branch applies and why.
17
18	\| Task type \| Technology \| Rationale \|
19	\|-----------\|-----------\|-----------\|
20	\| Structured/tabular data: classification, regression, clustering, anomaly detection, recommendation \| ML.NET (`Microsoft.ML`) \| Reproducible (given a fixed seed and dataset), no cloud dependency, purpose-built models for these tasks \|
21	\| Natural language understanding, generation, summarization, reasoning over unstructured text (single prompt → response, no tool calling) \| LLM via Microsoft.Extensions.AI (`IChatClient`) \| Requires language model capabilities beyond pattern matching; no orchestration needed \|
22	\| Agentic workflows: tool/function calling, multi-step reasoning, agent loops, multi-agent collaboration \| Microsoft Agent Framework (`Microsoft.Agents.AI`) built on top of Microsoft.Extensions.AI \| Requires orchestration, tool dispatch, iteration control, and guardrails that `IChatClient` alone does not provide \|
23	\| Building GitHub Copilot extensions, custom agents, or developer workflow tools \| GitHub Copilot SDK (`GitHub.Copilot.SDK`) \| Integrates with the Copilot agent runtime for IDE and CLI extensibility \|
24	\| Running a pre-trained or fine-tuned custom model in production \| ONNX Runtime (`Microsoft.ML.OnnxRuntime`) \| Hardware-accelerated inference, model-format agnostic \|
25	\| Local/offline LLM inference with no cloud dependency \| OllamaSharp with local [AI models supported by Ollama](https://ollama.com/search) \| Privacy-sensitive, air-gapped, or cost-constrained scenarios \|
26	\| Semantic search, RAG, or embedding storage \| Microsoft.Extensions.VectorData.Abstractions + a vector database provider (e.g., Azure AI Search, Milvus, MongoDB, pgvector, Pinecone, Qdrant, Redis, SQL) \| Provider-agnostic abstractions for vector similarity search; pair with a database-specific connector package (many are moving to community toolkits) \|
27	\| Ingesting, chunking, and loading documents into a vector store \| Microsoft.Extensions.AI.DataIngestion (preview) + Microsoft.Extensions.VectorData.Abstractions (MEVD) \| Handles document parsing, text chunking, embedding generation, and upserting into a vector database; pairs with Microsoft.Extensions.VectorData.Abstractions \|
28	\| Both structured ML predictions AND natural language reasoning \| Hybrid: ML.NET for predictions + LLM for reasoning layer \| Keep loosely coupled; ML.NET handles reproducible scoring, LLM adds explanation \|
29
30	Critical rule: Do NOT use an LLM for tasks that ML.NET handles well (classification on tabular data, regression, clustering). LLMs are slower, more expensive, and non-deterministic for these tasks.
31
32	### Step 1b: Select the correct library layer
33
34	After identifying the task type, select the right library layer. These libraries form a stack — each builds on the one below it. Using the wrong layer is a major source of non-deterministic agent behavior.
35
36	\| Layer \| Library \| NuGet package \| Use when \|
37	\|-------\|---------\|---------------\|----------\|
38	\| Abstraction \| Microsoft.Extensions.AI (MEAI) \| `Microsoft.Extensions.AI` \| You need a provider-agnostic interface for chat, embeddings, or tool calling. This is the foundation — always include it. Use `IChatClient` directly only for simple prompt-in/response-out scenarios with no tool calling or agentic loops. If the task

People who liked this also viewed

6 picks

Type