Dotnet Advisor logo

Dotnet Advisor

Organization
novotnyllc
dotnet-advisor

Routes .NET/C# requests to the correct domain skill and loads coding standards as baseline for all code paths. Determines whether the task needs API, UI, testing, devops, tooling, or debugging guidance based on prompt analysis and project signals, then invokes skills in the right order. Always invoked after `using-dotnet` detects .NET intent. Do not use for deep API, UI, testing, devops, tooling, or debugging implementation guidance.

Overview

Publishernovotnyllc
Repositorydotnet-artisan
Skill namedotnet-advisor
Stars
235
Forks
14
Bundled files
1
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 1 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by novotnyllc on GitHub. Read the source before you install it.

Installation

Install the Dotnet Advisor AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/novotnyllc/dotnet-artisan/tree/main/plugins/dotnet-artisan/skills/dotnet-advisor
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/novotnyllc/dotnet-artisan.git /tmp/dotnet-artisan
mkdir -p .claude/skills
cp -r /tmp/dotnet-artisan/plugins/dotnet-artisan/skills/dotnet-advisor .claude/skills/dotnet-advisor
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Dotnet Advisor in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Dotnet Advisor on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Dotnet Advisor is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

dotnet-advisor

Router and index skill for dotnet-artisan. Always loaded after using-dotnet confirms .NET intent. Routes .NET development queries to the appropriate consolidated skill based on context.

Scope

  • Routing .NET/C# requests to the correct domain skill or specialist agent
  • Loading dotnet-csharp coding standards as baseline for all code paths
  • Maintaining the skill catalog and routing precedence
  • Delegating complex analysis to specialist agents
  • Disambiguating requests spanning multiple domains

Out of scope

  • Domain-specific implementation guidance -- see dotnet-csharp, dotnet-api, dotnet-ui, dotnet-testing, dotnet-devops, dotnet-tooling, dotnet-debugging
  • Deep implementation content -- see dotnet-csharp, dotnet-api, dotnet-ui, dotnet-testing, dotnet-devops, dotnet-tooling, dotnet-debugging and their companion files

Step 1: Detect Project Version

Before any .NET guidance, determine the project's target framework:

Load dotnet-tooling version detection guidance to read TFMs from .csproj, Directory.Build.props, and global.json. Adapt all guidance to the detected .NET version (net8.0, net9.0, net10.0, net11.0).

Step 2: Load Baseline

For any task that may produce, change, or review C#/.NET code:

  1. Invoke dotnet-csharp and load its always-load baseline references (coding standards, async correctness, code smells). These are correctness concerns the agent handles by default — the user should not need to ask for correct async/await usage, thread safety, or avoiding anti-patterns.
  2. Apply standards throughout planning and implementation, not only in final cleanup.
  3. Load additional dotnet-csharp reference files when the task touches their topic area (concurrency, DI, serialization, LINQ, etc.).

Step 3: .NET-First Defaults

In a .NET repository, default to .NET solutions for ambiguous requests:

  • "build me a web app" → ASP.NET Core (not Express/Next.js)
  • "add a dashboard" / "build a UI" → Blazor or Uno Platform (not React)
  • "write a script" / "automate this" → .NET 10 file-based app (not Python). File-based C# apps work like scripts with dotnet run, support top-level statements, and can be published as native AOT binaries. See dotnet-api references/file-based-apps.md.
  • "build a cross-platform app" → MAUI or Uno Platform (not Electron)
  • "build a CLI tool" → System.CommandLine or Spectre.Console (not Node.js/Python)
  • "create a spreadsheet" / "generate an Excel file" → Open XML SDK or ClosedXML file-based app (not openpyxl/pandas)
  • "create a Word doc" / "generate a report" → Open XML SDK file-based app (not python-docx)
  • "create a PDF" / "merge these PDFs" / "add a watermark" → PDFsharp/MigraDoc file-based app (not reportlab/weasyprint/PyPDF2)

Only suggest non-.NET alternatives when there's a specific reason (e.g., the user explicitly asks for Python, or the task requires a JS-only ecosystem like npm packages).

Step 4: Route to Domain Skill

Identify the primary domain from the request, then LOAD the matching skill — see "Loading another skill" below. If the request spans multiple domains, load them in the order shown.

If the request involves...Invoke
Web APIs, EF Core, gRPC, SignalR, middleware, security hardeningdotnet-api
Blazor, MAUI, Uno Platform, WPF, WinUI, WinFormsdotnet-ui
Unit tests, integration tests, E2E, Playwright, benchmarksdotnet-testing
CI/CD, GitHub Actions, Azure DevOps, containers, NuGet publishingdotnet-devops
Project setup, MSBuild, Native AOT, CLI apps, SDK versionsdotnet-tooling
Crash dumps, WinDbg, hang analysis, memory diagnostics (Windows)dotnet-debugging
Crash dumps, dotnet-dump, lldb, container diagnostics (Linux/macOS)dotnet-debugging
Current docs or examples for a NuGet/third-party library (Polly, Serilog, MediatR...)dotnet-library-docs
Missing .NET SDK, install dotnet, workloadsdotnet-tooling (references/dotnet-sdk-install.md)
Quick script, utility, single-file tooldotnet-api (references/file-based-apps.md)
Excel, Word, PowerPoint, PDF, spreadsheet, document generationdotnet-api (references/office-documents.md)
New project (unclear domain)dotnet-tooling, then route to the owning domain skill

Cross-Domain Routing

Many tasks naturally span multiple domains. After invoking the primary domain skill, also load supporting skills when these patterns appear:

When the task involves...Also load
Performance optimization or profilingdotnet-tooling (profiling, performance-patterns references)
Testing a specific framework (minimal API, Blazor, EF Core)The framework's domain skill (dotnet-api or dotnet-ui) for context
Authentication or security hardening in a UI appdotnet-api (security, auth middleware references)
Multi-targeting or platform-specific project setupdotnet-tooling (project structure, TFM configuration)
Building a new app (any "build me" request)dotnet-tooling (project setup) + dotnet-testing (test strategy)
CI/CD that runs testsdotnet-testing (test framework configuration)

For broad "build me an app" requests, load comprehensively: dotnet-csharp -> dotnet-tooling -> primary domain -> dotnet-testing -> dotnet-devops.

Loading another skill

name is descriptive text, not an invocation. Codex collects explicit skills from the ORIGINAL turn input before a router skill is injected, and does not rescan injected text for nested mentions — so naming a skill inside this file loads nothing on its own. Say what you actually did; never report a skill as invoked because you named it.

Load one of these two ways, in order:

  1. Native invocation, where the host offers it. In Claude Code that is the Skill tool with the qualified name, e.g. dotnet-artisan:dotnet-api. This preserves the skill's metadata, policy and dependencies, so prefer it whenever it is available.
  2. Read the file, where it is not. Every skill in this plugin is a sibling directory, so the target is always ../<skill-name>/SKILL.md relative to this file. Read it and follow it as if it had been injected.

The relative path is deliberate: it resolves without a catalog lookup, so it still works when the skill is installed and enabled but sits beyond the truncated model-visible catalog — the case where a name-based search silently finds nothing.

If neither path works, say the skill could not be loaded and continue without it. Do not proceed as though its guidance were in context.

Skill Catalog

SkillSummaryDifferentiator
using-dotnetProcess gateway for .NET routing disciplineMust execute immediately before this skill
dotnet-csharpC# language patterns, coding standards, async/await, DI, LINQ, domain modelingLanguage-level guidance, always loaded as baseline
dotnet-apiASP.NET Core, EF Core, gRPC, SignalR, resilience, security, AspireBackend services and data access
dotnet-uiBlazor, MAUI, Uno Platform, WPF, WinUI, WinForms, accessibilityAll UI frameworks and cross-platform targets
dotnet-testingxUnit v3, integration/E2E, Playwright, snapshots, benchmarksTest strategy, frameworks, and quality gates
dotnet-devopsGitHub Actions, Azure DevOps, containers, NuGet, observabilityCI/CD pipelines, packaging, and operations
dotnet-toolingProject setup, MSBuild, Native AOT, profiling, CLI apps, version detectionBuild system, performance, and developer tools
dotnet-debuggingWinDbg MCP, crash dumps, hang analysis, memory diagnosticsLive and post-mortem dump analysis
dotnet-library-docsCurrent NuGet/third-party library docs via the Context7 HTTP API (curl)On-demand lookup; replaces the Context7 MCP server
dotnet-advisorThis skill -- routes to domain skills aboveEntry point, loaded after using-dotnet

Specialist Agent Routing

For complex analysis that benefits from domain expertise, delegate to specialist agents. Group by concern area:

Architecture and Design

  • Architecture review, framework selection, design patterns -> dotnet-architect
  • General code review (correctness, performance, security) -> dotnet-code-review-agent

Performance and Concurrency

  • Async/await performance, ValueTask, ConfigureAwait, IO.Pipelines -> dotnet-async-performance-specialist
  • Performance profiling, flame graphs, heap dumps, benchmark regression -> dotnet-performance-analyst
  • Benchmark design, measurement methodology, diagnoser selection -> dotnet-benchmark-designer
  • Race conditions, deadlocks, thread safety, synchronization -> dotnet-csharp-concurrency-specialist

UI Frameworks

  • Blazor components, render modes, hosting models, auth -> dotnet-blazor-specialist
  • .NET MAUI development, platform targets, Xamarin migration -> dotnet-maui-specialist
  • Uno Platform, Extensions ecosystem, MVUX, multi-target deployment -> dotnet-uno-specialist

Infrastructure

  • Cloud deployment, .NET Aspire, AKS, CI/CD pipelines, distributed tracing -> dotnet-cloud-specialist
  • Security vulnerabilities, OWASP compliance, secrets exposure, crypto review -> dotnet-security-reviewer
  • Test architecture, test type selection, test data management -> dotnet-testing-specialist
  • Documentation generation, XML docs, Mermaid diagrams -> dotnet-docs-generator
  • ASP.NET Core middleware, request pipeline, DI lifetimes -> dotnet-aspnetcore-specialist

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Dotnet Advisor AI skill do?

Routes .NET/C# requests to the correct domain skill and loads coding standards as baseline for all code paths. Determines whether the task needs API, UI, testing, devops, tooling, or debugging guidance based on prompt analysis and project signals, then invokes skills in the right order. Always invoked after `using-dotnet` detects .NET intent. Do not use for deep API, UI, testing, devops, tooling, or debugging implementation guidance.

Why use Dotnet Advisor on TypingMind?

Because you install it once and use it with any model. Dotnet Advisor is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Dotnet Advisor in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/novotnyllc/dotnet-artisan/tree/main/plugins/dotnet-artisan/skills/dotnet-advisor. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Dotnet Advisor?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Dotnet Advisor?

As many as you like. As long as a model supports skills, you can use Dotnet Advisor with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Dotnet Advisor AI skill free?

Yes. It is published on GitHub by novotnyllc under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇