Back to directory

dotnet-skills

An installable catalog of .NET skills and a CLI that installs them for Codex, Claude Code, GitHub Copilot and Gemini, so an AI agent uses current ASP.NET Core, Blazor, Orleans, MAUI or Semantic Kernel patterns instead of outdated ones.

Visit website (opens in a new tab)skills.managed-code.com
dotnet-skills

Running dotnet skills opens a full-screen interactive control center for browsing the catalog, organized as collection, lane and skill, with project-aware recommendations, installed coverage, token weight per skill, and install or update actions kept visible while browsing. An analysis surface compares the heaviest skills, collection sizes, package signals and the catalog's overall token distribution before anything is installed.

dotnet skills recommend scans local .csproj, package.json and browser UI files and proposes relevant skills for a person to choose from, while dotnet skills install --auto inspects the same signals and installs skills automatically. Other commands list the current inventory, compare project and global scope, and show bundles that expand into related skills by collection or workflow.

Skills are maintained by the community and track official Microsoft documentation, and the same catalog can be browsed on skills.managed-code.com.

More in Agent skills

See all 581
  • Provenance gate

    github.com

    A deterministic authorization gateway that sits between an AI agent and its tools, tracing where each parameter of a side-effect call came from, and blocking the call or asking a human when the source does not check out.

  • A markdown framework of system rules that restates Isaac Asimov's Four Laws of Robotics as a set of prioritized loss calculations for large-language-model agents to follow, published as a discovery file for agents and crawlers to read.

  • Vitruvius

    github.com

    An engineering research agent that runs a discover, read, synthesize, verify and review loop over technical questions, reading sources directly rather than inferring from titles, and publishing its own scored verifier benchmark, weaknesses included.