OpenViSTAI · Agents · Blockchain · Crypto
Menu
Agent Frameworks

Agent Skills

Agent Skills is a public repository of reusable skills, custom agents, AGENTS.md templates and MCP configurations for AI coding agents working with Azure SDKs and Microsoft AI Foundry.

Independent OpenViST project profile, based on linked sources.

Agent Skills — OpenViST project profile in Agent Frameworks.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use Agent Skills when a coding agent needs targeted Azure SDK or Microsoft AI Foundry context, or when configuring reusable agent materials for a project.

Who it is for

  • Developers using coding agents on Azure SDK or Microsoft AI Foundry projects.
  • Teams configuring agent behavior or sharing selected skills across projects and agent setups.
  • Developers creating MCP servers or Copilot SDK applications who want relevant guidance materials.

Documented uses

  • Give a coding agent focused domain context for an SDK-related task.
  • Install selected skills into an agent's configuration directory.
  • Share skill directories across projects or agent configurations using symlinks.
  • Consult role-specific custom agents, MCP configurations and an AGENTS.md template.
Before you choose

Requirements & limits

The repository is public and identifies its license as MIT.

  • The collection is organized across Core, Foundry, Python, .NET, TypeScript, Java and Rust areas.
  • The README recommends loading only skills relevant to the current project to avoid diluted or conflated context.
  • The repository describes itself as work in progress, with skills and tests being updated.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Add selected skills with the skills installer

Choose repository skills and place them in a coding agent's configuration directory.

Before you start

  • A project using a coding agent
  • The skills installer available through npx

Steps

  1. Run the command below.

    Documented command
    npx skills add microsoft/skills
  2. Select the skills needed for the project in the wizard.

  3. Use the installed skills from the chosen agent's directory, such as .github/skills/ for GitHub Copilot.

Expected outcome

Selected repository skills are installed in the chosen agent's directory; the README says they can be symlinked when using multiple agents.

Guide limitations

  • The repository recommends selecting only relevant skills rather than loading the whole collection.
  • The repository is identified as work in progress.
Source-based practical guide

Copy a skill from a repository clone

Add a specific skill directory to a project using the documented manual method.

Before you start

  • Git
  • A project directory with an agent configuration location

Steps

  1. Clone https://github.com/microsoft/skills.git.

  2. Copy the selected skill directory from the repository into the project's agent skills directory.

Expected outcome

The chosen skill's files are copied into the project directory.

Guide limitations

  • The README's example copies an Azure Cosmos DB Python skill; it does not document how to execute a task with the installed skill.
COMPARE OPTIONS

Compare options for AI coding assistance

These projects document a common task and share a project role. This is a source-based comparison, not an execution benchmark or a guarantee of interchangeability.

ProjectDocumented purposePlatformAccess and requirements
Agent SkillsGive a coding agent focused domain context for an SDK-related task.Server, WebThe repository is public and identifies its license as MIT.
DextoDefine agents in YAML with a model, tools, storage and permissions.CLI
Evidence and transparency

Sources & review

Source record details
Source availability
Active
Sources checked
9 October 2026
Original website title
microsoft/skills · Official homepage title · retained in its source language