Agent Skills

Basic setup

Create a FileAgentSkillsProvider pointing to a directory containing your skills, and add it to the agent's context providers:

using Azure.AI.OpenAI;
using Azure.Identity;
using Microsoft.Agents.AI;

// Discover skills from the 'skills' directory
var skillsProvider = new FileAgentSkillsProvider(
    skillPath: Path.Combine(AppContext.BaseDirectory, "skills"));

// Create an agent with the skills provider
AIAgent agent = new AzureOpenAIClient(
    new Uri(endpoint), new DefaultAzureCredential())
    .GetResponsesClient(deploymentName)
    .AsAIAgent(new ChatClientAgentOptions
    {
        Name = "SkillsAgent",
        ChatOptions = new()
        {
            Instructions = "You are a helpful assistant.",
        },
        AIContextProviders = [skillsProvider],
    });

Invoking the agent

Once configured, the agent automatically discovers available skills and uses them when a task matches:

// The agent loads the expense-report skill and reads the FAQ resource
AgentResponse response = await agent.RunAsync(
    "Are tips reimbursable? I left a 25% tip on a taxi ride.");
Console.WriteLine(response.Text);

Basic setup

Create a SkillsProvider pointing to a directory containing your skills, and add it to the agent's context providers:

from pathlib import Path
from agent_framework import SkillsProvider
from agent_framework.azure import AzureOpenAIChatClient
from azure.identity.aio import AzureCliCredential

# Discover skills from the 'skills' directory
skills_provider = SkillsProvider(
    skill_paths=Path(__file__).parent / "skills"
)

# Create an agent with the skills provider
agent = AzureOpenAIChatClient(credential=AzureCliCredential()).as_agent(
    name="SkillsAgent",
    instructions="You are a helpful assistant.",
    context_providers=[skills_provider],
)

Invoking the agent

Once configured, the agent automatically discovers available skills and uses them when a task matches:

# The agent loads the expense-report skill and reads the FAQ resource
response = await agent.run(
    "Are tips reimbursable? I left a 25% tip on a taxi ride."
)
print(response.text)

var skillsProvider = new FileAgentSkillsProvider(
    skillPaths: [
        Path.Combine(AppContext.BaseDirectory, "company-skills"),
        Path.Combine(AppContext.BaseDirectory, "team-skills"),
    ]);

skills_provider = SkillsProvider(
    skill_paths=[
        Path(__file__).parent / "company-skills",
        Path(__file__).parent / "team-skills",
    ]
)

var skillsProvider = new FileAgentSkillsProvider(
    skillPath: Path.Combine(AppContext.BaseDirectory, "skills"),
    options: new FileAgentSkillsProviderOptions
    {
        SkillsInstructionPrompt = """
            You have skills available. Here they are:
            {0}
            Use the `load_skill` function to get skill instructions.
            Use the `read_skill_resource` function to read skill files.
            """
    });

skills_provider = SkillsProvider(
    skill_paths=Path(__file__).parent / "skills",
    instruction_template=(
        "You have skills available. Here they are:\n{skills}\n"
        "Use the `load_skill` function to get skill instructions.\n"
        "Use the `read_skill_resource` function to read skill files."
    ),
)

Code-defined skills

In addition to file-based skills discovered from SKILL.md files, you can define skills entirely in Python code. Code-defined skills are useful when:

• Skill content is generated dynamically (for example, reading from a database or environment).
• You want to keep skill definitions alongside the application code that uses them.
• You need resources that execute logic at read time rather than serving static files.

Basic code skill

Create a Skill instance with a name, description, and instruction content. Optionally attach SkillResource instances with static content:

from textwrap import dedent
from agent_framework import Skill, SkillResource, SkillsProvider

code_style_skill = Skill(
    name="code-style",
    description="Coding style guidelines and conventions for the team",
    content=dedent("""\
        Use this skill when answering questions about coding style,
        conventions, or best practices for the team.
    """),
    resources=[
        SkillResource(
            name="style-guide",
            content=dedent("""\
                # Team Coding Style Guide
                - Use 4-space indentation (no tabs)
                - Maximum line length: 120 characters
                - Use type annotations on all public functions
            """),
        ),
    ],
)

skills_provider = SkillsProvider(skills=[code_style_skill])

Dynamic resources

Use the @skill.resource decorator to register a function as a resource. The function is called each time the agent reads the resource, so it can return up-to-date data. Both sync and async functions are supported:

import os
from agent_framework import Skill

project_info_skill = Skill(
    name="project-info",
    description="Project status and configuration information",
    content="Use this skill for questions about the current project.",
)

@project_info_skill.resource
def environment() -> Any:
    """Get current environment configuration."""
    env = os.environ.get("APP_ENV", "development")
    region = os.environ.get("APP_REGION", "us-east-1")
    return f"Environment: {env}, Region: {region}"

@project_info_skill.resource(name="team-roster", description="Current team members")
def get_team_roster() -> Any:
    """Return the team roster."""
    return "Alice Chen (Tech Lead), Bob Smith (Backend Engineer)"

When the decorator is used without arguments (@skill.resource), the function name becomes the resource name and the docstring becomes the description. Use @skill.resource(name="...", description="...") to set them explicitly.

Code-defined scripts

Use the @skill.script decorator to register a function as an executable script on a skill. Code-defined scripts run in-process and do not require a script executor. Both sync and async functions are supported:

from agent_framework import Skill

unit_converter_skill = Skill(
    name="unit-converter",
    description="Convert between common units using a conversion factor",
    content="Use the convert script to perform unit conversions.",
)

@unit_converter_skill.script(name="convert", description="Convert a value: result = value × factor")
def convert_units(value: float, factor: float) -> str:
    """Convert a value using a multiplication factor."""
    import json
    result = round(value * factor, 4)
    return json.dumps({"value": value, "factor": factor, "result": result})

When the decorator is used without arguments (@skill.script), the function name becomes the script name and the docstring becomes the description. The function's typed parameters are automatically converted into a JSON Schema that the agent uses to pass arguments.

Combining file-based and code-defined skills

Pass both skill_paths and skills to a single SkillsProvider. File-based skills are discovered first; if a code-defined skill has the same name as an existing file-based skill, the code-defined skill is skipped:

from pathlib import Path
from agent_framework import Skill, SkillsProvider

my_skill = Skill(
    name="my-code-skill",
    description="A code-defined skill",
    content="Instructions for the skill.",
)

skills_provider = SkillsProvider(
    skill_paths=Path(__file__).parent / "skills",
    skills=[my_skill],
)

Script execution

Skills can include executable scripts that the agent runs via the run_skill_script tool. How a script runs depends on how it was defined:

• Code-defined scripts (registered via @skill.script) run in-process as direct function calls. No runner is needed.
• File-based scripts (.py files discovered in skill directories) require a SkillScriptRunner — any callable matching (skill, script, args) -> Any — that determines how the script is run (for example, as a local subprocess).

File-based script execution

To enable execution of file-based scripts, pass a script_runner to SkillsProvider. Any sync or async callable that satisfies the SkillScriptRunner protocol can be used:

from pathlib import Path
from agent_framework import Skill, SkillScript, SkillsProvider

def my_runner(skill: Skill, script: SkillScript, args: dict | None = None) -> str:
    """Run a file-based script as a subprocess."""
    import subprocess, sys
    cmd = [sys.executable, str(Path(skill.path) / script.path)]
    if args:
        for key, value in args.items():
            if value is not None:
                cmd.extend([f"--{key}", str(value)])
    result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
    return result.stdout.strip()

skills_provider = SkillsProvider(
    skill_paths=Path(__file__).parent / "skills",
    script_runner=my_runner,
)

The runner receives the resolved Skill, SkillScript, and an optional args dictionary. File-based scripts are automatically discovered from .py files in skill directories.

Script approval

Use require_script_approval=True on SkillsProvider to gate all script execution behind human approval. Instead of executing immediately, the agent pauses and returns approval requests:

from agent_framework import Agent, Skill, SkillsProvider

# Create provider with approval enabled
skills_provider = SkillsProvider(
    skills=[my_skill],
    require_script_approval=True,
)

# Run the agent — script calls pause for approval
result = await agent.run("Deploy version 2.5.0 to production", session=session)

# Handle approval requests
while result.user_input_requests:
    for request in result.user_input_requests:
        print(f"Script: {request.function_call.name}")
        print(f"Args: {request.function_call.arguments}")

        approval = request.to_function_approval_response(approved=True)
        result = await agent.run(approval, session=session)

When a script is rejected (approved=False), the agent is informed that the user declined and can respond accordingly.