aget_skills

Load toolbox skills as a deepagents-ready file mapping.

This is an opinionated convenience built on top of :meth:aget_resources. It fetches the toolbox skills (MCP resources with skill:// URIs) and returns a mapping of virtual file paths to deepagents FileData objects, laid out under base_path in the directory structure that create_deep_agent expects::

{f"{base_path}{skill_name}/SKILL.md": <FileData>, ...}

How the files reach the agent depends on the backend:

• StateBackend (default): leave backend as None and pass the returned mapping as the files payload on invoke. State writes go through the LangGraph runtime, so the backend cannot be seeded standalone.
• FilesystemBackend / StoreBackend / sandbox backends: pass the backend as backend. The skills are written into it via aupload_files and the same mapping is also returned.

Seeding a StateBackend (default)::

from deepagents import create_deep_agent
from deepagents.backends import StateBackend
from langchain_azure_ai.tools import AzureAIProjectToolbox

toolbox = AzureAIProjectToolbox(toolbox_name="my-tools")
skill_files = await toolbox.aget_skills()

agent = create_deep_agent(
    model="azure_ai:gpt-5.2",
    backend=StateBackend(),
    skills=[base_path],
)
await agent.ainvoke(
    {"messages": [...], "files": skill_files}
)

Seeding any other backend (e.g. FilesystemBackend)::

from deepagents.backends import FilesystemBackend

backend = FilesystemBackend(root_dir="./my-project")
toolbox = AzureAIProjectToolbox(toolbox_name="my-tools")
await toolbox.aget_skills(backend=backend)

agent = create_deep_agent(
    model="azure_ai:gpt-5.2",
    backend=backend,
    skills=["/skills/"],
)