airflow.providers.common.ai.example_dags.example_agent_skills

Example DAGs demonstrating Agent Skills with AgentOperator.

Agent Skills are SKILL.md bundles the model discovers and loads on demand (progressive disclosure). They are passed to the agent as an AgentSkillsToolset in the operator’s toolsets= list. Skill sources are resolved when the task runs, on the worker (not while the DAG processor parses the file), so a Git token resolved from an Airflow connection is never baked into the serialized DAG.

These DAGs need the optional skills extra:

pip install "apache-airflow-providers-common-ai[skills]"

Attributes

SKILLS_DIR

Functions

example_agent_skills_local()

example_agent_skills_git()

Module Contents

airflow.providers.common.ai.example_dags.example_agent_skills.SKILLS_DIR[source]
airflow.providers.common.ai.example_dags.example_agent_skills.example_agent_skills_local()[source]
airflow.providers.common.ai.example_dags.example_agent_skills.example_agent_skills_git()[source]

Was this entry helpful?