Airflow Hitl

Adds approval gates, form inputs, and human-driven branching to Airflow DAGs using deferrable operators that release worker slots while waiting. You get ApprovalOperator for approve/reject flows, HITLBranchOperator for routing based on human choices, and HITLEntryOperator for pure form collection. The skill is built around a discover-then-code pattern: query the live Airflow registry for current constructor signatures before writing any tasks, since the provider changes params across releases. Responses come through the Airflow UI or REST API. Requires Airflow 3.1+. The safety checklist and external integration examples (Slack bots, custom scripts) are the most useful parts if you need humans in the loop without blocking workers.

skills.sh installs: 980
GitHub stars: 459
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add astronomer/agents --skill airflow-hitl --agent claude-code

Installs into .claude/skills of the current project.

Files

Airflow Human-in-the-Loop Operators

Pause a DAG until a human responds via the Airflow UI or REST API. HITL operators are deferrable — they release their worker slot while waiting.

Requires Airflow 3.1+ (af config version).

UI location: Browse → Required Actions. Respond from the task instance page's Required Actions tab.

Cross-references: migrating-ai-sdk-to-common-ai for AI/LLM task decorators; airflow for registry and API discovery commands used below.

Step 1 — Pick the capability you need

Capability	Class (verify in Step 2)
Approve or reject; downstream skips on reject	`ApprovalOperator`
Present N options and return which were chosen	`HITLOperator`
Branch to one or more downstream tasks based on a choice	`HITLBranchOperator`
Collect a form (no approve/select step)	`HITLEntryOperator`
Use the HITL trigger directly (advanced / custom operators)	`HITLTrigger`

This is the only place class names are hardcoded. The provider adds, renames, and removes params across releases — do not copy parameter lists from memory. Fetch the current signature before writing code.

SKILL.md on GitHub

Details

Repository: github.com/astronomer/agents
Categories: AI & Agent Building, Productivity & Planning, Automation & Workflows
First seen: May 16, 2026