Agent skill

Airflow Hitl

Builds human-in-the-loop (HITL) Airflow workflows - approval gates, form input, and human-driven branching.

Apache-2.0Auto-check passedData & Analytics

Install Airflow Hitl

skills CLI

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

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install astronomer/agents airflow-hitl --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/astronomer/agents.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/airflow-hitl .claude/skills/airflow-hitl && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "airflow-hitl" agent skill from https://github.com/astronomer/agents/tree/main/skills/airflow-hitl into .claude/skills/airflow-hitl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airflow-hitl", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/astronomer/agents/tree/main/skills/airflow-hitl

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add astronomer/agents --skill airflow-hitl -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install astronomer/agents airflow-hitl --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/astronomer/agents.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/airflow-hitl .agents/skills/airflow-hitl && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "airflow-hitl" agent skill from https://github.com/astronomer/agents/tree/main/skills/airflow-hitl into .agents/skills/airflow-hitl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airflow-hitl", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add astronomer/agents --skill airflow-hitl -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install astronomer/agents airflow-hitl --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/astronomer/agents.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/airflow-hitl .cursor/skills/airflow-hitl && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "airflow-hitl" agent skill from https://github.com/astronomer/agents/tree/main/skills/airflow-hitl into .cursor/skills/airflow-hitl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airflow-hitl", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/astronomer/agents.git --path skills/airflow-hitl

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add astronomer/agents --skill airflow-hitl -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install astronomer/agents airflow-hitl --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/astronomer/agents.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/airflow-hitl .gemini/skills/airflow-hitl && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "airflow-hitl" agent skill from https://github.com/astronomer/agents/tree/main/skills/airflow-hitl into .gemini/skills/airflow-hitl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airflow-hitl", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install astronomer/agents airflow-hitl

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add astronomer/agents --skill airflow-hitl -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/astronomer/agents.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/airflow-hitl .github/skills/airflow-hitl && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "airflow-hitl" agent skill from https://github.com/astronomer/agents/tree/main/skills/airflow-hitl into .github/skills/airflow-hitl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airflow-hitl", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add astronomer/agents --skill airflow-hitl -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install astronomer/agents airflow-hitl --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/astronomer/agents.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/airflow-hitl .opencode/skills/airflow-hitl && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "airflow-hitl" agent skill from https://github.com/astronomer/agents/tree/main/skills/airflow-hitl into .opencode/skills/airflow-hitl/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "airflow-hitl", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: airflow-hitl
GitHub stars: 451
Token cost: ~1.8k tokens
SKILL.md length: 594 words
Files: 1
Skills in repo: 34
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Builds human-in-the-loop (HITL) Airflow workflows - approval gates, form input, and human-driven branching.

Works in 6 steps: Pick the capability you need → Discover the current signatures from the… → Canonical example (approval gate) → …
A DAG needs a human in the loop - an approval
SKILL.md covers Step 1 — Pick the capability…, Step 2 — Discover the current…, Step 3 — Canonical example… and Step 4 — Behavior contracts…, plus 4 more sections
Calls jq; needs AIRFLOW_API_TOKEN

What it does

Airflow Hitl is an agent skill from astronomer/agents. Builds human-in-the-loop (HITL) Airflow workflows - approval gates, form input, and human-driven branching. Use when a DAG needs a human in the loop - an approval or reject step, sign-off before a task runs, a decision or approval UI, branching on a human choice, or collecting form input mid-run; also on mentions of ApprovalOperator, HITLOperator, HITLBranchOperator, HITLEntryOperator, or HITLTrigger. Requires Airflow 3.1+. Not for AI/LLM task calls (see migrating-ai-sdk-to-common-ai).

Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Data & Analytics, covering Data pipelines and ETL and Human-in-the-loop approvals. It works with Apache Airflow and Vercel AI SDK. The repository describes itself as: AI agent tooling for data engineering workflows. The licence is Apache-2.0.

When your agent uses it

A DAG needs a human in the loop - an approval
Sign-off before a task runs
Branching on a human choice
Collecting form input mid-run

Example prompts

“Use the airflow-hitl skill to build human-in-the-loop (HITL) Airflow workflows - approval gates, form input, and human-driven branching”
“/airflow-hitl”

Requirements

Python 3
A credential in AIRFLOW_API_TOKEN

Workflow steps

6 steps, taken from the step headings in SKILL.md.

Pick the capability you need
Discover the current signatures from the Airflow Registry
Canonical example (approval gate)
Behavior contracts (stable across versions)
Responding from external integrations
Safety checks

What it can do on your machine

Read from SKILL.md and the folder at commit 486ee63. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- jq
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- AIRFLOW_API_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Airflow Hitl loads about 1.8k tokens when it runs. Until then it costs about 126 tokens; SKILL.md has 594 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~126
When it runs · the whole SKILL.md, loaded when a task matches: ~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from astronomer/agents at commit 486ee63, republished under its Apache-2.0 licence (© astronomer). 594 words, ~1,847 tokens.

Download SKILL.mdSave it as .claude/skills/airflow-hitl/SKILL.md (or your agent's skills folder).

name: airflow-hitl
description: Builds human-in-the-loop (HITL) Airflow workflows - approval gates, form input, and human-driven branching. Use when a DAG needs a human in the loop - an approval or reject step, sign-off before a task runs, a decision or approval UI, branching on a human choice, or collecting form input mid-run; also on mentions of ApprovalOperator, HITLOperator, HITLBranchOperator, HITLEntryOperator, or HITLTrigger. Requires Airflow 3.1+. Not for AI/LLM task calls (see migrating-ai-sdk-to-common-ai).

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.

Step 2 — Discover the current signatures from the Airflow Registry

Before writing HITL code, run these to see the live roster and constructor params (see the airflow skill for the full af registry reference):

bash

# Every HITL-related module in the standard provider
af registry modules standard \
  | jq '.modules[] | select(.import_path | test("\\.hitl\\.")) | {name, type, import_path, short_description, docs_url}'

# Constructor signatures: name, type, default, required, description
af registry parameters standard \
  | jq '.classes | to_entries[] | select(.key | test("\\.hitl\\.")) | {fqn: .key, parameters: .value.parameters}'

# Pin to the exact installed provider version
af config providers \
  | jq '.providers[] | select(.package_name == "apache-airflow-providers-standard") | .version'
# then: af registry parameters standard --version <VERSION>

If the registry shows a param that this skill does not mention, prefer the registry. If the registry shows a class that is not in Step 1, treat it as additive — the decision table above may be stale.

Step 3 — Canonical example (approval gate)

Starting point for any HITL task. Adapt by swapping the class name and params per Step 2.

python

from airflow.providers.standard.operators.hitl import ApprovalOperator
from airflow.sdk import dag, task, chain, Param
from pendulum import datetime

@dag(start_date=datetime(2025, 1, 1), schedule="@daily")
def approval_example():
    @task
    def prepare():
        return "Review quarterly report"

    approval = ApprovalOperator(
        task_id="approve_report",
        subject="Report Approval",
        body="{{ ti.xcom_pull(task_ids='prepare') }}",
        defaults="Approve",              # Auto-selected on timeout
        params={"comments": Param("", type="string")},
    )

    @task
    def after_approval(result):
        print(f"Decision: {result['chosen_options']}")

    chain(prepare(), approval)
    after_approval(approval.output)

approval_example()

For the other classes in Step 1, the shape is the same (task_id, subject, plus class-specific params). Verify each constructor through Step 2 — for example, HITLBranchOperator requires every option either to match a downstream task id directly or to be resolved via a mapping param surfaced in the registry.

Step 4 — Behavior contracts (stable across versions)

Timeout

With defaults set: task succeeds on timeout, default option(s) selected.
Without defaults: task fails on timeout.

Markdown + Jinja in `body`

body supports Markdown and is Jinja-templatable. Render XCom context directly:

python

body = """**Total Budget:** {{ ti.xcom_pull(task_ids='get_budget') }}

| Category | Amount |
|----------|--------|
| Marketing | $1M |
"""

Callbacks

All HITL operators accept the standard Airflow callback kwargs (on_success_callback, on_failure_callback, etc.).

Show full SKILL.md (246 more words)Show less

Notifiers

HITL operators accept a notifiers list. Inside a notifier's notify(context) method, build a link to the pending task with HITLOperator.generate_link_to_ui_from_context(context, base_url=...).

Restricting who can respond

The parameter name and accepted identifier format depend on the active auth manager. Do not hardcode — check which one is active and which kwarg the current provider exposes:

bash

af config show | jq '.auth_manager // .core.auth_manager'

Then look up the current kwarg in Step 2 (at the time of writing it is assigned_users, accepting identifiers in whatever format the active auth manager uses — Astro uses the Astro user ID, FabAuthManager uses email, SimpleAuthManager uses username).

Step 5 — Responding from external integrations

For Slack bots, custom apps, or scripts. Discover the live endpoint rather than hardcoding a path:

bash

af api ls --filter hitl           # live endpoint list
af api spec \
  | jq '.paths | to_entries[] | select(.key | test("hitl"))'   # request/response schemas

The PATCH-to-respond pattern is stable; the exact path is discovered. Typical shape:

python

import os, requests

HOST = os.environ["AIRFLOW_HOST"]
TOKEN = os.environ["AIRFLOW_API_TOKEN"]
HEADERS = {"Authorization": f"Bearer {TOKEN}"}

# List pending — use the path from `af api ls --filter hitl`
requests.get(f"{HOST}/<path>", headers=HEADERS, params={"state": "pending"})

# Respond — same discovered path family, PATCH
requests.patch(
    f"{HOST}/<path>/{dag_id}/{run_id}/{task_id}",
    headers=HEADERS,
    json={"chosen_options": ["Approve"], "params_input": {"comments": "ok"}},
)

Step 6 — Safety checks

Airflow version ≥ 3.1 (af config version).
Constructor kwargs match the current registry output from Step 2 — no respondents-vs-assigned_users style drift.
For branching: every option resolves to a downstream task id (directly or via the mapping kwarg from Step 2).
Every value in defaults is also in options.
execution_timeout set; defaults configured if timeout should succeed rather than fail.
API token configured if external responders are part of the flow.

References

The upstream docs URL is surfaced per-module by the registry — do not hardcode:

bash

af registry modules standard \
  | jq '.modules[] | select(.import_path | test("\\.hitl\\.")) | {name, docs_url}'

airflow — af registry, af api, af config command reference.
migrating-ai-sdk-to-common-ai — AI/LLM task decorators and GenAI patterns (common-ai provider).
authoring-dags — general DAG writing best practices.
testing-dags — iterative test → debug → fix cycles.

Files

Just SKILL.md in skills/airflow-hitl of astronomer/agents.

Open the folder on GitHubat commit 486ee63

Compare with similar skills

Airflow Hitl next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Airflow Hitl compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Airflow Hitl this skillastronomer/agents	451	—	~1.8k	Automated safety check: Pass	Apache-2.0	3 days ago
Chart Testsastronomer/airflow-chart	297	—	~2.8k	Automated safety check: Pass	Custom licence	3 days ago
Functional Testsastronomer/airflow-chart	297	—	~2.2k	Automated safety check: Pass	Custom licence	3 days ago
Create Examplegodatadriven/whirl	205	—	~1.1k	Automated safety check: Pass	Apache-2.0	9 days ago
Senior Data Engineerbenchflow-ai/skillsbench	1.8k	—	~5.9k	Automated safety check: Pass	MIT	2 mo ago
Airflow DAG Patternswshobson/agents	40k	9 repos	~784	Automated safety check: Pass	MIT	6 days ago

Similar skills

Chart Tests
astronomer/airflow-chart
A skill your agent uses when writing, editing, reviewing, or running Helm chart tests for the Astronomer airflow-chart repository.
297 GitHub stars~2.8k tokensUpdated 3 days ago
Data & AnalyticsAuto-check passed
Functional Tests
astronomer/airflow-chart
A skill your agent uses when writing, editing, reviewing, or running functional (end-to-end) tests for the Astronomer airflow-chart repository.
297 GitHub stars~2.2k tokensUpdated 3 days ago
Data & AnalyticsAuto-check passed
Create Example
godatadriven/whirl
Create a new Whirl example project in the examples/ directory.
205 GitHub stars~1.1k tokensUpdated 9 days ago
Data & AnalyticsAuto-check passed
Senior Data Engineer
benchflow-ai/skillsbench
World-class data engineering skill for building scalable data pipelines, ETL/ELT systems, real-time streaming, and data infrastructure.
1.8k GitHub stars~5.9k tokensUpdated 2 mo ago
Data & AnalyticsAuto-check passed
Airflow DAG Patterns
wshobson/agents
Patterns for writing production-ready Apache Airflow DAGs: task dependencies, custom operators and sensors, local testing, and rules for what to avoid.
40k GitHub starsUsed in 9 repos~784 tokens
Data & AnalyticsAuto-check passed
Version Bumper
godatadriven/whirl
Bump the Airflow or Python version across all project files.
205 GitHub stars~1.2k tokensUpdated 9 days ago
Data & AnalyticsAuto-check passed

Questions about Airflow Hitl

What does Airflow Hitl do?

Builds human-in-the-loop (HITL) Airflow workflows - approval gates, form input, and human-driven branching. Airflow Hitl is an agent skill from astronomer/agents. Builds human-in-the-loop (HITL) Airflow workflows - approval gates, form input, and human-driven branching.

When should I use Airflow Hitl?

Airflow Hitl fits situations like: A DAG needs a human in the loop - an approval; sign-off before a task runs; branching on a human choice; collecting form input mid-run.

How do I install Airflow Hitl in Claude Code?

Run `npx skills add astronomer/agents --skill airflow-hitl -a claude-code`. Or copy the skill folder (skills/airflow-hitl in astronomer/agents) into .claude/skills/airflow-hitl in your project. Claude Code loads it when a task matches its description.

How do I install Airflow Hitl in Codex?

Run `npx skills add astronomer/agents --skill airflow-hitl -a codex`. Or copy the skill folder (skills/airflow-hitl in astronomer/agents) into .agents/skills/airflow-hitl in your project. Codex loads it when a task matches its description.

Can I use Airflow Hitl in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add astronomer/agents --skill airflow-hitl -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/airflow-hitl, .gemini/skills/airflow-hitl, .github/skills/airflow-hitl and .opencode/skills/airflow-hitl in your project.

What does Airflow Hitl need to run?

Going by SKILL.md and its folder, Airflow Hitl needs the command-line tools its instructions call (jq) and credentials named AIRFLOW_API_TOKEN. Our summary lists: Python 3; A credential in AIRFLOW_API_TOKEN.

Does Airflow Hitl access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Airflow Hitl safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Airflow Hitl use?

Airflow Hitl is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Airflow Hitl use?

About 1.8k tokens (SKILL.md is roughly 7.4k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Airflow Hitl?

Skills that share tags, products or a category with Airflow Hitl: Chart Tests (astronomer/airflow-chart, 297 stars), Functional Tests (astronomer/airflow-chart, 297 stars), Create Example (godatadriven/whirl, 205 stars) and Senior Data Engineer (benchflow-ai/skillsbench, 1.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Airflow Hitl?

astronomer (a GitHub organization) maintains it in astronomer/agents, which has 451 GitHub stars. The repository holds 34 skills in this directory. The repository was last updated on October 7, 2026.

Source: astronomer/agents on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Airflow Hitl

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Airflow Human-in-the-Loop Operators

Step 1 — Pick the capability you need

Step 2 — Discover the current signatures from the Airflow Registry

Step 3 — Canonical example (approval gate)

Step 4 — Behavior contracts (stable across versions)

Timeout

Markdown + Jinja in body

Callbacks

Notifiers

Restricting who can respond

Step 5 — Responding from external integrations

Step 6 — Safety checks

References

Related skills

Files

Compare with similar skills

Similar skills

More from astronomer/agents

Related

Questions about Airflow Hitl

Markdown + Jinja in `body`