Skip to content
Back to search

astronomer

MarketplaceWorks with Claude CodeGitHub

AI agent tooling for data engineering workflows.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today

Check it deeper on your machine

It has changed since its scan on 11 Nov 2026.

As a Claude Code plugin, install it and then ask Claude Code:

/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/astronomer/agents with scanskillsafety

Or from a terminal, clone it and run it:

git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/astronomer/agents'

It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.

Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/astronomer-agents/badge.svg)](/listings/astronomer-agents)

HTML

<a href="/listings/astronomer-agents"><img src="/api/listings/astronomer-agents/badge.svg" alt="findsafeskills safety rating" /></a>

Install

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

Quick Start

npx skills add astronomer/agents --skill '*'

This installs all Astronomer skills into your project via [skills.sh](https://skills.sh). You'll be prompted to select which agents to install to. To also select skills individually, omit the `--skill` flag.

> [!IMPORTANT] > **Claude Code users:** We recommend using the plugin instead (see [Claude Code](#claude-code) section below) for better integration with MCP servers and hooks.

Compatibility

**Skills:** Works with [25+ AI coding agents](https://github.com/vercel-labs/add-skill?tab=readme-ov-file#available-agents) including Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, Cline, and more.

**MCP Server:** Works with any [MCP-compatible client](https://modelcontextprotocol.io/clients) including Claude Desktop, VS Code, and others.

> [!NOTE] > **Open-source Airflow users:** The MCP server works with any Airflow 2.x/3.x REST API. Set `AIRFLOW_API_URL` to your self-hosted instance. Skills are tool-agnostic and work with any Airflow deployment.

Claude Code

# Add the marketplace and install the plugin
claude plugin marketplace add astronomer/agents
claude plugin install astronomer-data@astronomer

# Upgrading from the old plugin name? Uninstall first:
# claude plugin uninstall data@astronomer && claude plugin marketplace update && claude plugin install astronomer-data@astronomer

The plugin includes the Airflow MCP server that runs via `uvx` from PyPI. Data warehouse queries are handled by the `analyzing-data` skill using a background Jupyter kernel.

Cursor

Cursor supports both MCP servers and skills.

**MCP Server** - Click to install:

**Skills** - Install to your project:

npx skills add astronomer/agents --skill '*' -a cursor

This installs skills to `.cursor/skills/` in your project.

<details> <summary>Manual MCP configuration</summary>

Add to `~/.cursor/mcp.json`:

{
  "mcpServers": {
    "airflow": {
      "command": "uvx",
      "args": ["astro-airflow-mcp", "--transport", "stdio"]
    }
  }
}

</details>

<details> <summary>Enable hooks (session management)</summary>

Create `.cursor/hooks.json` in your project:

{
  "version": 1,
  "hooks": {
    "stop": [
      {
        "command": "uv run $CURSOR_PROJECT_DIR/.cursor/skills/analyzing-data/scripts/cli.py stop",
        "timeout": 10
      }
    ]
  }
}

**What these hooks do:** - `stop`: Cleans up kernel when session ends

</details>

Other MCP Clients

For any MCP-compatible client (Claude Desktop, VS Code, etc.):

# Airflow MCP
uvx astro-airflow-mcp --transport stdio

# With remote Airflow
AIRFLOW_API_URL=https://your-airflow.example.com \
AIRFLOW_USERNAME=admin \
AIRFLOW_PASSWORD=admin \
uvx astro-airflow-mcp --transport stdio

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

.claude-plugin/marketplace.json · Manifest · 22 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. {
  2. "name": "astronomer",
  3. "owner": {
  4. "name": "Astronomer",
  5. "email": "support@astronomer.io"
  6. },
  7. "plugins": [
  8. {
  9. "name": "astronomer-data",
  10. "source": "./",
  11. "strict": false,
  12. "description": "Data engineering plugin - warehouse exploration, pipeline authoring, Airflow integration",
  13. "author": {
  14. "name": "Astronomer",
  15. "email": "support@astronomer.io"
  16. },
  17. "homepage": "https://github.com/astronomer/agents",
  18. "repository": "https://github.com/astronomer/agents",
  19. "keywords": ["data-engineering", "airflow", "snowflake", "bigquery", "jupyter", "astronomer"]
  20. }
  21. ]
  22. }
README.md · README · 507 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # agents
  2. AI agent tooling for data engineering workflows. Includes an [MCP server](./astro-airflow-mcp/) for Airflow, a [CLI tool (`af`)](./astro-airflow-mcp/README.md#airflow-cli-tool) for interacting with Airflow from your terminal, and [skills](#skills) that extend AI coding agents with specialized capabilities for working with Airflow and data warehouses. Works with [Claude Code](https://docs.anthropic.com/en/docs/claude-code), [Cursor](https://cursor.com), and other agentic coding tools.
  3. Built by [Astronomer](https://www.astronomer.io/). [Apache 2.0 licensed](https://github.com/astronomer/agents/blob/main/LICENSE) and compatible with open-source Apache Airflow.
  4. ## Table of Contents
  5. <!-- START doctoc generated TOC please keep comment here to allow auto update -->
  6. <!-- DON'T EDIT THIS SECTION, INSTEAD RE-RUN doctoc TO UPDATE -->
  7. - [Installation](#installation)
  8. - [Quick Start](#quick-start)
  9. - [Compatibility](#compatibility)
  10. - [Claude Code](#claude-code)
  11. - [Cursor](#cursor)
  12. - [Other MCP Clients](#other-mcp-clients)
  13. - [Features](#features)
  14. - [MCP Server](#mcp-server)
  15. - [Skills](#skills)
  16. - [Why Astro?](#why-astro)
  17. - [User Journeys](#user-journeys)
  18. - [Airflow CLI (`af`)](#airflow-cli-af)
  19. - [Configuration](#configuration)
  20. - [Warehouse Connections](#warehouse-connections)
  21. - [Airflow](#airflow)
  22. - [Usage](#usage)
  23. - [Getting Started](#getting-started)
  24. - [Development](#development)
  25. - [Local Development Setup](#local-development-setup)
  26. - [Adding Skills](#adding-skills)
  27. - [Troubleshooting](#troubleshooting)
  28. - [Common Issues](#common-issues)
  29. - [Contributing](#contributing)
  30. - [Roadmap](#roadmap)
  31. - [License](#license)
  32. <!-- END doctoc generated TOC please keep comment here to allow auto update -->
  33. ## Installation
  34. ### Quick Start
  35. ```bash
  36. npx skills add astronomer/agents --skill '*'
  37. ```
  38. This installs all Astronomer skills into your project via [skills.sh](https://skills.sh). You'll be prompted to select which agents to install to. To also select skills individually, omit the `--skill` flag.
  39. > [!IMPORTANT]
  40. > **Claude Code users:** We recommend using the plugin instead (see [Claude Code](#claude-code) section below) for better integration with MCP servers and hooks.
  41. ### Compatibility
  42. **Skills:** Works with [25+ AI coding agents](https://github.com/vercel-labs/add-skill?tab=readme-ov-file#available-agents) including Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, Cline, and more.
  43. **MCP Server:** Works with any [MCP-compatible client](https://modelcontextprotocol.io/clients) including Claude Desktop, VS Code, and others.
  44. > [!NOTE]
  45. > **Open-source Airflow users:** The MCP server works with any Airflow 2.x/3.x REST API. Set `AIRFLOW_API_URL` to your self-hosted instance. Skills are tool-agnostic and work with any Airflow deployment.
  46. ### Claude Code
  47. ```bash
  48. # Add the marketplace and install the plugin
  49. claude plugin marketplace add astronomer/agents
  50. claude plugin install astronomer-data@astronomer
  51. # Upgrading from the old plugin name? Uninstall first:
  52. # claude plugin uninstall data@astronomer && claude plugin marketplace update && claude plugin install astronomer-data@astronomer
  53. ```
  54. The plugin includes the Airflow MCP server that runs via `uvx` from PyPI. Data warehouse queries are handled by the `analyzing-data` skill using a background Jupyter kernel.
  55. ### Cursor
  56. Cursor supports both MCP servers and skills.
  57. **MCP Server** - Click to install:
  58. <a href="https://cursor.com/en-US/install-mcp?name=astro-airflow-mcp&config=eyJjb21tYW5kIjoidXZ4IiwiYXJncyI6WyJhc3Ryby1haXJmbG93LW1jcCIsIi0tdHJhbnNwb3J0Iiwic3RkaW8iXX0"><img src="https://cursor.com/deeplink/mcp-install-dark.svg" alt="Add Airflow MCP to Cursor" height="32"></a>
  59. **Skills** - Install to your project:
  60. ```bash
  61. npx skills add astronomer/agents --skill '*' -a cursor
  62. ```
  63. This installs skills to `.cursor/skills/` in your project.
  64. <details>
  65. <summary>Manual MCP configuration</summary>
  66. Add to `~/.cursor/mcp.json`:
  67. ```json
  68. {
  69. "mcpServers": {
  70. "airflow": {
  71. "command": "uvx",
  72. "args": ["astro-airflow-mcp", "--transport", "stdio"]
  73. }
  74. }
  75. }
  76. ```
  77. </details>
  78. <details>
  79. <summary>Enable hooks (session management)</summary>
  80. Create `.cursor/hooks.json` in your project:
  81. ```json
  82. {
  83. "version": 1,
  84. "hooks": {
  85. "stop": [
  86. {
  87. "command": "uv run $CURSOR_PROJECT_DIR/.cursor/skills/analyzing-data/scripts/cli.py stop",
  88. "timeout": 10
  89. }
  90. ]
  91. }
  92. }
  93. ```
  94. **What these hooks do:**
  95. - `stop`: Cleans up kernel when session ends
  96. </details>
  97. ### Other MCP Clients
  98. For any MCP-compatible client (Claude Desktop, VS Code, etc.):
  99. ```bash
  100. # Airflow MCP
  101. uvx astro-airflow-mcp --transport stdio
  102. # With remote Airflow
  103. AIRFLOW_API_URL=https://your-airflow.example.com \
  104. AIRFLOW_USERNAME=admin \
  105. AIRFLOW_PASSWORD=admin \
  106. uvx astro-airflow-mcp --transport stdio
  107. ```
  108. ## Features
  109. The `astronomer-data` plugin bundles an MCP server and skills into a single installable package.
  110. ### MCP Server
  111. | Server | Description |
  112. |--------|-------------|
  113. | **[Airflow](https://github.com/astronomer/agents/tree/main/astro-airflow-mcp)** | Full Airflow REST API integration via [astro-airflow-mcp](https://github.com/astronomer/agents/tree/main/astro-airflow-mcp): DAG management, triggering, task logs, system health |
  114. ### Skills
  115. #### Data Discovery & Analysis
  116. | Skill | Description |
  117. |-------|-------------|
  118. | [warehouse-init](./skills/warehouse-init/) | Initialize schema discovery - generates `.astro/warehouse.md` for instant lookups |
  119. | [analyzing-data](./skills/analyzing-data/) | SQL-based analysis to answer business questions (uses background Jupyter kernel) |
  120. | [checking-freshness](./skills/checking-freshness/) | Check how current your data is |
  121. | [profiling-tables](./skills/profiling-tables/) | Comprehensive table profiling and quality assessment |
  122. #### Data Lineage
  123. | Skill | Description |
  124. |-------|-------------|
  125. | [tracing-downstream-lineage](./skills/tracing-downstream-lineage/) | Analyze what breaks if you change something |
  126. | [tracing-upstream-lineage](./skills/tracing-upstream-lineage/) | Trace where data comes from |
  127. | [annotating-task-lineage](./skills/annotating-task-lineage/) | Add manual lineage to tasks using inlets/outlets |
  128. | [creating-openlineage-extractors](./skills/creating-openlineage-extractors/) | Build custom OpenLineage extractors for operators |
  129. #### DAG Development
  130. | Skill | Description |
  131. |-------|-------------|
  132. | [airflow](./skills/airflow/) | Main entrypoint - routes to specialized Airflow skills |
  133. | [setting-up-astro-project](./skills/setting-up-astro-project/) (Astro) | Initialize and configure new Astro/Airflow projects |
  134. | [managing-astro-local-env](./skills/managing-astro-local-env/) (Astro) | Manage local Airflow environment (start, stop, logs, troubleshoot) |
  135. | [authoring-dags](./skills/authoring-dags/) | Create and validate Airflow DAGs with best practices |
  136. | [blueprint](./skills/blueprint/) | Compose DAGs from YAML using reusable templates with Pydantic validation ([airflow-blueprint](https://github.com/astronomer/blueprint)) |
  137. | [testing-dags](./skills/testing-dags/) | Test and debug Airflow DAGs locally |
  138. | [debugging-dags](./skills/debugging-dags/) | Deep failure diagnosis and root cause analysis |
  139. | [deploying-airflow](./skills/deploying-airflow/) | Deploy Airflow DAGs and projects (Astro, Docker Compose, Kubernetes) |
  140. | [airflow-hitl](./skills/airflow-hitl/) | Human-in-the-loop workflows: approval gates, form input, branching (Airflow 3.1+) |
  141. #### dbt Integration
  142. | Skill | Description |
  143. |-------|-------------|
  144. | [cosmos-dbt-core](./skills/cosmos-dbt-core/) | Run dbt Core projects as Airflow DAGs using [Astronomer Cosmos](https://github.com/astronomer/astronomer-cosmos) |
  145. | [cosmos-dbt-fusion](./skills/cosmos-dbt-fusion/) | Run dbt Fusion projects with Cosmos (Snowflake/Databricks only) |
  146. #### Migration
  147. | Skill | Description |
  148. |-------|-------------|
  149. | [migrating-airflow-2-to-3](./skills/migrating-airflow-2-to-3/) | Migrate DAGs from Airflow 2.x to 3.x |
  150. ## Why Astro?
  151. Astro is Astronomer's managed Airflow platform. It's optional, but a good fit if you want managed deployments, built-in alerting, and centralized observability across environments. If you run open-source Airflow, everything in this repo still applies—you'll just configure your own Airflow URL and infrastructure.
  152. ### User Journeys
  153. #### Data Analysis Flow
  154. ```mermaid
  155. flowchart LR
  156. init["/astronomer-data:warehouse-init"] --> analyzing["/astronomer-data:analyzing-data"]
  157. analyzing --> profiling["/astronomer-data:profiling-tables"]
  158. analyzing --> freshness["/astronomer-data:checking-freshness"]
  159. ```
  160. 1. **Initialize** (`/astronomer-data:warehouse-init`) - One-time setup to generate `warehouse.md` with schema metadata
  161. 2. **Analyze** (`/astronomer-data:analyzing-data`) - Answer business questions with SQL
  162. 3. **Profile** (`/astronomer-data:profiling-tables`) - Deep dive into specific tables for statistics and quality
  163. 4. **Check freshness** (`/astronomer-data:checking-freshness`) - Verify data is up to date before using
  164. #### DAG Development Flow
  165. For open-source Airflow, use Docker Compose for local dev and the Helm chart for production (see `deploying-airflow`) instead of Astro setup skills.
  166. ```mermaid
  167. flowchart LR
  168. setup["/astronomer-data:setting-up-astro-project"] --> authoring["/astronomer-data:authoring-dags"]
  169. setup --> env["/astronomer-data:managing-astro-local-env"]
  170. authoring --> testing["/astronomer-data:testing-dags"]
  171. testing --> debugging["/astronomer-data:debugging-dags"]
  172. ```
  173. 1. **Setup** (`/astronomer-data:setting-up-astro-project`) - Initialize project structure and dependencies
  174. 2. **Environment** (`/astronomer-data:managing-astro-local-env`) - Start/stop local Airflow for development
  175. 3. **Author** (`/astronomer-data:authoring-dags`) - Write DAG code following best practices
  176. 4. **Test** (`/astronomer-data:testing-dags`) - Run DAGs and fix issues iteratively
  177. 5. **Debug** (`/astronomer-data:debugging-dags`) - Deep investigation for complex failures
  178. ### Airflow CLI (`af`)
  179. The `af` command-line tool lets you interact with Airflow directly from your terminal. Install it with:
  180. ```bash
  181. uvx --from astro-airflow-mcp af --help
  182. ```
  183. For frequent use, add an alias to your shell config (`~/.bashrc` or `~/.zshrc`):
  184. ```bash
  185. alias af='uvx --from astro-airflow-mcp af'
  186. ```
  187. Then use it for quick operations like `af health`, `af dags list`, or `af runs trigger <dag_id>`.
  188. See the [full CLI documentation](./astro-airflow-mcp/README.md#airflow-cli-tool) for all commands and instance management.
  189. > **Telemetry:** The `af` CLI collects anonymous usage telemetry to help improve the tool. Only the command name is collected (e.g., `dags list`), never the arguments or their values. Opt out with `af telemetry disable`.
  190. ## Configuration
  191. ### Warehouse Connections
  192. Configure data warehouse connections at `~/.astro/agents/warehouse.yml`:
  193. ```yaml
  194. my_warehouse:
  195. type: snowflake
  196. account: ${SNOWFLAKE_ACCOUNT}
  197. user: ${SNOWFLAKE_USER}
  198. auth_type: private_key
  199. private_key_path: ~/.ssh/snowflake_key.p8
  200. private_key_passphrase: ${SNOWFLAKE_PRIVATE_KEY_PASSPHRASE}
  201. warehouse: COMPUTE_WH
  202. role: ANALYST
  203. query_tag: claude-code
  204. databases:
  205. - ANALYTICS
  206. - RAW
  207. ```
  208. > [!IMPORTANT]
  209. > **How the `databases` list works:**
  210. > - **Optional for most connectors** (`snowflake`, `postgres`, `bigquery`) but **required for `sqlalchemy`**
  211. > - **For schema discovery** (`/astronomer-data:warehouse-init`): Determines which databases are scanned and included in the generated `.astro/warehouse.md`. Only databases listed here will be discovered. If omitted, no schema discovery will occur.
  212. > - **For query execution** (`/astronomer-data:analyzing-data`): The **first database** in the list becomes the default database context for the connection, but does NOT restrict which databases you can query. You can still access any database you have permissions for using fully-qualified table names (e.g., `OTHER_DB.SCHEMA.TABLE`).
  213. >
  214. > **Example:** If you configure `databases: [ANALYTICS, RAW]`:
  215. > - `ANALYTICS` becomes the default database for queries
  216. > - You can still query `PROD` with `SELECT * FROM PROD.PUBLIC.USERS`
  217. > - Only `ANALYTICS` and `RAW` will appear in warehouse schema documentation (run `/astronomer-data:warehouse-init --refresh` after adding `PROD` to include it)
  218. > [!NOTE]
  219. > The `account` field requires your Snowflake **account identifier** (e.g., `orgname-accountname` or `xy12345.us-east-1`), not your account name. Find this in your Snowflake console under Admin > Accounts.
  220. Store credentials in `~/.astro/agents/.env`:
  221. ```bash
  222. SNOWFLAKE_ACCOUNT=myorg-myaccount # Use your Snowflake account identifier (format: orgname-accountname or accountname.region)
  223. SNOWFLAKE_USER=myuser
  224. SNOWFLAKE_PRIVATE_KEY_PASSPHRASE=your-passphrase-here # Only required if using an encrypted private key
  225. ```
  226. **Supported databases:**
  227. | Type | Package | Description |
  228. |------|---------|-------------|
  229. | `snowflake` | Built-in | Snowflake Data Cloud |
  230. | `postgres` | Built-in | PostgreSQL |
  231. | `bigquery` | Built-in | Google BigQuery |
  232. | `sqlalchemy` | Any SQLAlchemy driver | Auto-detects packages for 25+ databases (see below) |
  233. <details>
  234. <summary>Auto-detected SQLAlchemy databases</summary>
  235. The connector automatically installs the correct driver packages for:
  236. | Database | Dialect URL |
  237. |----------|-------------|
  238. | PostgreSQL | `postgresql://` or `postgres://` |
  239. | MySQL | `mysql://` or `mysql+pymysql://` |
  240. | MariaDB | `mariadb://` |
  241. | SQLite | `sqlite:///` |
  242. | SQL Server | `mssql+pyodbc://` |
  243. | Oracle | `oracle://` |
  244. | Redshift | `redshift://` |
  245. | Snowflake | `snowflake://` |
  246. | BigQuery | `bigquery://` |
  247. | DuckDB | `duckdb:///` |
  248. | Trino | `trino://` |
  249. | ClickHouse | `clickhouse://` |
  250. | CockroachDB | `cockroachdb://` |
  251. | Databricks | `databricks://` |
  252. | Amazon Athena | `awsathena://` |
  253. | Cloud Spanner | `spanner://` |
  254. | Teradata | `teradata://` |
  255. | Vertica | `vertica://` |
  256. | SAP HANA | `hana://` |
  257. | IBM Db2 | `db2://` |
  258. For unlisted databases, install the driver manually and use standard SQLAlchemy URLs.
  259. </details>
  260. <details>
  261. <summary>Example configurations</summary>
  262. ```yaml
  263. # PostgreSQL
  264. my_postgres:
  265. type: postgres
  266. host: localhost
  267. port: 5432
  268. user: analyst
  269. password: ${POSTGRES_PASSWORD}
  270. database: analytics
  271. application_name: claude-code
  272. # BigQuery
  273. my_bigquery:
  274. type: bigquery
  275. project: my-gcp-project
  276. credentials_path: ~/.config/gcloud/service_account.json
  277. location: US
  278. labels:
  279. team: data-eng
  280. env: prod
  281. # SQLAlchemy (any supported database)
  282. my_duckdb:
  283. type: sqlalchemy
  284. url: duckdb:///path/to/analytics.duckdb
  285. databases: [main]
  286. # SQLAlchemy with connect_args (passed to the DBAPI driver)
  287. my_pg_sqlalchemy:
  288. type: sqlalchemy
  289. url: postgresql://${PG_USER}:${PG_PASSWORD}@localhost/analytics
  290. databases: [analytics]
  291. connect_args:
  292. application_name: claude-code
  293. # Redshift (via SQLAlchemy)
  294. my_redshift:
  295. type: sqlalchemy
  296. url: redshift+redshift_connector://${REDSHIFT_USER}:${REDSHIFT_PASSWORD}@${REDSHIFT_HOST}:5439/${REDSHIFT_DATABASE}
  297. databases: [my_database]
  298. ```
  299. </details>
  300. ### Airflow
  301. The Airflow MCP auto-discovers your project when you run Claude Code from an Airflow project directory (contains `airflow.cfg` or `dags/` folder).
  302. For remote instances, set environment variables:
  303. | Variable | Description |
  304. |----------|-------------|
  305. | `AIRFLOW_API_URL` | Airflow webserver URL |
  306. | `AIRFLOW_USERNAME` | Username |
  307. | `AIRFLOW_PASSWORD` | Password |
  308. | `AIRFLOW_AUTH_TOKEN` | Bearer token (alternative to username/password) |
  309. ## Usage
  310. Skills are invoked automatically based on what you ask. You can also invoke them directly with `/astronomer-data:<skill-name>`.
  311. ### Getting Started
  312. 1. **Initialize your warehouse** (recommended first step):
  313. ```
  314. /astronomer-data:warehouse-init
  315. ```
  316. This generates `.astro/warehouse.md` with schema metadata for faster queries.
  317. 2. **Ask questions naturally**:
  318. - "What tables contain customer data?"
  319. - "Show me revenue trends by product"
  320. - "Create a DAG that loads data from S3 to Snowflake daily"
  321. - "Why did my etl_pipeline DAG fail yesterday?"
  322. ## Development
  323. See [CLAUDE.md](./CLAUDE.md) for plugin development guidelines.
  324. ### Local Development Setup
  325. ```bash
  326. # Clone the repo
  327. git clone https://github.com/astronomer/agents.git
  328. cd agents
  329. # Test with local plugin
  330. claude --plugin-dir .
  331. # Or install from local marketplace
  332. claude plugin marketplace add .
  333. claude plugin install astronomer-data@astronomer
  334. ```
  335. ### Adding Skills
  336. Create a new skill in `skills/<name>/SKILL.md` with YAML frontmatter:
  337. ```yaml
  338. ---
  339. name: my-skill
  340. description: When to invoke this skill
  341. ---
  342. # Skill instructions here...
  343. ```
  344. After adding skills, reinstall the plugin:
  345. ```bash
  346. claude plugin uninstall astronomer-data@astronomer && claude plugin marketplace update && claude plugin install astronomer-data@astronomer
  347. ```
  348. ## Troubleshooting
  349. ### Common Issues
  350. | Issue | Solution |
  351. |-------|----------|
  352. | Skills not appearing | Reinstall plugin: `claude plugin uninstall astronomer-data@astronomer && claude plugin marketplace update && claude plugin install astronomer-data@astronomer` |
  353. | Installed as `data@astronomer` (old name) | Uninstall old name and reinstall: `claude plugin uninstall data@astronomer && claude plugin marketplace update && claude plugin install astronomer-data@astronomer` |
  354. | Warehouse connection errors | Check credentials in `~/.astro/agents/.env` and connection config in `warehouse.yml` |
  355. | Airflow not detected | Ensure you're running from a directory with `airflow.cfg` or a `dags/` folder |
  356. ## Contributing
  357. Contributions welcome! Please read our [Code of Conduct](./CODE_OF_CONDUCT.md) and [Contributing Guide](./CONTRIBUTING.md) before getting started.
  358. ## Roadmap
  359. Skills we're likely to build:
  360. **DAG Operations**
  361. - CI/CD pipelines for DAG deployment
  362. - Performance optimization and tuning
  363. - Monitoring and alerting setup
  364. - Data quality and validation workflows
  365. **Astronomer Open Source**
  366. - [DAG Factory](https://github.com/astronomer/dag-factory) - Generate DAGs from YAML
  367. - Other open source projects we maintain
  368. **Conference Learnings**
  369. - Reviewing talks from Airflow Summit, Coalesce, Data Council, and other conferences to extract reusable skills and patterns
  370. **Broader Data Practitioner Skills**
  371. - Churn prediction, data modeling, ML training, and other workflows that span DE/DS/analytics roles
  372. **Don't see a skill you want? [Open an issue](https://github.com/astronomer/agents/issues) or submit a PR!**
  373. ## License
  374. Apache 2.0
  375. ---
  376. Made with :heart: by Astronomer
  377. <img referrerpolicy="no-referrer-when-downgrade" src="https://static.scarf.sh/a.png?x-pxid=f1c1d270-334e-45ec-b711-77385036cff9" />

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.