dagster-io / skills
★ 179A skill package that teaches your agent 4 capabilities — every one documented and browsable below, no GitHub required · by dagster-io.
Each skill below is one capability this package teaches your agent. Install the whole package, or open a skill to install just that one.
Expert guidance for working with Dagster and the dg CLI. ALWAYS use before doing any task that requires
50 files — installable on its own
Expert guidance for Dagster projects, asset definitions, and dg CLI workflows. Provides deep knowledge of Dagster concepts (assets, components, schedules, sensors, jobs) and helps with project structure, debugging, and codebase navigation Covers the dg CLI for common tasks: creating projects, scaffolding definitions, listing assets, launching runs, and exploring project structure Includes guidance on automation approaches (schedules, sensors, declarative automation) and integration patterns...
50 files — installable on its own
Opinionated production Python standards with automatic version detection (3.10-3.13). Use when
24 files — installable on its own
Opinionated production Python standards with automatic version detection (3.10-3.13). Use when
24 files — installable on its own
Dagster Skills
AI assistant skills for building workflows and data pipelines using Dagster.
Compatible with Claude Code, Cursor, OpenCode, OpenAI Codex, Pi, and other Agent Skills-compatible tools.
Installation
Claude Code
Install using the Claude plugin marketplace:
/plugin marketplace add dagster-io/skills
/plugin install dagster-expert@dagster
/dagster-expert "What's an asset?"Using npx skills
Install using the npx skills command-line:
npx skills add dagster-io/skillsManual Installation
<details> <summary>See full instructions...</summary>Clone the repository and copy skills to your tool's skills directory:
OpenCode:
git clone https://github.com/dagster-io/skills.git
cp -r skills/skills/* ~/.config/opencode/skill/OpenAI Codex:
git clone https://github.com/dagster-io/skills.git
cp -r skills/skills/* ~/.codex/skills/Pi Agent:
git clone https://github.com/dagster-io/skills.git
cp -r skills/skills/* ~/.pi/agent/skills/Skills
dagster-expert
Expert guidance for building production-quality Dagster projects, covering CLI commands, asset patterns, automation strategies, and implementation workflows.
What you can do:
- Create and scaffold projects, assets, schedules, and sensors
- Understand asset patterns (dependencies, partitions, multi-assets, metadata)
- Implement automation (declarative automation, schedules, sensors)
- Use CLI commands (launch, list, check, scaffold, logs)
- Design project structure and configure environments
- Follow implementation workflows and best practices
- Debug issues and validate project configuration
Example prompts:
Create a new Dagster project called analytics
How do I scaffold a new asset?
Show me how to set up declarative automation
What's the proper way to partition my assets?
Help me debug why my materialization failed
How should I structure my project for multiple pipelines?
Launch all assets tagged with priority=highdignified-python
Production-quality Python coding standards for modern Python.
Use for general Python code quality, not Dagster-specific patterns.
What's included:
- Modern type syntax (list[str], str | None)
- LBYL exception handling patterns
- Pathlib operations
- Python version-specific features (3.10-3.13)
- CLI patterns (Click, argparse)
- Advanced typing patterns
- Interface design (ABC, Protocol)
- API design principles
Example questions:
Is this good Python code?
How should I annotate this function?
What's the difference between LBYL and EAFP?
Should I use pathlib or os.path?Contributing
See CONTRIBUTING.md.
<div align="center"> <img alt="dagster logo" src="https://github.com/user-attachments/assets/6fbf8876-09b7-4f4a-8778-8c0bb00c5237" width="auto" height="16px"> </div>Install the whole package (4 skills):
npx skills add https://github.com/dagster-io/skillsOr install a single skill:
npx skills add https://github.com/dagster-io/skills --skill <name>Pick the skill name from the Skills tab — each entry there installs independently.