Skip to main content
Archived

This project has been archived by its maintainers, and is no longer receiving any updates.

vulcan-skills

AI agent skills for the Vulcan data platform.

Teach any AI agent (Cursor, Claude, GitHub Copilot) how to work with Vulcan correctly — writing models, using the CLI, following best practices.


Install

pip install vulcan-skills

Usage

→ Full Usage Guide — Complete guide with examples, best practices, and troubleshooting

Install a skill into your project

vulcan skills install data-quality
vulcan skills install cli-commands sql-models incremental-patterns

Skills land as markdown files in .vulcan/skills/ — your AI agent reads them automatically.

List available skills

vulcan skills list

See what's active in your project

vulcan skills show

Add your own business rules

vulcan skills create acme-naming-rules
# Opens editor — write your rules in markdown
# Commit .vulcan/skills/acme-naming-rules.md to share with your team

Remove a skill

vulcan skills remove data-quality

Update installed skills

vulcan skills update

Available Skills

Skill What It Teaches
cli-commands All Vulcan CLI commands with examples
sql-models How to write SQL models in Vulcan
python-models How to write Python models
incremental-patterns Incremental model patterns and best practices
data-quality Writing checks, audits, and tests
model-properties Model properties and configuration
semantics How to define semantic layers
macros Writing and using Jinja macros
bigquery BigQuery-specific patterns
snowflake Snowflake-specific patterns
databricks Databricks-specific patterns

Project Structure After Install

your-vulcan-project/
├── models/
├── checks/
├── vulcan.yaml
└── .vulcan/
    └── skills/
        ├── data-quality.md          ← public skill (from this package)
        ├── incremental-patterns.md  ← public skill (from this package)
        └── acme-naming-rules.md     ← your custom skill (stays in your repo)

Agent Setup

Cursor

Add to your .cursorrules:

Before helping with any Vulcan task, read all files in .vulcan/skills/

Claude (MCP)

Vulcan's MCP server exposes .vulcan/skills/ to Claude automatically.

Any other agent

Point your agent's context to read .vulcan/skills/*.md before every Vulcan-related task.


Contributing

Skills live in skills/ as plain markdown files. To contribute:

  1. Fork this repo
  2. Add or improve a skill in skills/
  3. Open a pull request

See CONTRIBUTING.md for guidelines.


License

Apache 2.0

Metadata

Release files for vulcan-skills 0.2.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for vulcan-skills 0.2.0
File Size Uploaded Provenance
vulcan_skills-0.2.0.tar.gz 19.8 kB Without provenance Details

Built distribution (wheel)

Table of built distributions (wheels) for vulcan-skills 0.2.0
File Interpreter ABI Platform
vulcan_skills-0.2.0-py3-none-any.whl Python 3 none any Details

Total release size: 51.1 kB

Release files / vulcan_skills-0.2.0.tar.gz

Download URL vulcan_skills-0.2.0.tar.gz
Size 19.8 kB
Tags Source
SHA-256 checksum
How to use checksums
ad210559fa997f17cf560c067e0a4e1851785ebf7120999b7baa98cf7ddeffef
BLAKE2b-256 checksum
How to use checksums
edbe98b348452324f74ee02e05a74ba7626afdb0b2b05e85df2011885cb0b394
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.3

Release files / vulcan_skills-0.2.0-py3-none-any.whl

Download URL vulcan_skills-0.2.0-py3-none-any.whl
Size 31.3 kB
Tags Python 3
SHA-256 checksum
How to use checksums
df8605e11a62150ffdeb0eeb404b9a9a1b6dea1e4cc4f6145f8f27960fa6d04d
BLAKE2b-256 checksum
How to use checksums
1836da5d5b09a283ca27fdc017e02efb16fcd270c20514b5112be274d4bbda30
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.14.3

Security for vulcan-skills 0.2.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page