AI Data Compass
AI Data Compass provides guidelines and automation for AI-assisted work in data repositories.
-
Guidelines. Repository instructions guide coding agents on privacy, development practices, testing, and documentation.
-
Automation. Reusable skills and scripts automate recurring developer tasks so teams can avoid repeating manual checks.
Installation
The CLI supports Python 3.9 and newer. Install the package with pip, then run init to install assets in your repository:
python -m pip install ai-data-compass
ai-data-compass init --assets complete
The recommended complete selection installs the agent instructions and all available skills. Run ai-data-compass init without --assets to choose interactively; leaving the selection empty chooses complete.
Every installation includes the base documentation, license, and third-party notices. The installer creates missing files and preserves existing files whose content and required permissions already match. If another existing target file differs, the installer refuses that asset instead of overwriting the file; it can continue with other selected assets and exits with a nonzero status.
When AGENTS.md already contains different instructions, the installer asks permission to create AGENTS-ai-data-compass.md (or the next available numbered name) and add a reference to it in the existing file; declining skips the agent-instructions asset. When a skill directory name is already occupied by different content, the installer uses <skill-name>-ai-data-compass (or a numbered suffix) and updates the installed references to use that name.
Available assets
| Name | Description | How to use |
|---|---|---|
agents.md |
AGENTS.md guidance and host adapters for supported coding agents. Tested with Claude and Codex |
Your agent should import and follow AGENTS.md; instructions already defined by the project take precedence if they conflict. |
security_audit |
Security-audit skill with its scanner, references, tests, and Codex and Claude adapters. | Ask your agent to run the security-audit skill and review its metadata-only findings. |
Documentation
Project guidance, workflows, and planning references:
- Central AI agent instructions
- Documentation index
- Distribution and installation
- AI agent skills
- Security and privacy
- Testing guidance
- Task completion checklist
- Internal pending features backlog
License
This project is licensed under the MIT License.
1 maintainer
Metadata
1 maintainer
Release files for ai-data-compass 0.0.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | |
|---|---|---|---|---|
| ai_data_compass-0.0.1.tar.gz | 51.9 kB | With provenance | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| ai_data_compass-0.0.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 106.6 kB
Release files / ai_data_compass-0.0.1.tar.gz
| Download URL | ai_data_compass-0.0.1.tar.gz |
|---|---|
| Size | 51.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
9ff6ab119015cbfdcba0ef35c01432d00eacf1bb480dad9f39028f946a34ca16
|
|
BLAKE2b-256 checksum How to use checksums |
80d3b4f859a9ef0aac84435f15eb867206caa6c97689f26ca690eee0f2080692
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 23, 2026.
Transparency logRelease files / ai_data_compass-0.0.1-py3-none-any.whl
| Download URL | ai_data_compass-0.0.1-py3-none-any.whl |
|---|---|
| Size | 54.7 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
35f4ea490cae92a4f6d5deb4dec814c6489d1e7e908b1783f03da02f53de541d
|
|
BLAKE2b-256 checksum How to use checksums |
16165baa37496baf629d9fe0a3c792fa75261b442431093f8567afa92b41ee63
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
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.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 23, 2026.
Transparency logSecurity for ai-data-compass 0.0.1
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.
Full provenance
All 2 files in this release have been uploaded with provenance metadata.
Attestation for ai_data_compass-0.0.1.tar.gz
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Sep 23, 2026.
Transparency logA 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.
