microsoft/hve-core
Publicmirrored fromhttps://github.com/microsoft/hve-coreAvailable
collections/data-science.collection.md
12lines · modecode
| 1 | Generate data specifications, Jupyter notebooks, and Streamlit dashboards from natural language descriptions. Evaluate AI-powered data systems against Responsible AI standards. This collection includes specialized agents for data science workflows in Python and RAI assessment. |
| 2 | |
| 3 | > [!CAUTION] |
| 4 | > The RAI agents and prompts in this collection are **assistive tools only**. They do not replace qualified human review, organizational RAI review boards, or regulatory compliance programs. All AI-generated RAI artifacts **must** be reviewed and validated by qualified professionals before use. AI outputs may contain inaccuracies, miss critical risks, or produce recommendations that are incomplete or inappropriate for your context. |
| 5 | |
| 6 | This collection includes agents for: |
| 7 | |
| 8 | - **Data Specification Generation** — Create structured data schemas and specifications from requirements |
| 9 | - **Jupyter Notebook Generation** — Build data analysis notebooks with visualizations and documentation |
| 10 | - **Streamlit Dashboard Generation** — Create interactive dashboards from data sources |
| 11 | - **Dashboard Testing** — Comprehensive test suites for Streamlit applications |
| 12 | - **RAI Planner** — Responsible AI assessment with security model analysis, impact assessment, and dual-format backlog handoff |
| 13 | |