microsoft/hve-core
Publicmirrored fromhttps://github.com/microsoft/hve-coreAvailable
plugins/data-science/README.md
67lines · modecode
| 1 | <!-- markdownlint-disable-file --> |
| 2 | # Data Science |
| 3 | |
| 4 | Data specification generation, Jupyter notebooks, and Streamlit dashboards |
| 5 | |
| 6 | > [!CAUTION] |
| 7 | > This collection includes RAI (Responsible AI) agents and prompts that are **assistive tools only**. They do not replace qualified responsible AI review, ethics board oversight, or established organizational RAI governance processes. All AI-generated RAI assessments, impact analyses, and recommendations **must** be reviewed and validated by qualified professionals before use. AI outputs may contain inaccuracies, miss sensitive use categories, or produce recommendations that are incomplete or inappropriate for your context. |
| 8 | |
| 9 | ## Overview |
| 10 | |
| 11 | 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. |
| 12 | |
| 13 | > [!CAUTION] |
| 14 | > 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. |
| 15 | |
| 16 | This collection includes agents for: |
| 17 | |
| 18 | - **Data Specification Generation** — Create structured data schemas and specifications from requirements |
| 19 | - **Jupyter Notebook Generation** — Build data analysis notebooks with visualizations and documentation |
| 20 | - **Streamlit Dashboard Generation** — Create interactive dashboards from data sources |
| 21 | - **Dashboard Testing** — Comprehensive test suites for Streamlit applications |
| 22 | - **RAI Planner** — Responsible AI assessment with sensitive uses screening, security model analysis, impact assessment, and dual-format backlog handoff |
| 23 | |
| 24 | ## Install |
| 25 | |
| 26 | ```bash |
| 27 | copilot plugin install data-science@hve-core |
| 28 | ``` |
| 29 | |
| 30 | ## Agents |
| 31 | |
| 32 | | Agent | Description | |
| 33 | |--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 34 | | gen-data-spec | Generate comprehensive data dictionaries, machine-readable data profiles, and objective summaries for downstream analysis (EDA notebooks, dashboards) through guided discovery | |
| 35 | | gen-jupyter-notebook | Create structured exploratory data analysis Jupyter notebooks from available data sources and generated data dictionaries | |
| 36 | | gen-streamlit-dashboard | Develop a multi-page Streamlit dashboard | |
| 37 | | test-streamlit-dashboard | Automated testing for Streamlit dashboards using Playwright with issue tracking and reporting | |
| 38 | | rai-planner | Responsible AI assessment agent with 6-phase conversational workflow. Evaluates AI systems against Microsoft RAI Standard v2 and NIST AI RMF 1.0. Produces sensitive uses screening, RAI security model, impact assessment, control surface catalog, and dual-format backlog handoff. - Brought to you by microsoft/hve-core | |
| 39 | | researcher-subagent | Research subagent using search tools, read tools, fetch web page, github repo, and mcp tools | |
| 40 | |
| 41 | ## Commands |
| 42 | |
| 43 | | Command | Description | |
| 44 | |-----------------------------|------------------------------------------------------------------------------------------------------------------------------------------| |
| 45 | | rai-capture | Initiate a responsible AI assessment from existing knowledge using the RAI Planner agent in capture mode | |
| 46 | | rai-plan-from-prd | Initiate a responsible AI assessment from PRD/BRD artifacts using the RAI Planner agent in from-prd mode | |
| 47 | | rai-plan-from-security-plan | Initiate a responsible AI assessment from a completed Security Plan using the RAI Planner agent in from-security-plan mode (recommended) | |
| 48 | |
| 49 | ## Instructions |
| 50 | |
| 51 | | Instruction | Description | |
| 52 | |------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 53 | | python-script.instructions | Instructions for Python scripting implementation - Brought to you by microsoft/hve-core | |
| 54 | | uv-projects.instructions | Create and manage Python virtual environments using uv commands | |
| 55 | | rai-backlog-handoff.instructions | RAI review and backlog handoff for Phase 6: review rubric, RAI scorecard, dual-format backlog generation | |
| 56 | | rai-identity.instructions | RAI Planner identity, 6-phase orchestration, state management, and session recovery - Brought to you by microsoft/hve-core | |
| 57 | | rai-impact-assessment.instructions | RAI impact assessment for Phase 5: control surface taxonomy, evidence register, tradeoff documentation, and work item generation | |
| 58 | | rai-security-model.instructions | RAI security model analysis for Phase 4: AI STRIDE extensions, dual threat IDs, ML STRIDE matrix, and security model merge protocol | |
| 59 | | rai-sensitive-uses.instructions | Sensitive Uses assessment for Phase 2: screening categories, restricted uses gate, and depth tier assignment | |
| 60 | | rai-standards.instructions | Embedded RAI standards for Phase 3: Microsoft RAI Standard v2 principles and NIST AI RMF subcategory mappings | |
| 61 | | rai-capture-coaching.instructions | Exploration-first questioning techniques for RAI capture mode adapted from Design Thinking research methods - Brought to you by microsoft/hve-core | |
| 62 | | hve-core-location.instructions | Important: hve-core is the repository containing this instruction file; Guidance: if a referenced prompt, instructions, agent, or script is missing in the current directory, fall back to this hve-core location by walking up this file's directory tree. | |
| 63 | |
| 64 | --- |
| 65 | |
| 66 | > Source: [microsoft/hve-core](https://github.com/microsoft/hve-core) |
| 67 | |
| 68 | |