microsoft/hve-core
Publicmirrored fromhttps://github.com/microsoft/hve-coreAvailable
plugins/data-science/README.md
101lines · modecode
| 1 | <!-- markdownlint-disable-file --> |
| 2 | # Data Science |
| 3 | |
| 4 | Evaluation dataset creation, 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 critical risk 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 | <!-- BEGIN AUTO-GENERATED ARTIFACTS --> |
| 17 | |
| 18 | ### Chat Agents |
| 19 | |
| 20 | | Name | Description | |
| 21 | |------------------------------|-----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 22 | | **eval-dataset-creator** | Creates evaluation datasets and documentation for AI agent testing using interview-driven data curation | |
| 23 | | **gen-data-spec** | Generate comprehensive data dictionaries, machine-readable data profiles, and objective summaries for downstream analysis (EDA notebooks, dashboards) through guided discovery | |
| 24 | | **gen-jupyter-notebook** | Create structured exploratory data analysis Jupyter notebooks from available data sources and generated data dictionaries | |
| 25 | | **gen-streamlit-dashboard** | Develop a multi-page Streamlit dashboard | |
| 26 | | **rai-planner** | Responsible AI assessment planning agent with 6-phase conversational workflow. Guides planning against NIST AI RMF 1.0 as the default evaluation framework. Prepares RAI security model, impact assessment, control surface catalog, and dual-format backlog handoff. | |
| 27 | | **researcher-subagent** | Research subagent using search tools, read tools, fetch web page, github repo, and mcp tools | |
| 28 | | **test-streamlit-dashboard** | Automated testing for Streamlit dashboards using Playwright with issue tracking and reporting | |
| 29 | |
| 30 | ### Prompts |
| 31 | |
| 32 | | Name | Description | |
| 33 | |---------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------| |
| 34 | | **rai-capture** | Initiate responsible AI assessment planning from existing knowledge using the RAI Planner agent in capture mode | |
| 35 | | **rai-plan-from-prd** | Initiate responsible AI assessment planning from PRD/BRD artifacts using the RAI Planner agent in from-prd mode | |
| 36 | | **rai-plan-from-security-plan** | Initiate responsible AI assessment planning from a completed Security Plan using the RAI Planner agent in from-security-plan mode (recommended) | |
| 37 | | **synth-data-generate** | Generate comprehensive synthetic data for any specified subject with realistic patterns and relationships | |
| 38 | |
| 39 | ### Instructions |
| 40 | |
| 41 | | Name | Description | |
| 42 | |------------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 43 | | **coding-standards/python-script** | Instructions for Python scripting implementation | |
| 44 | | **coding-standards/uv-projects** | Create and manage Python virtual environments using uv commands | |
| 45 | | **rai-planning/rai-backlog-handoff** | RAI review and backlog handoff for Phase 6: review rubric, RAI review summary, dual-format backlog generation | |
| 46 | | **rai-planning/rai-capture-coaching** | Exploration-first questioning techniques for RAI capture mode adapted from Design Thinking research methods | |
| 47 | | **rai-planning/rai-identity** | RAI Planner identity, 6-phase orchestration, state management, and session recovery | |
| 48 | | **rai-planning/rai-impact-assessment** | RAI impact assessment for Phase 5: control surface taxonomy, evidence register, tradeoff documentation, and work item generation | |
| 49 | | **rai-planning/rai-risk-classification** | Risk classification screening for Phase 2: prohibited uses gate, risk indicator assessment, and depth tier assignment | |
| 50 | | **rai-planning/rai-security-model** | RAI security model analysis for Phase 4: AI STRIDE extensions, dual threat IDs, ML STRIDE matrix, and security model merge protocol | |
| 51 | | **rai-planning/rai-standards** | Embedded RAI standards for Phase 3: NIST AI RMF 1.0 trustworthiness characteristics, subcategory mappings, and framework isolation architecture | |
| 52 | | **shared/hve-core-location** | 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. | |
| 53 | |
| 54 | <!-- END AUTO-GENERATED ARTIFACTS --> |
| 55 | |
| 56 | ## Install |
| 57 | |
| 58 | ```bash |
| 59 | copilot plugin install data-science@hve-core |
| 60 | ``` |
| 61 | |
| 62 | ## Agents |
| 63 | |
| 64 | | Agent | Description | |
| 65 | |--------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 66 | | eval-dataset-creator | Creates evaluation datasets and documentation for AI agent testing using interview-driven data curation | |
| 67 | | gen-data-spec | Generate comprehensive data dictionaries, machine-readable data profiles, and objective summaries for downstream analysis (EDA notebooks, dashboards) through guided discovery | |
| 68 | | gen-jupyter-notebook | Create structured exploratory data analysis Jupyter notebooks from available data sources and generated data dictionaries | |
| 69 | | gen-streamlit-dashboard | Develop a multi-page Streamlit dashboard | |
| 70 | | test-streamlit-dashboard | Automated testing for Streamlit dashboards using Playwright with issue tracking and reporting | |
| 71 | | rai-planner | Responsible AI assessment planning agent with 6-phase conversational workflow. Guides planning against NIST AI RMF 1.0 as the default evaluation framework. Prepares RAI security model, impact assessment, control surface catalog, and dual-format backlog handoff. - Brought to you by microsoft/hve-core | |
| 72 | | researcher-subagent | Research subagent using search tools, read tools, fetch web page, github repo, and mcp tools | |
| 73 | |
| 74 | ## Commands |
| 75 | |
| 76 | | Command | Description | |
| 77 | |-----------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------| |
| 78 | | rai-capture | Initiate responsible AI assessment planning from existing knowledge using the RAI Planner agent in capture mode | |
| 79 | | rai-plan-from-prd | Initiate responsible AI assessment planning from PRD/BRD artifacts using the RAI Planner agent in from-prd mode | |
| 80 | | rai-plan-from-security-plan | Initiate responsible AI assessment planning from a completed Security Plan using the RAI Planner agent in from-security-plan mode (recommended) | |
| 81 | | synth-data-generate | Generate comprehensive synthetic data for any specified subject with realistic patterns and relationships | |
| 82 | |
| 83 | ## Instructions |
| 84 | |
| 85 | | Instruction | Description | |
| 86 | |--------------------------------------|-------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------| |
| 87 | | python-script.instructions | Instructions for Python scripting implementation - Brought to you by microsoft/hve-core | |
| 88 | | uv-projects.instructions | Create and manage Python virtual environments using uv commands | |
| 89 | | rai-backlog-handoff.instructions | RAI review and backlog handoff for Phase 6: review rubric, RAI review summary, dual-format backlog generation | |
| 90 | | rai-identity.instructions | RAI Planner identity, 6-phase orchestration, state management, and session recovery - Brought to you by microsoft/hve-core | |
| 91 | | rai-impact-assessment.instructions | RAI impact assessment for Phase 5: control surface taxonomy, evidence register, tradeoff documentation, and work item generation - Brought to you by microsoft/hve-core | |
| 92 | | rai-risk-classification.instructions | Risk classification screening for Phase 2: prohibited uses gate, risk indicator assessment, and depth tier assignment - Brought to you by microsoft/hve-core | |
| 93 | | 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 - Brought to you by microsoft/hve-core | |
| 94 | | rai-standards.instructions | Embedded RAI standards for Phase 3: NIST AI RMF 1.0 trustworthiness characteristics, subcategory mappings, and framework isolation architecture - Brought to you by microsoft/hve-core | |
| 95 | | 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 | |
| 96 | | 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. | |
| 97 | |
| 98 | --- |
| 99 | |
| 100 | > Source: [microsoft/hve-core](https://github.com/microsoft/hve-core) |
| 101 | |
| 102 | |