HVE Core - Data Science
Data specification generation, Jupyter notebooks, and Streamlit dashboards
Generate data specifications, Jupyter notebooks, and Streamlit dashboards from natural language descriptions. This collection includes specialized agents for data science workflows in Python.
This collection includes agents for:
- Data Specification Generation — Create structured data schemas and specifications from requirements
- Jupyter Notebook Generation — Build data analysis notebooks with visualizations and documentation
- Streamlit Dashboard Generation — Create interactive dashboards from data sources
- Dashboard Testing — Comprehensive test suites for Streamlit applications
Included Artifacts
Chat Agents
| Name |
Description |
| gen-data-spec |
Generate comprehensive data dictionaries, machine-readable data profiles, and objective summaries for downstream analysis (EDA notebooks, dashboards) through guided discovery |
| gen-jupyter-notebook |
Create structured exploratory data analysis Jupyter notebooks from available data sources and generated data dictionaries |
| gen-streamlit-dashboard |
Develop a multi-page Streamlit dashboard |
| memory |
Conversation memory persistence for session continuity |
| pr-review |
Comprehensive Pull Request review assistant ensuring code quality, security, and convention compliance |
| prompt-builder |
Prompt engineering assistant with phase-based workflow for creating and validating prompts, agents, and instructions files |
| rpi-agent |
Autonomous RPI orchestrator dispatching task-* agents through Research → Plan → Implement → Review → Discover phases |
| task-implementor |
Executes implementation plans from .copilot-tracking/plans with progressive tracking and change records |
| task-planner |
Implementation planner for creating actionable implementation plans |
| task-researcher |
Task research specialist for comprehensive project analysis |
| task-reviewer |
Reviews completed implementation work for accuracy, completeness, and convention compliance |
| test-streamlit-dashboard |
Automated testing for Streamlit dashboards using Playwright with issue tracking and reporting |
Prompts
| Name |
Description |
| checkpoint |
Save or restore conversation context using memory files |
| git-commit |
Stages all changes, generates a conventional commit message, shows it to the user, and commits using only git add/commit |
| git-commit-message |
Generates a commit message following the commit-message.instructions.md rules based on all changes in the branch |
| git-merge |
Coordinate Git merge, rebase, and rebase --onto workflows with consistent conflict handling. |
| git-setup |
Interactive, verification-first Git configuration assistant (non-destructive) |
| prompt-analyze |
Evaluates prompt engineering artifacts against quality criteria and reports findings |
| prompt-build |
Build or improve prompt engineering artifacts following quality criteria |
| prompt-refactor |
Refactors and cleans up prompt engineering artifacts through iterative improvement |
| pull-request |
Provides prompt instructions for pull request (PR) generation - Brought to you by microsoft/edge-ai |
| rpi |
Autonomous Research-Plan-Implement-Review-Discover workflow for completing tasks |
| task-implement |
Locates and executes implementation plans using task-implementor mode |
| task-plan |
Initiates implementation planning based on user context or research documents |
| task-research |
Initiates research for implementation planning based on user requirements |
| task-review |
Initiates implementation review based on user context or automatic artifact discovery |
Instructions
| Name |
Description |
| commit-message |
Required instructions for creating all commit messages |
| git-merge |
Required protocol for Git merge, rebase, and rebase --onto workflows with conflict handling and stop controls. |
| markdown |
Required instructions for creating or editing any Markdown (.md) files |
| prompt-builder |
Authoring standards for prompt engineering artifacts including file types, protocol patterns, writing style, and quality criteria |
| python-script |
Instructions for Python scripting implementation |
| uv-projects |
Create and manage Python virtual environments using uv commands |
| writing-style |
Required writing style conventions for voice, tone, and language in all markdown content |
Getting Started
After installing this extension, the chat agents are available in GitHub Copilot Chat:
- Use custom agents by selecting the custom agent from the agent picker drop-down list in Copilot Chat
- Apply prompts through the Copilot Chat interface
- Reference instructions — they are automatically applied based on file patterns
Post-Installation Setup
Some chat agents create workflow artifacts in your project directory. See the installation guide for recommended .gitignore configuration and other setup details.
Pre-release Channel
HVE Core offers two installation channels:
| Channel |
Description |
Maturity Levels |
| Stable |
Production-ready artifacts only |
stable |
| Pre-release |
Early access to new features and experimental artifacts |
stable, preview, experimental |
To install the pre-release version, select Install Pre-Release Version from the extension page in VS Code.
Full Edition
Looking for more agents covering additional domains? Check out the full HVE Core extension.
Requirements
- VS Code version 1.106.1 or higher
- GitHub Copilot extension
License
MIT License - see LICENSE for details
Support
For issues, questions, or contributions, visit the GitHub repository.
Brought to you by Microsoft ISE HVE Essentials
