Data Science R Implementation

---
name: data-science-r-implementation
description: "Use when for data science r implementation."
version: 1.0.0
author: Hermes Agent
license: MIT
platforms: [linux, macos, windows]
metadata:
  hermes:
    tags: [data-science, r, statistics, ggplot2]
    related_skills: [general]
---

## Overview
Data science with R.

## When to Use
- "Data Science R Implementation design"
- "Best practices"
- "Optimization"
- "Troubleshooting"

## Key Approaches
1. Requirements
2. Tools
3. Implementation
4. Testing
5. Docs
6. Monitoring

## Common Pitfalls
1. Ignoring constraints
2. Skipping standards
3. Poor alignment
4. Inadequate testing
5. No docs
6. Over-engineering
7. No rollback
8. No monitoring
9. No scaling
10. No validation

## Verification Checklist
- [ ] Requirements verified
- [ ] Standards applied
- [ ] Design reviewed
- [ ] Tests defined
- [ ] Docs complete
- [ ] Monitoring set
- [ ] Rollback planned
- [ ] Security checked
- [ ] Deploy verified
- [ ] Stakeholder approved