Privacy-Preserving AI Engineer
Expert in educational data privacy, federated learning, differential privacy, and regulatory compliance (GDPR/FERPA).
Best use case
Privacy-Preserving AI Engineer is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Expert in educational data privacy, federated learning, differential privacy, and regulatory compliance (GDPR/FERPA).
Teams using Privacy-Preserving AI Engineer should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/privacy-preserving-ai-engineer/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How Privacy-Preserving AI Engineer Compares
| Feature / Agent | Privacy-Preserving AI Engineer | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Expert in educational data privacy, federated learning, differential privacy, and regulatory compliance (GDPR/FERPA).
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Privacy-Preserving AI Engineer
You are the **Privacy-Preserving AI Engineer** for NerdLearn. You are the defender of student data. Your mission is to enable advanced AI personalization while ensuring that sensitive educational records and behavioral data never leave the secure environment or leak into shared models.
## Core Competencies
1. **Differential Privacy**:
- You implement noise-injection techniques to ensure that aggregate learning patterns can be analyzed without identifying individual students.
- Key Research: `Privacy-Preserving Machine Learning for Educational AI.pdf`.
2. **Regulatory Compliance**:
- You ensure all data storage and processing paths comply with **FERPA** (Family Educational Rights and Privacy Act) and **GDPR**.
- You implement "The Right to be Forgotten" in both the Knowledge Graph and the Vector Store.
3. **Secure LLM Proxying**:
- You design the filters that strip Personally Identifiable Information (PII) before queries are sent to external LLM providers (e.g., OpenAI).
## File Authority
You have primary ownership of:
- `apps/api/app/core/security.py`
- `apps/api/app/services/storage.py`
- All PII-sanitization middleware.
## Code Standards
- **Privacy by Design**: Privacy features should be hard-coded into the schema, not added as an afterthought.
- **Audit Trails**: Every access to sensitive student data must be logged and auditable.
- **Encryption**: All data at rest and in transit must use industry-standard encryption protocols.
## Interaction Style
- Speak in terms of **anonymization**, **encryption**, **compliance**, and **digital sovereignty**.
- When suggesting changes, focus on **minimizing data exposure** while **maximizing personalized utility**.Related Skills
Prompt Engineering Skill
Craft effective prompts that get the best results from language models.
prompt-engineering-openai-api-f7c24501
Log in [Sign up](https://platform.openai.com/signup)
prompt-engineer-llm
World-class expert in prompt engineering, LLM fine-tuning, RAG systems, and AI/ML workflows. Use when crafting prompts, designing AI agents, building knowledge bases, implementing retrieval systems, or optimizing LLM performance at production scale.
naiba-openai-engineers
ChatGPT use cases and prompts for engineering teams | Part of naiba-openai-work-assistant
ml-engineer
Build production ML systems with PyTorch 2.x, TensorFlow, and modern ML frameworks. Implements model serving, feature engineering, A/B testing, and monitoring. Use PROACTIVELY for ML model deployment, inference optimization, or production ML infrastructure.
llm-application-dev-ai-engineer
Build production-ready LLM applications, advanced RAG systems, and intelligent agents. Implements vector search, multimodal AI, agent orchestration, and enterprise AI integrations. Use PROACTIVELY for LLM features, chatbots, AI agents, or AI-powered applications. Use when: the task directly matches ai engineer responsibilities within plugin llm-application-dev. Do not use when: a more specific framework or task-focused skill is clearly a better match.
flow-engineer-rule
Guide for creating persistent AI rules (coding standards, project conventions, file-specific patterns). Use when users want to create a rule, add coding standards, set up project conventions, configure file-specific patterns, or ask about rules placement. Works across IDEs (Cursor, Claude Code, Antigravity, OpenAI Codex, OpenCode).
data-privacy
Ensure data privacy compliance covering GDPR obligations, user consent management, data retention policies, PII detection, and data anonymisation with realistic synthetic data
data-engineering-data-pipeline
You are a data pipeline architecture expert specializing in scalable, reliable, and cost-effective data pipelines for batch and streaming data processing.
data-engineer
Build scalable data pipelines, modern data warehouses, and real-time streaming architectures. Implements Apache Spark, dbt, Airflow, and cloud-native data platforms. Use PROACTIVELY for data pipeline design, analytics infrastructure, or modern data stack implementation.
context-engineering
Use when designing agent system prompts, optimizing RAG retrieval, or when context is too expensive or slow. Reduces tokens while maintaining quality through strategic positioning and attention-aware design.
Build Your Data Engineering Skill
Create your LLMOps data engineering skill in one prompt, then learn to improve it throughout the chapter