skills.rest
simota
simotaCOMMUNITY
Explore all skills by this author →
GitHub

Oracle

Design and evaluate LLM-based systems with prompt engineering, RAG, and cost optimization.

68|14|Updated Jan 7, 2026
Search Tags:#prompt engineering#mlops#rag#evaluation#cost optimization#ai safety#ai/ml
One-click install
npx skills add https://github.com/simota/agent-skills --skill oracle-simota
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: Oracle
Source: https://github.com/simota/agent-skills/tree/main/oracle
Command: npx skills add https://github.com/simota/agent-skills --skill oracle-simota

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill streamlines the design, evaluation, and optimization of AI/ML systems, ensuring robust, safe, and cost-effective LLM applications.

Core Features & Use Cases

  • Prompt Engineering: Design, optimize, and evaluate LLM prompts for various tasks.
  • RAG Architecture: Design Retrieval-Augmented Generation pipelines, including chunking and retrieval strategies.
  • AI Safety & Guardrails: Implement safety measures, evaluate bias, and ensure responsible AI deployment.
  • Cost Optimization: Develop strategies to minimize LLM usage costs without sacrificing performance.
  • Use Case: When developing a new AI feature, use Oracle to design the optimal prompt, set up a RAG system for knowledge retrieval, define safety guardrails, and plan for cost-effective deployment.

Quick Start

Use the Oracle skill to design a RAG architecture for a new customer support chatbot.

Frequently Asked Questions about Oracle

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I design a RAG architecture for an LLM application?▼

To design a RAG architecture, you need to define chunking strategies, retrieval pipelines, and LLM application patterns. This Skill generates design specifications for Retrieval-Augmented Generation systems to streamline knowledge retrieval and ensure robust AI deployment.

What is the best way to optimize LLM prompts for specific tasks?▼

The best way to optimize LLM prompts is through systematic design and evaluation frameworks. This Skill provides prompt engineering specifications and evaluation strategies to refine LLM inputs, ensuring robust performance for various targeted AI tasks.

How can I reduce LLM usage costs without sacrificing performance?▼

You can reduce LLM usage costs by applying cost optimization strategies and cost-aware delivery plans. This Skill develops targeted methods to minimize LLM operational expenses while maintaining the performance and safety of your AI/ML systems.

How do I implement AI safety guardrails for LLM applications?▼

Implementing AI safety guardrails requires defining safety measures and evaluating bias for responsible AI deployment. This Skill provides design specifications to establish safety protocols and evaluation frameworks for secure LLM applications.

Does this support MLOps evaluation frameworks for AI systems?▼

Yes, it supports MLOps by providing comprehensive evaluation frameworks for AI/ML systems. This Skill specializes in defining evaluation strategies and cost-aware delivery plans, ensuring your LLM-based applications are robust, safe, and effectively monitored.

Related Skills

Explore More Software Engineering Skills→
Yeachan-HeoYeachan-Heo
242

ml-rigor

Automate ML evaluation with baselines, stratified cross-validation, and leakage checks.

Community
Advanced
Patasse97Patasse97

senior-ml-engineer

Deploy production ML systems with monitoring, drift detection, and cost controls.

Community
Advanced
zhangzhang-111-izhangzhang-111-i
2

rag-architect

Designs RAG pipelines with chunking, embedding, retrieval, and evaluation strategies.

Community
Advanced
ContextJet-aiContextJet-ai
29

optimize-prompts

Select the best prompt variation based on performance metrics on an evaluation set.

Official
Intermediate