Browse skills

Eval Harness allows you to systematically test and evaluate AI model outputs against a defined set of criteria for consistent performance & reliability.

System Prompt Structure — provides AI agent assistance for software development workflows.

Karpathy System Prompt Learning — provides AI agent assistance for software development workflows.

Evaluates Retrieval-Augmented Generation (RAG) responses for accuracy and relevance, boosting RAG system quality & reliability.

Analyzes system performance data to identify bottlenecks and suggest optimizations based on established benchmarks.

Predicts and optimizes system performance under high load, ensuring consistent service levels at scale.

This tool rapidly constructs Retrieval-Augmented Generation (RAG) systems by automating data sourcing and prompt engineering for enhanced AI responses.

Adversarial Machine Learning identifies vulnerabilities in AI models by crafting malicious inputs to expose weaknesses – crucial for robust and secure systems.

This skill generates dense vector embeddings from text modules for semantic similarity searches and enhanced retrieval within RAG systems.

System Prompt Validator — provides AI agent assistance for software development workflows.

System Prompt — provides AI agent assistance for software development workflows.

This skill assesses the quality of retrieved documents in RAG systems, ensuring accuracy and relevance for improved responses.

Analyzes AI systems for potential safety risks, biases, and ethical concerns using jmsktm's proprietary methodology.

This skill generates vector embeddings of text, enabling semantic similarity searches and powering advanced AI applications like recommendation systems.

Evaluates a core system’s performance against a predefined scorecard, identifying key strengths and weaknesses for targeted improvement.

Creates detailed fictional worlds including geography, cultures, history, and magic systems based on user prompts.

Automatically generates configuration files based on user prompts and desired system behavior.

Analyzes and optimizes performance metrics from The Bearded Bears' AS (Automated Systems) deployments for improved efficiency.

Eval Harness allows you to systematically test and evaluate AI models’ performance across diverse datasets for robust results and reliable insights.