agrag-llm-judge
Run headless AgRAG prompts in a shared thread and produce an LLM-as-judge evaluation report. Use for
738 个 Skills
Run headless AgRAG prompts in a shared thread and produce an LLM-as-judge evaluation report. Use for
Aggregate and analyze AI news from 7 authoritative sources including expert newsletters (Andrew Ng's
Answer Engine Optimization (AEO) and Generative Engine Optimization (GEO) strategies for AI-powered
Real-time alerting and notification system for Univers infrastructure. Use this when you need to mon
Send alerts and notifications using AppleScript - banners, modals, and text-to-speech
Use when creating custom Ameba rules for Crystal code analysis including rule development, AST trave
Deep attachment analysis with extraction, importance classification, and content analysis for emails
Use when analyzing event-driven systems, message queues, async processing, and pub/sub patterns
Run Android JVM unit tests via Gradle, collect reports, and fix failures. Use when asked to run/repa
Annual security report aggregation and analysis. USE WHEN annual reports, security reports, threat r
Expert on Anthropic Claude API, models, prompt engineering, function calling, vision, and best pract
Official Anthropic SDK for Claude AI with chat, streaming, function calling, and vision capabilities