Browse and install thousands of AI Agent skills in the Killer-Skills directory. Supports Claude Code, Windsurf, Cursor, and more.
NEXUS AI: Fair & Auditable Credit Scoring An advanced credit decisioning system bringing transparency and governance to AI lending. Features a Random Forest model trained on Indian datasets, cryptographic audit logging, and a real-time "Glassmorphism" executive dashboard. Built with Python, FastAPI, and Streamlit.
Agent Capability Standard is an open specification for composable AI agent capabilities. It defines 36 atomic capabilities across 9 cognitive layers, a type-safe workflow DSL, and grounded world modeling with trust-aware conflict resolution. Built on the Grounded Agency philosophy, it makes agent reliability structural—not optional.
Seamlessly route requests to your LLM backends—whether you're using stream=false for standard JSON responses or stream=true for real-time token streaming via Server-Sent Events (SSE). LLMProxy handles both modes out of the box, with zero buffering on streams, intelligent load balancing, and OpenAI-compatible API routing.