Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4,...

Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want faster inference. Supports INT8, NF4,...

Use when learning Rust concepts. Keywords: mental model, how to think about ownership, understanding borrow checker, visualizing memory layout, analogy, misconception, explaining ownership, why...

Build MCP (Model Context Protocol) servers that give Claude new capabilities. Use when user wants to create an MCP server, add tools to Claude, or integrate external services.

Use when designing or reviewing systems handling sensitive data (PII, PHI, financial, auth credentials), building features with security implications (auth, payments, file uploads, APIs),...

Build high-quality Model Context Protocol (MCP) servers to integrate external APIs and services. Use when creating MCP tools, resources, or prompts.

This skill should be used when the user asks to "design multi-agent system", "implement supervisor pattern", "create swarm architecture", "coordinate multiple agents", or mentions multi-agent...

General principles for structured content modeling that apply across CMSs, with Sanity-specific guidance. Use when designing content schemas, planning content architecture, or evaluating content...

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate...

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate...

Provides a Model Context Protocol (MCP) server interface to the skills library, allowing any MCP-compliant agent (e.g. Claude Desktop) to invoke Antigravity skills as native tools.

This skill should be used when the user asks to "implement LLM-as-judge", "compare model outputs", "create evaluation rubrics", "mitigate evaluation bias", or mentions direct scoring, pairwise...

This skill should be used when the user asks to "start an LLM project", "design batch pipeline", "evaluate task-model fit", "structure agent project", or mentions pipeline architecture,...

Explore a codebase to gather context for coding tasks. Preserves context window and offloads work to cheaper models.

# Liberty House Club **A Parallel Binance Chain to Enable Smart Contracts** _NOTE: This document is under development. Please check regularly for updates!_ ## Table of Contents -...

Universal Runtime best practices for PyTorch inference, Transformers models, and FastAPI serving. Covers device management, model loading, memory optimization, and performance tuning.

Out-of-band codebase exploration using a cheap/fast model. Keeps your context clean while a cheap model runs 30-80 commands in parallel. Tunable precision and output size - works for broad...

Use when the user asks to run Gemini CLI for any tasks or if big context (>200k) is needed. Ideal for Code Review, Plan Review, Multi-file Analysis, and any task that requires large context...

>-

>-