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,...

Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is unavailable. Supports GGUF quantization...

PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions, create sound effects, or perform...

Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN...

Provides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive...

|

View and manage the runtime changelog for observability

Semantic search for finding code by meaning using natural language queries. Orchestrates semantic-search-reader (search/find-similar/list-projects) and semantic-search-indexer...

Use when designing prompts for LLMs, optimizing model performance, building evaluation frameworks, or implementing advanced prompting techniques like chain-of-thought, few-shot learning, or...

Guides creation, validation, and application of Supabase database migrations with RLS policy checks and type generation. Use when adding tables, modifying schema, or updating database structure.

Verify development environment is ready

Fast workflow for small changes, bug fixes, and UI tweaks that don't require full feature development. Uses sub-agent orchestration with model selection (Sonnet 4.5 orchestrator, Haiku 4.5...

List all available skills (core + custom)

Orchestrate comprehensive planning phase from ideation to development-ready specifications using 4 specialized agents

Orchestrate comprehensive planning phase from ideation to development-ready specifications using 3 specialized agents (Full workflow documentation at docs/workflows/planning-workflow.md)

Simple Pomodoro timer for focused work sessions with session tracking and productivity analytics. Use when users request focus timers, ask about productivity patterns, or want to track work...

Replace with description of the skill and when Claude should use it.

Validate MCP configuration and suggest improvements

How to write a Claude Code skill

Runs mandatory quality checks before commits. Executes build, tests, and pattern validation from code-review-standards.md. Use when ready to commit code or when asked to verify code quality meets...