Index of every page on this site: llms.txt
Daniel Avila on GitHub

Daniel Avila

@davila7

Building AI dev tools with LLMs

Grand Rapids, Michigan and New York

875 skills
README badge for davila7/claude-code-templates
  • Use when building, fixing or tuning any video game. Invoke it before writing or changing game code (game loop, movement, physics, input, enemies, levels), in any engine (Godot, Unity, Unreal, Phaser, PixiJS, Three.js, Babylon.js, raw Canvas/WebGL) or platform (web, mobile, PC/console, VR/AR). Covers the game loop, fixed timestep, input mapping, frame budgets, AI, collision and game feel, and points to reference guides for 2D, 3D, game design, multiplayer, art and audio.

    README badge for davila7/claude-code-templates/game-development
  • GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.

    README badge for davila7/claude-code-templates/data-processing-nemo-curator
  • Use when the user asks to run Gemini CLI for code review, plan review, or big context (>200k) processing. Ideal for comprehensive analysis requiring large context windows. Uses Gemini 3 Pro by default for state-of-the-art reasoning and coding.

    README badge for davila7/claude-code-templates/gemini
  • 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 (1.5-8 bit) for reduced memory and 4-10× speedup vs PyTorch on CPU.

    README badge for davila7/claude-code-templates/inference-serving-llama-cpp
  • Reserved and on-demand GPU cloud instances for ML training and inference. Use when you need dedicated GPU instances with simple SSH access, persistent filesystems, or high-performance multi-node clusters for large-scale training.

    README badge for davila7/claude-code-templates/infrastructure-lambda-labs
  • Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

    README badge for davila7/claude-code-templates/llm-app-patterns

Curated setups

Skills grouped for one workflow and installable with one command.

No collections yet

When @davila7 publishes a collection, it will appear here.

Browse curators