Narrow the list first, then review author, source, risk, and alternatives to pick faster.
Start simple, then layer advanced filters
Showing the first 24 of 45,975 indexed skills.
Applied filters
forrestchang · forrestchang/andrej-karpathy-skills
A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.
C · Review first · Execution High
You get source-backed evidence and hints here; installation decisions always stay with you.
Anuken · Anuken/Mindustry
The automation tower defense RTS
B · Good evidence · Execution High
JuliusBrussee · JuliusBrussee/caveman
🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman
B · Good evidence · Execution High
onyx-dot-app · onyx-dot-app/onyx
Open Source AI Platform - AI Chat with advanced features that works with every LLM
B · Good evidence · Execution High
NirDiamant · NirDiamant/RAG_Techniques
This repository showcases various advanced techniques for Retrieval-Augmented Generation (RAG) systems. Each technique has a detailed notebook tutorial.
B · Good evidence · Execution High
Hannibal046 · Hannibal046/Awesome-LLM
Awesome-LLM: a curated list of Large Language Model
B · Good evidence · Execution High
QuantumNous · QuantumNous/new-api
A unified AI model hub for aggregation & distribution. It supports cross-converting various LLMs into OpenAI-compatible, Claude-compatible, or Gemini-compatible formats. A centralized gateway for personal and enterprise model management. 🍥
B · Good evidence · Execution High
eyaltoledano · eyaltoledano/claude-task-master
An AI-powered task-management system you can drop into Cursor, Lovable, Windsurf, Roo, and others.
B · Good evidence · Execution High
rtk-ai · rtk-ai/rtk
CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies
B · Good evidence · Execution High
dapr · dapr/dapr
Dapr is a portable runtime for building distributed applications across cloud and edge, combining event-driven architecture with workflow orchestration.
B · Good evidence · Execution High
SillyTavern · SillyTavern/SillyTavern
LLM Frontend for Power Users.
B · Good evidence · Execution High
jenkinsci · jenkinsci/jenkins
Jenkins automation server
B · Good evidence · Execution High
VectifyAI · VectifyAI/PageIndex
📑 PageIndex: Document Index for Vectorless, Reasoning-based RAG
B · Good evidence · Execution High
pypa · pypa/pipenv
Python Development Workflow for Humans.
C · Review first · Execution High
microsoft · microsoft/JARVIS
JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf
B · Good evidence · Execution High
arendst · arendst/Tasmota
Alternative firmware for ESP8266 and ESP32 based devices with easy configuration using webUI, OTA updates, automation using timers or rules, expandability and entirely local control over MQTT, HTTP, Serial or KNX. Full documentation at
B · Good evidence · Execution High
karpathy · karpathy/minGPT
A minimal PyTorch re-implementation of the OpenAI GPT (Generative Pretrained Transformer) training
C · Review first · Execution High
mozilla-ai · mozilla-ai/llamafile
Distribute and run LLMs with a single file.
C · Review first · Execution High
liguodongiot · liguodongiot/llm-action
本项目旨在分享大模型相关技术原理以及实战经验（大模型工程化、大模型应用落地）
B · Good evidence · Execution High
toon-format · toon-format/toon
🎒 Token-Oriented Object Notation (TOON) – Compact, human-readable, schema-aware JSON for LLM prompts. Spec, benchmarks, TypeScript SDK.
B · Good evidence · Execution High
datawhalechina · datawhalechina/llm-cookbook
面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版
B · Good evidence · Execution High
sinaptik-ai · sinaptik-ai/pandas-ai
Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.
B · Good evidence · Execution High
AlexsJones · AlexsJones/llmfit
Hundreds of models & providers. One command to find what runs on your hardware.
B · Good evidence · Execution High