The Digital Futurist logoSkills and Prompt Registry
type public-role-directoryrole llm-engineercategory ai-ml/llm-systemscurator Thomas Cherickalupdated 2026-11-15

llm-engineer: Public Skills (20)

Sorted by GitHub stars of the source repo, highest first.

# Skill Owner Repo Stars License What it does
1 huggingface-lora-space-builder sickn33 sickn33/agentic-awesome-skills 49,710 MIT Build and publish a Gradio demo on Hugging Face Spaces for a user-provided LoRA.
2 llm-fine-tuning sickn33 sickn33/agentic-awesome-skills 49,710 MIT Set up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axolotl, and distributed training...
3 trl-training sickn33 sickn33/agentic-awesome-skills 49,710 MIT Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and...
4 unsloth-finetuning sickn33 sickn33/agentic-awesome-skills 49,710 MIT Fine-tune and post-train LLMs with Unsloth Core on a single consumer GPU: VRAM sizing, LoRA/QLoRA, GRPO/DPO, chat-template correctness, and...
5 vllm-server sickn33 sickn33/agentic-awesome-skills 49,710 MIT Deploy and manage vLLM for high-throughput LLM inference. Configure continuous batching, tensor parallelism, quantization, and...
6 dataset-curation wshobson wshobson/agents 42,512 MIT Prepare, format, and validate datasets for supervised fine-tuning and preference training. Use when converting raw data into training...
7 finetuning-method-selection wshobson wshobson/agents 42,512 MIT Decide whether to fine-tune at all, and route to the right method (SFT, DPO/ORPO/KTO, GRPO/RLVR, continued pretraining) and base model. Use...
8 grpo-rlvr-training wshobson wshobson/agents 42,512 MIT Train reasoning and verifiable-task behavior with GRPO and reinforcement learning from verifiable rewards (RLVR). Use when task success is...
9 lora-qlora-recipes wshobson wshobson/agents 42,512 MIT Configure LoRA and QLoRA supervised fine-tuning with current best-practice hyperparameters. Use when writing or reviewing a LoRA/QLoRA...
10 distributed-training-deepspeed davila7 davila7/claude-code-templates 33,617 MIT Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse...
11 distributed-training-megatron-core davila7 davila7/claude-code-templates 33,617 MIT Trains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models...
12 distributed-training-pytorch-fsdp davila7 davila7/claude-code-templates 33,617 MIT Expert guidance for Fully Sharded Data Parallel training with PyTorch FSDP - parameter sharding, mixed precision, CPU offloading, FSDP2
13 emerging-techniques-knowledge-distillation davila7 davila7/claude-code-templates 33,617 MIT Compress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained...
14 emerging-techniques-long-context davila7 davila7/claude-code-templates 33,617 MIT Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long...
15 axolotl Orchestra-Research Orchestra-Research/AI-Research-SKILLs 14,542 MIT Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support
16 deepspeed Orchestra-Research Orchestra-Research/AI-Research-SKILLs 14,542 MIT Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse...
17 distributed-llm-pretraining-torchtitan Orchestra-Research Orchestra-Research/AI-Research-SKILLs 14,542 MIT Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama...
18 fine-tuning-openvla-oft Orchestra-Research Orchestra-Research/AI-Research-SKILLs 14,542 MIT Fine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation,...
19 fine-tuning-serving-openpi Orchestra-Research Orchestra-Research/AI-Research-SKILLs 14,542 MIT Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference...
20 fine-tuning-expert Jeffallan jeffallan/claude-skills 12,361 MIT Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA...