AI & LLM Engineering · Qwen · For data scientists

RL training reference for the ART framework. An agent skill from OpenPipe/ART.

OpenPipe/ART

SFT training reference for the ART framework. An agent skill from OpenPipe/ART.

OpenPipe/ART

Complete agent-ready workflow for Qwen-family MTP or nextn GGUF conversion and release.

R6410418/Jackrong-llm-finetuning-guide

A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document.

MigoXLab/dingo

A skill your agent uses when adding support for a new model to VeOmni.

ByteDance-Seed/VeOmni

Rules for adding a new model or model family to the finetuning pipeline, or changing finetuning behavior for an existing one — engine-agnostic customization via family hooks instead of if/else in…

overmind-core/overmind

Guides reinforcement-learning post-training of LLMs with slime, which pairs Megatron-LM training with SGLang rollouts, including GRPO runs on GLM, Qwen3 and Llama 3 models.

Orchestra-Research/AI-Research-SKILLs

Guide a tester through hipfire bring-up, serve smoke, claim-scoped harnesses, and benchmark reporting on AMD RDNA/CDNA GPUs.

warpfront/hipfire

Builds and publishes a Gradio demo on Hugging Face Spaces for a LoRA, with the pipeline, UI and settings chosen to match that LoRA's task and model card.

huggingface/skills

Add new AI models to Kiln's mlmodellist.py and produce a Discord announcement.

Kiln-AI/Kiln

Qwen-Image-2.1 LoRA line (NOT Anima) — running cache/train through the daemon, make gui-qwen, the CacheRequest/TrainRequest flag surface and how to add a field, model-dir resolution, cache layout…

sorryhyun/anima_lora

MUST be considered at task start in this repository to detect OpenSpec change lifecycle work and route it to token-efficient stage prompts.

HsienW/chat-gun

把基于 prompts/ 主源的 skill 打包成断网单机可用的离线提示词包。Use when the user wants to export/package offline prompts for disconnected hosts (WebUI、Qwen、AnythingLLM、Claude.ai), generate self-contained systemprompt /…

zhaohui-yang/official-document-drafting

Fine-tune LLMs with LlamaFactory — register datasets, train via YAML configs, merge LoRA adapters and serve the result.

Prism-Shadow/penguin-harness

CLI tools execution specification (gemini/claude/codex/qwen/opencode) with unified prompt template, mode options, and auto-invoke triggers for code analysis and implementation tasks.

catlog22/Claude-Code-Workflow

综合办公文员与内容创作者在需要整理会议纪要或创作社媒文案时，使用本技能将录音一键转写并智能改写为邮件、笔记或社媒文案，支持多段录音无缝拼接，秒出高质量结构化文本，让语音记录与内容产出效率翻倍！

anbeime/skill

Build Flux txt2img workflows with Flux.1 Dev (SRPO), Flux 2 Klein 9B, Turbo LoRAs, FluxGuidance, and DualCLIPLoader patterns

artokun/comfyui-mcp

Build Qwen Image Edit workflows covering model loading, conditioning, LoRAs, prompt patterns, and XY plot testing

artokun/comfyui-mcp

Build Qwen Image 2512 text-to-image workflows with QwenImageIntegratedKSampler, separate component loading, lightning LoRAs, and fine-tuned model variants

artokun/comfyui-mcp

Build Krea 2 Turbo txt2img workflows with the native krea2 CLIPLoader, Qwen3-VL encoder, Qwen image VAE, 8-step turbo settings, and Ideogram-style JSON prompting

artokun/comfyui-mcp

Benchmark an optimization (PR or branch) on a Device Farm device via the vlm-benchmark framework — baseline vs optimized, quality-regression-aware.

tetherto/qvac

Shared Cosmos3 frontend that explicitly routes Cosmos Framework and Cosmos-RL, validates runtime model/video-dataset/SLURM inputs, consumes an SQSH or packaged backend image, optionally plans…

NVIDIA/skills