Fine-tuning

Sample off-equilibrium potential energy surface (PES), used for benchmarking and fine-tuning MLIPs.

learningmatter-mit/AtomisticSkills

Fine-tune Fairchem machine learning interatomic potentials (UMA, ESEN) on custom datasets.

learningmatter-mit/AtomisticSkills

Generate inorganic material structures using MatterGen, a diffusion-based generative model.

learningmatter-mit/AtomisticSkills

Fine-tune MACE machine learning interatomic potentials on custom datasets.

learningmatter-mit/AtomisticSkills

Fine-tune MatGL machine learning interatomic potentials on custom datasets.

learningmatter-mit/AtomisticSkills

This skill should be used when the user asks about "local models", "custom models", "fine-tuning", "self-hosting models", "model selection", "which model should I use", "data privacy and models"…

Habitat-Thinking/ai-literacy-superpowers

Reference for the TRL (Transformer Reinforcement Learning) library codebase.

benchflow-ai/skillsbench

Generate images with Pruna P-Image models via inference.sh CLI.

aiskillstore/marketplace

Character consistency across AI-generated images with reference sheets and LoRA techniques.

aiskillstore/marketplace

Create polished HTML slide decks and PDF-ready documents for consulting deliverables.

thatrebeccarae/claude-marketing

A skill your agent uses when running open models or working on the Hugging Face platform — the Inference Providers router or InferenceClient, Hub repos via the hf CLI, a dedicated Inference Endpoint…

ericrisco/rsc-harness

A skill your agent uses when running GPU compute on RunPod and deciding between Pods (hourly, always-on) and Serverless (per-second, autoscaling) for training, fine-tuning or inference — serverless…

ericrisco/rsc-harness

A skill your agent uses when connecting an AI agent to Scenario (scenario.com) through MCP, or when a task involves generating images, video, 3D, audio, sprites, textures, or game assets.

scenario-labs/skills

A skill your agent uses when one look must hold across Scenario generations: one character across scenes, a turnaround, or a video animated from its references, one product across angles, one style…

scenario-labs/skills

Apply contrast and spacing for legibility — calibrating color contrast between text and background, character tracking, and line leading so a chosen typeface and size actually render legibly.

hashgraph-online/awesome-codex-plugins

Explains how HOT-Step's LoRA/LoKr adapter system loads, merges, caches, stacks, and regionally masks adapters at runtime, including hard-won failure modes.

scragnog/HOT-Step-CPP

Design, build, diagnose, and evolve agent harnesses: instructions, tools, execution environments, durable state, context management, verification, recovery, and bounded autonomous loops.

magnus919/agent-skills

Tmux skill for running background tasks. An agent skill from archibate/dotfiles-opencode.

archibate/dotfiles-opencode

Train DeePMD-kit machine learning potentials. An agent skill from Hello-QM/catgo-LRG.

Hello-QM/catgo-LRG

使用 ArkCLI 创建、查询和管理模型精调训练任务，并从训练指标选择最佳 step、导出训练产物为 custom model、衔接模型仓库与推理部署。任何包含精调任务 ID（mcj-）的查询、查不到原因诊断、日志、trajectory、状态或生命周期操作都应使用本 skill；也适用于选择训练方法、查询精调价格和超参数、校验精调训练/验证数据、匹配精调资源组、创建任务及导出部署。本…

volcengine/ark-cli

Techniques for reducing peak GPU memory in Megatron Bridge — expandable segments, PEFT + SP input re-gather, parallelism resizing, activation recompute, CPU offloading constraints, and common OOM…

NVIDIA/skills

This skill should be used when the user asks to "reflect on this conversation", "optimize my agent setup", "improve agent instructions", "analyze chat patterns", "audit AGENTS.md", "suggest agent…

shepherdjerred/monorepo

Multi-agent orchestration patterns for production deployments.

LeoYeAI/openclaw-master-skills

AI 学习记录与成长追踪工具。用于记录 AI/LLM 学习笔记、使用心得、Prompt 技巧、工具体验等，并提供学习指导和规划。当用户提到以下任何话题时都应使用此 skill：AI 学习记录、学习笔记、AI 使用心得、Prompt 工程学习、模型对比体验、AI 工具使用记录、LLM 学习、RAG 学习、Agent 学习、MCP 学习、AI 微调实践、AI 学习规划、怎么学 AI、AI…

LeoYeAI/openclaw-master-skills

Methodology for systematically designing a chatbot's intent classification taxonomy.

revfactory/harness-100

Machine-learning research loop for dataset curation, fine-tuning, evaluation, inference deployment, experiment tracking, and model explainability.

AnastasiyaW/codex-claude-code-config

Expert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training.

AlexAI-MCP/hermes-CCC

Run distributed GPU training jobs on CoreWeave with multi-node PyTorch.

jeremylongshore/tons-of-skills-marketplace

Local TensorZero documentation reference (latest). An agent skill from olorehq/olore.

olorehq/olore

Orchestrate AI/ML pipelines for data ingestion, model training, batch inference, and RAG indexing using Prefect, Airflow, or Dagster.

BagelHole/DevOps-Security-Agent-Skills

Set up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axolotl, and distributed training with DeepSpeed or FSDP.

BagelHole/DevOps-Security-Agent-Skills

Build transformer fine-tuning plans for classification and generation

wentorai/research-plugins

PyTorch Lightning framework for scalable model training and research

wentorai/research-plugins

Build Lightricks LTX-2 / LTX-2.3 video workflows covering text-to-video, image-to-video, GGUF and bundled checkpoints, distilled model, camera control LoRAs, synchronized audio, two-stage upscaling…

artokun/comfyui-mcp

Build OCR pipelines in MATLAB using the ocr() function. An agent skill from matlab/matlab-agentic-toolkit.

matlab/matlab-agentic-toolkit

Automatically discover machine learning and AI skills when working with machine learning, PyTorch, training, inference, RAG, embeddings, fine-tuning, LLM, DSPy, HuggingFace, or diffusion models.

rand/cc-polymath

Verl 分布式训练服务一键拉起与配置。触发场景：(1) 用户要启动 Verl 训练任务或部署 RLHF/DAPO 训练环境 (2) 在 NPU 集群上拉起 Verl 训练容器 (3) 配置 Ray 集群和 SwanLab 监控 (4) 根据 7 位二进制掩码灵活配置加速特性。支持 Qwen3-8B 等 Megatron 模型的 DAPO 训练全流程。

ascend-ai-coding/awesome-ascend-skills

Use ML.NET to train, evaluate, or integrate machine-learning models into .NET applications with realistic data preparation, inference, and deployment expectations.

managedcode/dotnet-skills

Physics-derived reasoning engine for AI models. An agent skill from LeoYeAI/openclaw-master-skills.

LeoYeAI/openclaw-master-skills

Use torchtune model/tokenizer builders, PEFT modules, losses, conversion utilities, and modeling components safely.

VectorSpaceLab/AREX-Skill

A skill your agent uses when modifying PEFT itself, preparing a PEFT pull request, adding a new PEFT method, selecting contributor tests, or checking PEFT contribution/style/backward-compatibility…

VectorSpaceLab/AREX-Skill

Build and review OpenRLHF supervised/preference training plans for SFT, reward models, DPO, IPO, and cDPO.

VectorSpaceLab/AREX-Skill

Use TorchRL for TensorDict-first reinforcement-learning environments, collectors, replay buffers, modules, objectives, LLM/RLHF/VLA workflows, services, rendering, and maintainer-safe repository…

VectorSpaceLab/AREX-Skill

Train or fine-tune ColBERT models, prepare and validate triples, use scored distillation examples, and plan GPU/resource settings.

VectorSpaceLab/AREX-Skill

A skill your agent uses for ModelScope trainer construction, TrainingArgs conversion, fine-tuning and evaluation preflight, checkpoint hooks, and safe train/eval command planning.

VectorSpaceLab/AREX-Skill

Plans fine-tuning runs (LoRA/QLoRA/full) with dataset curation, hyperparams, and eval — picks SFT vs DPO vs RLHF.

criptogus/agent-evolve-network

Diffusers Pipeline 推理指南，用于华为昇腾 NPU。覆盖环境预检、通用 Pipeline 推理（图像/视频模型）、内存优化（CPU offload、attention slicing、VAE slicing）、LoRA 加载与融合、多卡推理和按版本检索 Diffusers API。用户一旦提到在昇腾 NPU 上运行 FLUX、SDXL、Wan、CogVideoX 等…

ascend-ai-coding/awesome-ascend-skills

Universal VLM (vision-language understanding model) training guide for Huawei Ascend NPU using MindSpeed-MM.

ascend-ai-coding/awesome-ascend-skills