Recently active skills
Trending is calculated from star growth this site has recorded itself. No history is estimated or back-filled.
Not enough history yet: 2 of 7 days recorded. Until then this list is ordered by the most recent content change.
28352 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| peft-fine-tuningOrchestra-Research/AI-Research-SKILLsParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| unslothOrchestra-Research/AI-Research-SKILLsExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| nnsight-remote-interpretabilityOrchestra-Research/AI-Research-SKILLsProvides guidance for interpreting and manipulating neural network internals using nnsight with optional NDIF remote execution. Use when needing to run interpretability experiments on massive models (70B+) without local GPU resources, or when working with any PyTorch architecture. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| pyvene-interventionsOrchestra-Research/AI-Research-SKILLsProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, activation patching, interchange intervention training, or testing causal hypotheses about model behavior. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| sparse-autoencoder-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| transformer-lens-interpretabilityOrchestra-Research/AI-Research-SKILLsProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| nemo-curatorOrchestra-Research/AI-Research-SKILLsGPU-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. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| ray-dataOrchestra-Research/AI-Research-SKILLsScalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Integrates with Ray Train, PyTorch, TensorFlow. Scales from single machine to 100s of nodes. Use for batch inference, data preprocessing, multi-modal data loading, or distributed ETL pipelines. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| grpo-rl-trainingOrchestra-Research/AI-Research-SKILLsExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| miles-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for enterprise-grade RL training using miles, a production-ready fork of slime. Use when training large MoE models with FP8/INT4, needing train-inference alignment, or requiring speculative RL for maximum throughput. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| openrlhf-trainingOrchestra-Research/AI-Research-SKILLsHigh-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B-70B+). Built on Ray, vLLM, ZeRO-3. 2× faster than DeepSpeedChat with distributed architecture and GPU resource sharing. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| simpo-trainingOrchestra-Research/AI-Research-SKILLsSimple Preference Optimization for LLM alignment. Reference-free alternative to DPO with better performance (+6.4 points on AlpacaEval 2.0). No reference model needed, more efficient than DPO. Use for preference alignment when want simpler, faster training than DPO/PPO. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| slime-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| torchforge-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for PyTorch-native agentic RL using torchforge, Meta's library separating infra from algorithms. Use when you want clean RL abstractions, easy algorithm experimentation, or scalable training with Monarch and TorchTitan. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| fine-tuning-with-trlOrchestra-Research/AI-Research-SKILLsFine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/GRPO for reward optimization, and reward model training. Use when need RLHF, align model with preferences, or train from human feedback. Works with HuggingFace Transformers. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| verl-rl-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing RLHF, GRPO, PPO, or other RL algorithms for LLM post-training at scale with flexible infrastructure backends. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| constitutional-aiOrchestra-Research/AI-Research-SKILLsAnthropic's method for training harmless AI through self-improvement. Two-phase approach - supervised learning with self-critique/revision, then RLAIF (RL from AI Feedback). Use for safety alignment, reducing harmful outputs without human labels. Powers Claude's safety system. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| llamaguardOrchestra-Research/AI-Research-SKILLsMeta's 7-8B specialized moderation model for LLM input/output filtering. 6 safety categories - violence/hate, sexual content, weapons, substances, self-harm, criminal planning. 94-95% accuracy. Deploy with vLLM, HuggingFace, Sagemaker. Integrates with NeMo Guardrails. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| nemo-guardrailsOrchestra-Research/AI-Research-SKILLsNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| prompt-guardOrchestra-Research/AI-Research-SKILLsMeta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+ TPR, <1% FPR. Fast (<2ms GPU). Multilingual (8 languages). Deploy with HuggingFace or batch processing for RAG security. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| huggingface-accelerateOrchestra-Research/AI-Research-SKILLsSimplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpeed/FSDP/Megatron/DDP. Automatic device placement, mixed precision (FP16/BF16/FP8). Interactive config, single launch command. HuggingFace ecosystem standard. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| deepspeedOrchestra-Research/AI-Research-SKILLsExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| training-llms-megatronOrchestra-Research/AI-Research-SKILLsTrains large language models (2B-462B parameters) using NVIDIA Megatron-Core with advanced parallelism strategies. Use when training models >1B parameters, need maximum GPU efficiency (47% MFU on H100), or require tensor/pipeline/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| pytorch-fsdp2Orchestra-Research/AI-Research-SKILLsAdds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and distributed checkpointing. Use when models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| pytorch-lightningOrchestra-Research/AI-Research-SKILLsHigh-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| ray-trainOrchestra-Research/AI-Research-SKILLsDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| lambda-labs-gpu-cloudOrchestra-Research/AI-Research-SKILLsReserved 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. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| modal-serverless-gpuOrchestra-Research/AI-Research-SKILLsServerless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure management, deploying ML models as APIs, or running batch jobs with automatic scaling. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| skypilot-multi-cloud-orchestrationOrchestra-Research/AI-Research-SKILLsMulti-cloud orchestration for ML workloads with automatic cost optimization. Use when you need to run training or batch jobs across multiple clouds, leverage spot instances with auto-recovery, or optimize GPU costs across providers. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |
| awq-quantizationOrchestra-Research/AI-Research-SKILLsActivation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner. | Stars: 14k | Updated | Claude CodeCodex | Unverified | Install |