orchestra-research/ai-research-skills
- skills.sh installs
- 99.5K
- skills
- 95
Install
$ npx -y skills add orchestra-research/ai-research-skills --agent claude-codeInstalls into .claude/skills of the current project.
Skills
1
ml-paper-writingorchestra-research/ai-research-skillsWrite publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying ci2.5Kskills.sh installs
ml-paper-writingorchestra-research/ai-research-skillsWrite publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying ci2.5Kskills.sh installs2brainstorming-research-ideasorchestra-research/ai-research-skillsGuides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between p1.3Kskills.sh installs
brainstorming-research-ideasorchestra-research/ai-research-skillsGuides researchers through structured ideation frameworks to discover high-impact research directions. Use when exploring new problem spaces, pivoting between p1.3Kskills.sh installs3academic-plottingorchestra-research/ai-research-skillsGenerates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to1.3Kskills.sh installs
academic-plottingorchestra-research/ai-research-skillsGenerates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to1.3Kskills.sh installs4creative-thinking-for-researchorchestra-research/ai-research-skillsApplies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging co1.3Kskills.sh installs
creative-thinking-for-researchorchestra-research/ai-research-skillsApplies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely novel research directions by leveraging co1.3Kskills.sh installs5mlfloworchestra-research/ai-research-skillsTrack ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycl1.1Kskills.sh installs
mlfloworchestra-research/ai-research-skillsTrack ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycl1.1Kskills.sh installs6serving-llms-vllmorchestra-research/ai-research-skillsServes LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throu1.1Kskills.sh installs
serving-llms-vllmorchestra-research/ai-research-skillsServes LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throu1.1Kskills.sh installs7faissorchestra-research/ai-research-skillsFacebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Fla1.1Kskills.sh installs
faissorchestra-research/ai-research-skillsFacebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Fla1.1Kskills.sh installs8stable-diffusion-image-generationorchestra-research/ai-research-skillsState-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image1.1Kskills.sh installs
stable-diffusion-image-generationorchestra-research/ai-research-skillsState-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating images from text prompts, performing image1.1Kskills.sh installs9tensorrt-llmorchestra-research/ai-research-skillsOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 1.1Kskills.sh installs
tensorrt-llmorchestra-research/ai-research-skillsOptimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 1.1Kskills.sh installs10autoresearchorchestra-research/ai-research-skillsOrchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization t1.1Kskills.sh installs
autoresearchorchestra-research/ai-research-skillsOrchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid experiment iterations with clear optimization t1.1Kskills.sh installs11peft-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 t1.1Kskills.sh installs
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 t1.1Kskills.sh installs12audiocraft-audio-generationorchestra-research/ai-research-skillsPyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions1.1Kskills.sh installs
audiocraft-audio-generationorchestra-research/ai-research-skillsPyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you need to generate music from text descriptions1.1Kskills.sh installs13gguf-quantizationorchestra-research/ai-research-skillsGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible 1.1Kskills.sh installs
gguf-quantizationorchestra-research/ai-research-skillsGGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardware, Apple Silicon, or when needing flexible 1.1Kskills.sh installs14ray-trainorchestra-research/ai-research-skillsDistributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nodes. Built-in hyperparameter tuning with Ray1.1Kskills.sh installs
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 Ray1.1Kskills.sh installs15weights-and-biasesorchestra-research/ai-research-skillsTrack ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collabo1.1Kskills.sh installs
weights-and-biasesorchestra-research/ai-research-skillsTrack ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, and manage model registry with W&B - collabo1.1Kskills.sh installs16segment-anything-modelorchestra-research/ai-research-skillsFoundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or 1.1Kskills.sh installs
segment-anything-modelorchestra-research/ai-research-skillsFoundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or 1.1Kskills.sh installs17unslothorchestra-research/ai-research-skillsExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization1Kskills.sh installs
unslothorchestra-research/ai-research-skillsExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization1Kskills.sh installs18crewai-multi-agentorchestra-research/ai-research-skillsMulti-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you n1Kskills.sh installs
crewai-multi-agentorchestra-research/ai-research-skillsMulti-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents working together on complex tasks, when you n1Kskills.sh installs19evaluating-llms-harnessorchestra-research/ai-research-skillsEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting 1Kskills.sh installs
evaluating-llms-harnessorchestra-research/ai-research-skillsEvaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting 1Kskills.sh installs20huggingface-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 place1Kskills.sh installs
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 place1Kskills.sh installs21whisperorchestra-research/ai-research-skillsOpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes fr1Kskills.sh installs
whisperorchestra-research/ai-research-skillsOpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and language identification. Six model sizes fr1Kskills.sh installs22prompt-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). Multilingua1Kskills.sh installs
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). Multilingua1Kskills.sh installs23knowledge-distillationorchestra-research/ai-research-skillsCompress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transfe1Kskills.sh installs
knowledge-distillationorchestra-research/ai-research-skillsCompress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transfe1Kskills.sh installs24ray-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.1Kskills.sh installs
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.1Kskills.sh installs25fine-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 mo1Kskills.sh installs
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 mo1Kskills.sh installs26llama-cpporchestra-research/ai-research-skillsRuns LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is una1Kskills.sh installs
llama-cpporchestra-research/ai-research-skillsRuns LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M3 Macs, AMD/Intel GPUs, or when CUDA is una1Kskills.sh installs27tensorboardorchestra-research/ai-research-skillsVisualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML vi1Kskills.sh installs
tensorboardorchestra-research/ai-research-skillsVisualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile performance with TensorBoard - Google's ML vi1Kskills.sh installs28deepspeedorchestra-research/ai-research-skillsExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention1Kskills.sh installs
deepspeedorchestra-research/ai-research-skillsExpert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/FP8, 1-bit Adam, sparse attention1Kskills.sh installs29qdrant-vector-searchorchestra-research/ai-research-skillsHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, h1Kskills.sh installs
qdrant-vector-searchorchestra-research/ai-research-skillsHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, h1Kskills.sh installs30grpo-rl-trainingorchestra-research/ai-research-skillsExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training1Kskills.sh installs
grpo-rl-trainingorchestra-research/ai-research-skillsExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model training1Kskills.sh installs31optimizing-attention-flashorchestra-research/ai-research-skillsOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>1Kskills.sh installs
optimizing-attention-flashorchestra-research/ai-research-skillsOptimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/running transformers with long sequences (>1Kskills.sh installs32quantizing-models-bitsandbytesorchestra-research/ai-research-skillsQuantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want fast1Kskills.sh installs
quantizing-models-bitsandbytesorchestra-research/ai-research-skillsQuantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limited, need to fit larger models, or want fast1Kskills.sh installs33verl-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 fo1Kskills.sh installs
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 fo1Kskills.sh installs34dspyorchestra-research/ai-research-skillsBuild complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framewor1Kskills.sh installs
dspyorchestra-research/ai-research-skillsBuild complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and agents with DSPy - Stanford NLP's framewor1Kskills.sh installs35langchainorchestra-research/ai-research-skillsFramework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct 1Kskills.sh installs
langchainorchestra-research/ai-research-skillsFramework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, Anthropic, Google), 500+ integrations, ReAct 1Kskills.sh installs36pytorch-lightningorchestra-research/ai-research-skillsHigh-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks system, and minimal boilerplate. Scales from lap1Kskills.sh installs
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 lap1Kskills.sh installs37axolotlorchestra-research/ai-research-skillsExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support1Kskills.sh installs
axolotlorchestra-research/ai-research-skillsExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal support1Kskills.sh installs38hqq-quantizationorchestra-research/ai-research-skillsHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast 1Kskills.sh installs
hqq-quantizationorchestra-research/ai-research-skillsHalf-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast 1Kskills.sh installs39sentence-transformersorchestra-research/ai-research-skillsFramework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Suppo1Kskills.sh installs
sentence-transformersorchestra-research/ai-research-skillsFramework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Suppo1Kskills.sh installs40cliporchestra-research/ai-research-skillsOpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-tex1Kskills.sh installs
cliporchestra-research/ai-research-skillsOpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-tex1Kskills.sh installs41huggingface-tokenizersorchestra-research/ai-research-skillsFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. 1Kskills.sh installs
huggingface-tokenizersorchestra-research/ai-research-skillsFast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Supports BPE, WordPiece, and Unigram algorithms. 1Kskills.sh installs42long-contextorchestra-research/ai-research-skillsExtend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ token1Kskills.sh installs
long-contextorchestra-research/ai-research-skillsExtend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ token1Kskills.sh installs43nanogptorchestra-research/ai-research-skillsEducational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfec1Kskills.sh installs
nanogptorchestra-research/ai-research-skillsEducational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy. Perfec1Kskills.sh installs44pytorch-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 models1Kskills.sh installs
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 models1Kskills.sh installs45awq-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 GP1Kskills.sh installs
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 GP1Kskills.sh installs46modal-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, o1Kskills.sh installs
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, o1Kskills.sh installs47moe-trainingorchestra-research/ai-research-skillsTrain Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense mode1Kskills.sh installs
moe-trainingorchestra-research/ai-research-skillsTrain Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense mode1Kskills.sh installs48sglangorchestra-research/ai-research-skillsFast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with too1Kskills.sh installs
sglangorchestra-research/ai-research-skillsFast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with too1Kskills.sh installs49chromaorchestra-research/ai-research-skillsOpen-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function AP1Kskills.sh installs
chromaorchestra-research/ai-research-skillsOpen-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text search, filter by metadata. Simple 4-function AP1Kskills.sh installs50instructororchestra-research/ai-research-skillsExtract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream par1Kskills.sh installs
instructororchestra-research/ai-research-skillsExtract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream par1Kskills.sh installs51speculative-decodingorchestra-research/ai-research-skillsAccelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× spe1Kskills.sh installs
speculative-decodingorchestra-research/ai-research-skillsAccelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× spe1Kskills.sh installs52llama-factoryorchestra-research/ai-research-skillsExpert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support1Kskills.sh installs
llama-factoryorchestra-research/ai-research-skillsExpert guidance for fine-tuning LLMs with LLaMA-Factory - WebUI no-code, 100+ models, 2/3/4/5/6/8-bit QLoRA, multimodal support1Kskills.sh installs53model-mergingorchestra-research/ai-research-skillsMerge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific exp1Kskills.sh installs
model-mergingorchestra-research/ai-research-skillsMerge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific exp1Kskills.sh installs55transformer-lens-interpretabilityorchestra-research/ai-research-skillsProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation 1Kskills.sh installs
transformer-lens-interpretabilityorchestra-research/ai-research-skillsProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation 1Kskills.sh installs56distributed-llm-pretraining-torchtitanorchestra-research/ai-research-skillsProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or cu1Kskills.sh installs
distributed-llm-pretraining-torchtitanorchestra-research/ai-research-skillsProvides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP). Use when pretraining Llama 3.1, DeepSeek V3, or cu1Kskills.sh installs57openrlhf-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× fast1Kskills.sh installs
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× fast1Kskills.sh installs58evaluating-code-modelsorchestra-research/ai-research-skillsEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding 1Kskills.sh installs
evaluating-code-modelsorchestra-research/ai-research-skillsEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding 1Kskills.sh installs59gptqorchestra-research/ai-research-skillsPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduc1Kskills.sh installs
gptqorchestra-research/ai-research-skillsPost-training 4-bit quantization for LLMs with minimal accuracy loss. Use for deploying large models (70B, 405B) on consumer GPUs, when you need 4× memory reduc1Kskills.sh installs60sentencepieceorchestra-research/ai-research-skillsLanguage-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), determinis1Kskills.sh installs
sentencepieceorchestra-research/ai-research-skillsLanguage-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), determinis1Kskills.sh installs61outlinesorchestra-research/ai-research-skillsGuarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize in1Kskills.sh installs
outlinesorchestra-research/ai-research-skillsGuarantee valid JSON/XML/code structure during generation, use Pydantic models for type-safe outputs, support local models (Transformers, vLLM), and maximize in1Kskills.sh installs62llamaindexorchestra-research/ai-research-skillsData framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, que1Kskills.sh installs
llamaindexorchestra-research/ai-research-skillsData framework for building LLM applications with RAG. Specializes in document ingestion (300+ connectors), indexing, and querying. Features vector indices, que1Kskills.sh installs63pyvene-interventionsorchestra-research/ai-research-skillsProvides guidance for performing causal interventions on PyTorch models using pyvene's declarative intervention framework. Use when conducting causal tracing, a1Kskills.sh installs
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, a1Kskills.sh installs64simpo-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 1Kskills.sh installs
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 1Kskills.sh installs65slime-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 work1Kskills.sh installs
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 work1Kskills.sh installs66training-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, need1Kskills.sh installs
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, need1Kskills.sh installs67guidanceorchestra-research/ai-research-skillsControl LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance -1Kskills.sh installs
guidanceorchestra-research/ai-research-skillsControl LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance -1Kskills.sh installs68mamba-architectureorchestra-research/ai-research-skillsState-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware desi1Kskills.sh installs
mamba-architectureorchestra-research/ai-research-skillsState-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware desi1Kskills.sh installs69model-pruningorchestra-research/ai-research-skillsReduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsi1Kskills.sh installs
model-pruningorchestra-research/ai-research-skillsReduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsi1Kskills.sh installs70sparse-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 w1Kskills.sh installs
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 w1Kskills.sh installs71implementing-llms-litgptorchestra-research/ai-research-skillsImplements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implement1Kskills.sh installs
implementing-llms-litgptorchestra-research/ai-research-skillsImplements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral). Use when need clean model implement1Kskills.sh installs72llamaguardorchestra-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, cr1Kskills.sh installs
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, cr1Kskills.sh installs73miles-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 trai1Kskills.sh installs
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 trai1Kskills.sh installs74torchforge-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, easy1Kskills.sh installs
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, easy1Kskills.sh installs75nemo-guardrailsorchestra-research/ai-research-skillsNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filte1Kskills.sh installs
nemo-guardrailsorchestra-research/ai-research-skillsNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filte1Kskills.sh installs76pineconeorchestra-research/ai-research-skillsManaged vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Lo1Kskills.sh installs
pineconeorchestra-research/ai-research-skillsManaged vector database for production AI applications. Fully managed, auto-scaling, with hybrid search (dense + sparse), metadata filtering, and namespaces. Lo1Kskills.sh installs77nnsight-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 interpre1Kskills.sh installs
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 interpre1Kskills.sh installs78rwkv-architectureorchestra-research/ai-research-skillsRNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation1Kskills.sh installs
rwkv-architectureorchestra-research/ai-research-skillsRNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential). Linux Foundation1Kskills.sh installs79skypilot-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 sp1Kskills.sh installs
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 sp1Kskills.sh installs80autogpt-agentsorchestra-research/ai-research-skillsAutonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or 1Kskills.sh installs
autogpt-agentsorchestra-research/ai-research-skillsAutonomous AI agent platform for building and deploying continuous agents. Use when creating visual workflow agents, deploying persistent autonomous agents, or 1Kskills.sh installs81blip-2-vision-languageorchestra-research/ai-research-skillsVision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrie1Kskills.sh installs
blip-2-vision-languageorchestra-research/ai-research-skillsVision-language pre-training framework bridging frozen image encoders and LLMs. Use when you need image captioning, visual question answering, image-text retrie1Kskills.sh installs82constitutional-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 1Kskills.sh installs
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 1Kskills.sh installs83langsmith-observabilityorchestra-research/ai-research-skillsLLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring p1Kskills.sh installs
langsmith-observabilityorchestra-research/ai-research-skillsLLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring p1Kskills.sh installs84nemo-evaluator-sdkorchestra-research/ai-research-skillsEvaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluatio1Kskills.sh installs
nemo-evaluator-sdkorchestra-research/ai-research-skillsEvaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluatio1Kskills.sh installs85llavaorchestra-research/ai-research-skillsLarge Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language mo1Kskills.sh installs
llavaorchestra-research/ai-research-skillsLarge Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language mo1Kskills.sh installs86phoenix-observabilityorchestra-research/ai-research-skillsOpen-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations1Kskills.sh installs
phoenix-observabilityorchestra-research/ai-research-skillsOpen-source AI observability platform for LLM tracing, evaluation, and monitoring. Use when debugging LLM applications with detailed traces, running evaluations1Kskills.sh installs87lambda-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 filesyste1Kskills.sh installs
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 filesyste1Kskills.sh installs88ml-training-recipesorchestra-research/ai-research-skillsBattle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers train996skills.sh installs
ml-training-recipesorchestra-research/ai-research-skillsBattle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers train996skills.sh installs89presenting-conference-talksorchestra-research/ai-research-skillsGenerates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral 993skills.sh installs
presenting-conference-talksorchestra-research/ai-research-skillsGenerates conference presentation slides (Beamer LaTeX PDF and editable PPTX) from a compiled paper with speaker notes and talk script. Use when preparing oral 993skills.sh installs90systems-paper-writingorchestra-research/ai-research-skillsComprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns990skills.sh installs
systems-paper-writingorchestra-research/ai-research-skillsComprehensive guide for writing systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides paragraph-level structural blueprints, writing patterns990skills.sh installs91experiment-tracking-swanlaborchestra-research/ai-research-skillsProvides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media loggi961skills.sh installs
experiment-tracking-swanlaborchestra-research/ai-research-skillsProvides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media loggi961skills.sh installs92fine-tuning-openvla-oftorchestra-research/ai-research-skillsFine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning 926skills.sh installs
fine-tuning-openvla-oftorchestra-research/ai-research-skillsFine-tunes and evaluates OpenVLA-OFT and OpenVLA-OFT+ policies for robot action generation with continuous action heads, LoRA adaptation, and FiLM conditioning 926skills.sh installs93fine-tuning-serving-openpiorchestra-research/ai-research-skillsFine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and925skills.sh installs
fine-tuning-serving-openpiorchestra-research/ai-research-skillsFine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and925skills.sh installs94evaluating-cosmos-policyorchestra-research/ai-research-skillsEvaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running head921skills.sh installs
evaluating-cosmos-policyorchestra-research/ai-research-skillsEvaluates NVIDIA Cosmos Policy on LIBERO and RoboCasa simulation environments. Use when setting up cosmos-policy for robot manipulation evaluation, running head921skills.sh installs95evolving-ai-agentsorchestra-research/ai-research-skillsProvides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving 897skills.sh installs
evolving-ai-agentsorchestra-research/ai-research-skillsProvides guidance for automatically evolving and optimizing AI agents across any domain using LLM-driven evolution algorithms. Use when building self-improving 897skills.sh installs