orchestra-research/ai-research-skills

6173

ml-paper-writing Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research…

orchestra-research/ai-research-skills

2K

2

brainstorming-research-ideas Guides researchers through structured ideation frameworks to discover high-impact research directions. Use when explo…

orchestra-research/ai-research-skills

929

3

creative-thinking-for-research Applies cognitive science frameworks for creative thinking to CS and AI research ideation. Use when seeking genuinely…

orchestra-research/ai-research-skills

900

4

academic-plotting Generates publication-quality figures for ML papers from research context. Given a paper section or description, extr…

orchestra-research/ai-research-skills

891

5

mlflow Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments w…

orchestra-research/ai-research-skills

847

6

serving-llms-vllm Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production L…

orchestra-research/ai-research-skills

841

7

faiss Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU…

orchestra-research/ai-research-skills

835

8

tensorrt-llm Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment…

orchestra-research/ai-research-skills

835

9

stable-diffusion-image-generation State-of-the-art text-to-image generation with Stable Diffusion models via HuggingFace Diffusers. Use when generating…

orchestra-research/ai-research-skills

799

10

ray-train Distributed training orchestration across clusters. Scales PyTorch/TensorFlow/HuggingFace from laptop to 1000s of nod…

orchestra-research/ai-research-skills

786

11

weights-and-biases Track ML experiments with automatic logging, visualize training in real-time, optimize hyperparameters with sweeps, a…

orchestra-research/ai-research-skills

772

12

peft-fine-tuning Parameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70…

orchestra-research/ai-research-skills

771

13

huggingface-accelerate Simplest distributed training API. 4 lines to add distributed support to any PyTorch script. Unified API for DeepSpee…

orchestra-research/ai-research-skills

769

14

unsloth Expert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimization

orchestra-research/ai-research-skills

769

15

crewai-multi-agent Multi-agent orchestration framework for autonomous AI collaboration. Use when building teams of specialized agents wo…

orchestra-research/ai-research-skills

767

16

prompt-guard Meta's 86M prompt injection and jailbreak detector. Filters malicious prompts and third-party data for LLM apps. 99%+…

orchestra-research/ai-research-skills

767

17

gguf-quantization GGUF format and llama.cpp quantization for efficient CPU/GPU inference. Use when deploying models on consumer hardwar…

orchestra-research/ai-research-skills

765

18

qdrant-vector-search High-performance vector similarity search engine for RAG and semantic search. Use when building production RAG system…

orchestra-research/ai-research-skills

765

19

audiocraft-audio-generation PyTorch library for audio generation including text-to-music (MusicGen) and text-to-sound (AudioGen). Use when you ne…

orchestra-research/ai-research-skills

764

20

ray-data Scalable data processing for ML workloads. Streaming execution across CPU/GPU, supports Parquet/CSV/JSON/images. Inte…

orchestra-research/ai-research-skills

764

21

knowledge-distillation Compress large language models using knowledge distillation from teacher to student models. Use when deploying smalle…

orchestra-research/ai-research-skills

763

22

evaluating-llms-harness Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking …

orchestra-research/ai-research-skills

762

23

quantizing-models-bitsandbytes Quantizes LLMs to 8-bit or 4-bit for 50-75% memory reduction with minimal accuracy loss. Use when GPU memory is limit…

orchestra-research/ai-research-skills

761

24

autoresearch Orchestrates end-to-end autonomous AI research projects using a two-loop architecture. The inner loop runs rapid expe…

orchestra-research/ai-research-skills

759

25

fine-tuning-with-trl Fine-tune LLMs using reinforcement learning with TRL - SFT for instruction tuning, DPO for preference alignment, PPO/…

orchestra-research/ai-research-skills

758

26

langchain Framework for building LLM-powered applications with agents, chains, and RAG. Supports multiple providers (OpenAI, An…

orchestra-research/ai-research-skills

758

27

llama-cpp Runs LLM inference on CPU, Apple Silicon, and consumer GPUs without NVIDIA hardware. Use for edge deployment, M1/M2/M…

orchestra-research/ai-research-skills

758

28

deepspeed Expert guidance for distributed training with DeepSpeed - ZeRO optimization stages, pipeline parallelism, FP16/BF16/F…

orchestra-research/ai-research-skills

757

29

dspy Build complex AI systems with declarative programming, optimize prompts automatically, create modular RAG systems and…

orchestra-research/ai-research-skills

757

30

segment-anything-model Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images us…

orchestra-research/ai-research-skills

757

31

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

orchestra-research/ai-research-skills

756

32

optimizing-attention-flash Optimizes transformer attention with Flash Attention for 2-4x speedup and 10-20x memory reduction. Use when training/…

orchestra-research/ai-research-skills

756

33

pytorch-lightning High-level PyTorch framework with Trainer class, automatic distributed training (DDP/FSDP/DeepSpeed), callbacks syste…

orchestra-research/ai-research-skills

756

34

tensorboard Visualize training metrics, debug models with histograms, compare experiments, visualize model graphs, and profile pe…

orchestra-research/ai-research-skills

756

35

verl-rl-training Provides guidance for training LLMs with reinforcement learning using verl (Volcano Engine RL). Use when implementing…

orchestra-research/ai-research-skills

756

36

axolotl Expert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimo…

orchestra-research/ai-research-skills

753

37

huggingface-tokenizers Fast tokenizers optimized for research and production. Rust-based implementation tokenizes 1GB in <20 seconds. Suppor…

orchestra-research/ai-research-skills

753

38

long-context Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when…

orchestra-research/ai-research-skills

753

39

sglang Fast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, const…

orchestra-research/ai-research-skills

753

40

hqq-quantization Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision with…

orchestra-research/ai-research-skills

752

41

instructor Extract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse co…

orchestra-research/ai-research-skills

752

42

openrlhf-training High-performance RLHF framework with Ray+vLLM acceleration. Use for PPO, GRPO, RLOO, DPO training of large models (7B…

orchestra-research/ai-research-skills

752

43

sentence-transformers Framework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic s…

orchestra-research/ai-research-skills

752

44

whisper OpenAI's general-purpose speech recognition model. Supports 99 languages, transcription, translation to English, and …

orchestra-research/ai-research-skills

752

45

chroma Open-source embedding database for AI applications. Store embeddings and metadata, perform vector and full-text searc…

orchestra-research/ai-research-skills

751

46

modal-serverless-gpu Serverless GPU cloud platform for running ML workloads. Use when you need on-demand GPU access without infrastructure…

orchestra-research/ai-research-skills

751

47

sentencepiece Language-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences…

orchestra-research/ai-research-skills

751

48

awq-quantization Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when de…

orchestra-research/ai-research-skills

750

49

moe-training Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limit…

orchestra-research/ai-research-skills

750

50

pytorch-fsdp2 Adds PyTorch FSDP2 (fully_shard) to training scripts with correct init, sharding, mixed precision/offload config, and…

orchestra-research/ai-research-skills

750