🎯Skills97
Comprehensive open-source library of 77 AI research engineering skills across 20 categories including model architecture, fine-tuning, distributed training, RAG, multimodal, and ML paper writing.
A skill from the AI Research Engineering Skills library, a comprehensive open-source collection of 82 skills across 20 categories that provide engineering capabilities for AI agents to conduct research experiments, including training, evaluation, deployment, and agent building.
A Claude Code skill providing structured ideation frameworks with 10 complementary lenses for discovering high-impact AI research directions, part of the Orchestra Research AI research engineering skills library with 85+ skills across 21 categories.
An AI research engineering skill for Qdrant, a high-performance Rust-powered vector search engine with hybrid search and filtering capabilities, part of the 83-skill AI Research Skills library covering RAG and retrieval workflows.
A skill from the AI Research Skills library, a comprehensive open-source collection of 87 skills across 22 categories that enable AI agents to autonomously conduct AI research from idea generation through experiment execution to paper writing.
A comprehensive open-source library of 82 AI research engineering skills across 20 categories (fine-tuning, distributed training, RAG, multimodal, safety, and more) that enable coding agents to conduct AI research experiments.
AI research skill for long-context model techniques and optimizations, part of an 87-skill library enabling autonomous AI research across 22 categories from idea to paper.
AI research engineering skill for optimizing attention mechanisms with Flash Attention techniques, part of a comprehensive 83-skill library covering model architecture, training, and deployment.
A speculative decoding skill from the AI Research Engineering Skills library, part of a collection of 82 research skills covering emerging AI techniques. Provides expert-level guidance on speculative decoding for accelerating LLM inference.
Part of the AI Research Engineering Skills Library, a comprehensive collection of 83 skills across 20 categories covering the full AI research lifecycle. Provides expert-level guidance for knowledge distillation with real code examples and production-ready workflows for frameworks like Megatron-LM, vLLM, and TRL.
Part of the AI Research Engineering Skills Library covering 82 skills across 20 categories. This skill focuses on AutoGPT for building autonomous AI agents, one of the library's agent framework tools alongside LangChain, LlamaIndex, and CrewAI.
AI research skill for serving large language models with vLLM, part of the most comprehensive open-source library enabling AI agents to autonomously conduct research from idea to paper.
Part of the AI Research Engineering Skills Library covering 82 skills across 20 categories. This skill focuses on model merging techniques, one of the library's emerging techniques alongside MoE, long context, speculative decoding, distillation, and pruning.
An AI research engineering skill for serverless GPU computing with Modal, part of the Infrastructure category. From the AI Research Skills library providing 83 expert-level skills spanning the full AI research lifecycle from model architecture to deployment.
Part of the AI Research Engineering Skills Library, providing AI agents with comprehensive skills for conducting AI research including model architecture, fine-tuning, data processing, and distributed training best practices.
An AI research skill for text-to-image generation using Stable Diffusion via HuggingFace Diffusers, including SDXL and ControlNet support. Part of the AI Research Skills library with 87 skills enabling AI agents to autonomously conduct research from idea to paper.
Part of a comprehensive AI research engineering skills library with 83 skills across 20 categories including model architecture, fine-tuning, distributed training, inference, RAG, multimodal, and MLOps. Enables AI agents to autonomously implement and execute AI research experiments from data preparation to deployment.
An AI research engineering skill for audio generation using Meta's AudioCraft framework. Part of the Orchestra Research AI Research Skills library, which provides 82 skills across 20 categories including model architecture, fine-tuning, multimodal, and inference to enable coding agents to execute AI research engineering tasks.
An AI research skill for remote neural network interpretability via NDIF, enabling experiments on 70B+ parameter models. Part of the AI Research Skills library that empowers AI agents to autonomously conduct AI research from idea to paper.
Part of the AI Research Engineering Skills Library, providing AI agents with comprehensive skills for conducting AI research including model architecture, fine-tuning, data processing, and distributed training best practices.
An AI research skill for pyvene, Stanford's causal intervention library with declarative configs for mechanistic interpretability, part of the AI Research Skills library with 87 skills enabling autonomous research from idea to paper.
An AI research skill for Sparse Autoencoder (SAE) training and analysis for feature discovery in neural networks, using SAELens. Part of the AI Research Skills library covering mechanistic interpretability with 83 skills for autonomous AI research.
An AI research engineering skill for multi-cloud GPU orchestration using SkyPilot, part of the Infrastructure category. From the AI Research Skills library providing expert-level skills spanning the full AI research lifecycle from data preparation to deployment.
An AI research skill for Constitutional AI, implementing AI-driven self-improvement via principles for safety and alignment, part of the AI Research Skills library with 87 skills enabling autonomous research from idea to paper.
An AI research skill for working with Pinecone, a managed vector database with auto-scaling and sub-100ms latency, part of the AI Research Skills library with 87 skills enabling AI agents to autonomously conduct research from idea to paper.
An AI research skill for Sentence Transformers, providing access to 5000+ embedding models with multilingual support, part of the AI Research Skills library with 82 skills for autonomous AI research experimentation.
Part of an AI research engineering skills library with 77 skills across 20 categories, enabling AI agents to autonomously implement and execute AI research experiments from data preparation and model training to evaluation and deployment.
A skill from the AI Research Skills library for model pruning techniques, covering methods like Wanda and SparseGPT to achieve 50% sparsity with less than 1% accuracy loss. Part of a comprehensive 87-skill collection enabling AI agents to autonomously conduct AI research from idea to paper.
An AI research engineering skill for quantizing models using the bitsandbytes library. Part of the Orchestra Research AI Research Skills library, which provides 82 skills across 20 categories to enable coding agents to execute AI research engineering tasks such as model optimization and inference.
An AI research skill for Microsoft DeepSpeed ZeRO optimization for distributed training, part of the AI Research Skills library with 82 skills enabling AI agents to conduct research experiments from data preparation to model deployment.
Part of the AI Research Engineering Skills Library covering 82 skills across 20 categories. This skill focuses on Lightning (PyTorch Lightning) for distributed training, one of the library's distributed training tools alongside DeepSpeed, FSDP, and Accelerate.
A skill from the AI Research Skills library for HuggingFace Accelerate, covering its 4-line API for distributed training across multiple GPUs and machines. Part of a comprehensive 87-skill collection enabling AI agents to autonomously conduct AI research from idea to paper.
Part of the AI Research Skills Library, the most comprehensive open-source skills library enabling AI agents to autonomously conduct AI research from idea to paper, covering frameworks, model architectures, and evaluation methodologies.
Part of the AI Research Engineering Skills Library, providing AI agents with comprehensive skills for conducting AI research including model architecture, fine-tuning, data processing, and distributed training best practices.
Part of the AI Research Engineering Skills Library, providing AI agents with comprehensive skills for conducting AI research including model architecture, fine-tuning, data processing, and distributed training best practices.
Part of the AI Research Engineering Skills Library, providing AI agents with comprehensive skills for conducting AI research including model architecture, fine-tuning, data processing, and distributed training best practices.
Part of the AI Research Skills Library by Orchestra Research, a comprehensive collection of 87 skills enabling AI agents to autonomously conduct AI research from idea generation through experiment execution to paper writing, covering training, evaluation, and deployment.
Part of the AI Research Skills Library, the most comprehensive open-source skills library enabling AI agents to autonomously conduct AI research from idea to paper, covering frameworks, model architectures, and evaluation methodologies.
Part of the AI Research Engineering Skills Library, providing AI agents with comprehensive skills for conducting AI research including model architecture, fine-tuning, data processing, and distributed training best practices.
Part of the AI Research Engineering Skills Library, providing AI agents with comprehensive skills for conducting AI research including model architecture, fine-tuning, data processing, and distributed training best practices.
A Claude Code skill providing cognitive science frameworks including bisociation, structure-mapping, and constraint manipulation for generating genuinely novel AI research ideas, part of the Orchestra Research AI research skills library.
Part of the AI Research Skills Library, the most comprehensive open-source skills library enabling AI agents to autonomously conduct AI research from idea to paper, covering frameworks, model architectures, and evaluation methodologies.
A reinforcement learning training skill from the AI Research Skills Library, a comprehensive open-source collection of 87 skills across 22 categories enabling AI agents to autonomously conduct AI research from idea generation through experiment execution to paper writing.
Part of the AI Research Engineering Skills Library, providing AI agents with comprehensive skills for conducting AI research including model architecture, fine-tuning, data processing, and distributed training best practices.
Part of the AI Research Engineering Skills Library, providing AI agents with comprehensive skills for conducting AI research including model architecture, fine-tuning, data processing, and distributed training best practices.
Part of the AI Research Skills library by Orchestra Research, providing guidance for implementing prompt guard and safety mechanisms in AI systems to detect and prevent prompt injection attacks.
Part of the AI Research Skills library by Orchestra Research, providing guidance for provisioning and managing Lambda Labs GPU cloud instances for AI/ML training workloads.
Part of the AI Research Engineering Skills library, providing Ray Train-specific guidance for distributed AI model training workflows within AI agent-driven research environments.
AI research engineering skill for using Unsloth to perform efficient LLM fine-tuning, part of a comprehensive library of 82 skills that enable coding agents to conduct AI research experiments.
AI research skill for implementing NVIDIA NeMo Guardrails, enabling programmable guardrails with the Colang language to control LLM behavior and enforce safety policies.
Provides AI research engineering guidance for DSPy, a framework for programming language model pipelines with automatic prompt optimization, part of the Orchestra Research AI Research Skills library covering prompt engineering techniques.
Provides AI research engineering guidance for building applications with LangChain, part of the Orchestra Research AI Research Skills library covering agent frameworks and LLM application development.
Provides AI research engineering guidance for Group Relative Policy Optimization (GRPO) reinforcement learning training, part of the Orchestra Research AI Research Skills library covering post-training techniques for language models.
Provides AI research engineering guidance for llama.cpp, a C++ inference engine for running large language models locally, part of the Orchestra Research AI Research Skills library covering inference optimization techniques.
AI research skill for implementing Meta's LlamaGuard, a safety classifier that evaluates LLM inputs and outputs for harmful content, part of the AI Research Skills library.
Provides AI research engineering guidance for using SentencePiece tokenization, part of the Orchestra Research AI Research Skills library covering tokenization techniques for language model training and inference.
AI research skill providing expert guidance on OpenRLHF, a full RLHF (Reinforcement Learning from Human Feedback) training pipeline built on Ray and vLLM for scalable post-training of language models.
Provides AI research engineering guidance for GPTQ post-training quantization of large language models, part of the Orchestra Research AI Research Skills library covering optimization techniques for reducing model size and inference costs.
Provides AI research engineering guidance for MLflow experiment tracking and model management, part of the Orchestra Research AI Research Skills library covering MLOps workflows for AI research.
AI research skill for using LLaMA-Factory, a WebUI-based no-code fine-tuning framework that simplifies training and customizing large language models without writing code.
AI research skill for working with NanoGPT, Andrej Karpathy's educational GPT implementation in approximately 300 lines of code, designed for learning and experimenting with transformer architectures.
AI research skill for using SGLang, a high-performance inference serving framework with RadixAttention that provides 5-10x faster structured generation for AI agents and complex workflows.
AI research skill that provides expert-level guidance for working with OpenAI's CLIP vision-language model, covering zero-shot image classification, text-image similarity, and multimodal embeddings.
AI research skill for using Microsoft Research's Guidance library, which enables constrained generation with regex and grammars to produce structured and reliable LLM outputs.
AI research skill providing expert guidance on Weights & Biases (W&B) for experiment tracking, hyperparameter sweeps, artifact management, and model registry in machine learning workflows.
AI research skill that provides expert guidance on Mamba state-space models, which achieve O(n) sequence complexity and up to 5x faster inference than Transformers, ideal for long-context tasks.
Part of the AI Research Skills library by Orchestra Research, providing guidance for SimPO (Simple Preference Optimization) training workflows for aligning language models without a reference model.
Provides expert-level guidance on NVIDIA NeMo Curator for AI dataset preparation and curation. Part of the AI Research Engineering Skills library covering 83+ skills across the full AI research lifecycle, from data processing to model deployment.
AI research engineering skill providing guidance on evaluating LLMs using evaluation harnesses, from a comprehensive open-source library of research skills for AI agents.
Provides AI research engineering guidance for TensorRT-LLM, NVIDIA's high-performance inference library for large language models, part of the Orchestra Research AI Research Skills library covering inference optimization on GPU hardware.
An AI research skill for using the Instructor library to produce structured LLM outputs with Pydantic validation, part of a comprehensive 83-skill library covering the full AI research engineering lifecycle.
Part of the AI Research Skills library by Orchestra Research, providing guidance for Mixture of Experts (MoE) model training including architecture setup, expert routing, and load balancing.
Provides expert-level guidance on Chroma, an open-source vector database for building RAG (Retrieval-Augmented Generation) applications. Part of the AI Research Engineering Skills library covering 82+ skills for AI research, including embedding storage, similarity search, and retrieval pipelines.
An AI research skill for TensorBoard visualization, profiling, embeddings, and scalars/images monitoring, part of a comprehensive 83-skill library for AI research engineering spanning model training to deployment.
Provides expert-level guidance on implementing LLMs using LitGPT (Lightning AI), covering 20+ clean LLM implementations with production training recipes. Part of the AI Research Engineering Skills library spanning model architecture, fine-tuning, distributed training, and more.
Part of the AI Research Skills library by Orchestra Research, providing guidance for fine-tuning language models using TRL (Transformer Reinforcement Learning) with SFT, RLHF, and DPO methods.
AI research skill providing expert guidance on Outlines, a structured text generation library that uses finite state machines (FSM) for zero-overhead constrained output from language models.
AI research engineering skill providing guidance on LLaVA (Large Language-and-Vision Assistant) implementation, from a comprehensive open-source library of research skills for AI agents.
Part of the AI Research Skills library by Orchestra Research, providing guidance for building and using FAISS (Facebook AI Similarity Search) vector indexes for efficient similarity search in AI applications.
AI research engineering skill providing guidance on MILES reinforcement learning training, from a comprehensive open-source library of research skills for AI agents.
Part of the AI Research Skills library by Orchestra Research, providing guidance for using Axolotl, a tool for streamlined fine-tuning of language models with multi-GPU support and various training methods.
AI research engineering skill providing guidance on distributed LLM pretraining using TorchTitan, from a comprehensive open-source library of research skills for AI agents.
A reinforcement learning training skill for the SLIME framework (THUDM's Megatron+SGLang framework powering GLM-4.x models), part of the AI Research Skills library covering 83 skills across post-training, distributed training, and optimization.
Part of a comprehensive 98-skill AI research library that enables agents to autonomously conduct research from idea to paper, providing guidance on creating publication-quality academic plots and visualizations.
A comprehensive library of 98 skills enabling AI agents to autonomously conduct AI research from idea to paper, covering research orchestration, model training, evaluation, safety, and deployment across 23 categories.
A comprehensive open-source skills library with 98 skills across 23 categories enabling AI agents to autonomously conduct AI research, covering the full pipeline from ideation to paper writing including model architecture, training, evaluation, and MLOps.
A library of 98 skills across 23 categories enabling AI agents to autonomously conduct AI research, from literature review and experiment design to paper writing. Covers areas like fine-tuning, reinforcement learning, robotics, and multimodal AI.
A comprehensive open-source skills library with 98 skills across 23 categories that enables AI agents to autonomously conduct AI research, covering the full workflow from idea generation and experiment execution to paper writing.
A comprehensive open-source skills library with 98 skills across 23 categories that enables AI agents to autonomously conduct AI research from idea to paper, covering areas like model architecture, fine-tuning, distributed training, safety and alignment, and multimodal learning.
Part of the AI Research Skills library with 98 skills enabling AI agents to autonomously conduct research from idea to paper, covering model architecture, fine-tuning, tokenization, and production training workflows.
Part of the AI Research Skills library with 98 skills across 23 categories, enabling AI agents to autonomously conduct research from ideation to paper writing. Covers model architecture, fine-tuning, distributed training, evaluation, safety, and more.
A comprehensive open-source skills library with 98 skills across 23 categories that enable AI agents to autonomously conduct AI research from idea to paper. Covers model architecture, fine-tuning, distributed training, inference, evaluation, safety and alignment, RAG, multimodal, and more.
A comprehensive open-source skills library that enables AI agents to autonomously conduct AI research, from generating ideas to writing papers. Provides a full research workflow pipeline for AI-powered academic work.
Part of a comprehensive open-source skills library that enables AI agents to autonomously conduct AI research, covering the full pipeline from idea generation to paper writing.
A comprehensive library of 98 AI research skills enabling agents to autonomously conduct research from idea generation through experiment execution to paper writing. Covers 23 categories including model architecture, fine-tuning, distributed training, and evaluation.
A comprehensive skills library enabling AI agents to autonomously conduct AI research, covering the full workflow from generating ideas to writing papers.
Skill