Skip to content

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: 1 of 7 days recorded. Until then this list is ordered by the most recent content change.

7912 skills

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 targets. The outer loop synthesizes results, identifies patterns, and steers research direction. Routes to domain-specific skills for execution, supports continuous agent operation via Claude Code /loop and OpenClaw heartbeat, and produces research presentations and papers. Use when starting a research project, running autonomous experiments, or managing a multi-hypothesis research effort.Stars: 14kUpdated Claude CodeCodexUnverifiedInstall
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 implementations, educational understanding of architectures, or production fine-tuning with LoRA/QLoRA. Single-file implementations, no abstraction layers.Stars: 14kUpdated Claude CodeCodexUnverifiedInstall
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 design. Mamba-1 (d_state=16) and Mamba-2 (d_state=128, multi-head). Models 130M-2.8B on HuggingFace.Stars: 14kUpdated Claude CodeCodexUnverifiedInstall
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. Perfect for understanding GPT architecture from scratch. Train on Shakespeare (CPU) or OpenWebText (multi-GPU).Stars: 14kUpdated Claude CodeCodexUnverifiedInstall
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 Foundation AI project. Production at Windows, Office, NeMo. RWKV-7 (March 2025). Models up to 14B parameters.Stars: 14kUpdated Claude CodeCodexUnverifiedInstall
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 custom models at scale from 8 to 512+ GPUs with Float8, torch.compile, and distributed checkpointing.Stars: 14kUpdated Claude CodeCodexUnverifiedInstall
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. Train custom vocabularies, track alignments, handle padding/truncation. Integrates seamlessly with transformers. Use when you need high-performance tokenization or custom tokenizer training.Stars: 14kUpdated Claude CodeCodexUnverifiedInstall
sentencepieceOrchestra-Research/AI-Research-SKILLsLanguage-independent tokenizer treating text as raw Unicode. Supports BPE and Unigram algorithms. Fast (50k sentences/sec), lightweight (6MB memory), deterministic vocabulary. Used by T5, ALBERT, XLNet, mBART. Train on raw text without pre-tokenization. Use when you need multilingual support, CJK languages, or reproducible tokenization.Stars: 14kUpdated Claude CodeCodexUnverifiedInstall
axolotlOrchestra-Research/AI-Research-SKILLsExpert guidance for fine-tuning LLMs with Axolotl - YAML configs, 100+ models, LoRA/QLoRA, DPO/KTO/ORPO/GRPO, multimodal supportStars: 14kUpdated Claude CodeCodexUnverifiedInstall
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 supportStars: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
unslothOrchestra-Research/AI-Research-SKILLsExpert guidance for fast fine-tuning with Unsloth - 2-5x faster training, 50-80% less memory, LoRA/QLoRA optimizationStars: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
grpo-rl-trainingOrchestra-Research/AI-Research-SKILLsExpert guidance for GRPO/RL fine-tuning with TRL for reasoning and task-specific model trainingStars: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall
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: 14kUpdated Claude CodeCodexUnverifiedInstall