Claude Code, Codex, and Cursor
Agent skills for Claude Code, Codex, and Cursor
Find skills that work in Claude Code, Codex, and Cursor. See what each one does, look at its files, then install it with one command.
Browse all skills
Category
Tool
Intent
20 skills loaded
Orchestra Research/openpi
Fine-tune and serve Physical Intelligence OpenPI models (pi0, pi0-fast, pi0.5) using JAX or PyTorch backends for robot policy inference across ALOHA, DROID, and LIBERO environments. Use when adapting pi0 models to custom datasets, conver...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/nnsight
Provides 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...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/nemo-guardrails
NVIDIA'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. Product...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/nemo-evaluator
Evaluates LLMs across 100+ benchmarks from 18+ harnesses (MMLU, HumanEval, GSM8K, safety, VLM) with multi-backend execution. Use when needing scalable evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade p...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/nemo-curator
GPU-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 wit...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/nanogpt
Educational 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)...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/moe-training
Train Mixture of Experts (MoE) models using DeepSpeed or HuggingFace. Use when training large-scale models with limited compute (5× cost reduction vs dense models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or s...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/model-pruning
Reduce LLM size and accelerate inference using pruning techniques like Wanda and SparseGPT. Use when compressing models without retraining, achieving 50% sparsity with minimal accuracy loss, or enabling faster inference on hardware accel...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/model-merging
Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/modal
Serverless 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.
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/mlflow
Track ML experiments, manage model registry with versioning, deploy models to production, and reproduce experiments with MLflow - framework-agnostic ML lifecycle platform
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/ml-training-recipes
Battle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision,...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/ml-paper-writing
Write publication-ready ML/AI papers for NeurIPS, ICML, ICLR, ACL, AAAI, COLM. Use when drafting papers from research repos, structuring arguments, verifying citations, or preparing camera-ready submissions. For systems venues (OSDI, NSD...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/miles
Provides 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.
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/megatron-core
Trains 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/sequenc...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/mamba
State-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...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/long-context
Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ tokens), extending pre-trained models beyond original context limits, or implement...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/lm-evaluation-harness
Evaluates LLMs across 60+ academic benchmarks (MMLU, HumanEval, GSM8K, TruthfulQA, HellaSwag). Use when benchmarking model quality, comparing models, reporting academic results, or tracking training progress. Industry standard used by El...
Published by Orchestra Research
Imported from source. Claim this skill
Orchestra Research/llava
Large Language and Vision Assistant. Enables visual instruction tuning and image-based conversations. Combines CLIP vision encoder with Vicuna/LLaMA language models. Supports multi-turn image chat, visual question answering, and instruct...
Published by Orchestra Research
Imported from source. Claim this skill