Agent skills you can check before you install
Public SKILL.md skills from GitHub repositories with 50+ stars and from the vendors themselves, scanned and scored. Install any of them with one command in Claude Code, Cursor, Codex, GitHub Copilot or Gemini CLI.
46,700 skills from 2,243 repositories · updated 20 hours ago
46,700 skills
- entra-agent-idmicrosoft/skillsProvision Microsoft Entra Agent Identity Blueprints, BlueprintPrincipals, and per-instance Agent Identities via Microsoft Graph, and configure OAuth 2.0 token exchange (fmi_path, OBO, cross-tenant) including the Microsoft Entra SDK for AgentID sidecar. USE FOR: Agent Identity Blueprint, BlueprintPrincipal, agent OAuth, fmi_path token exchange, agent OBO, Workload Identity Federation for agents, polyglot agent auth, Microsoft.Identity.Web.AgentIdentities. DO NOT USE FOR: standard Entra app registration (use entra-app-registration), Microsoft Foundry agent authoring (use microsoft-foundry).OfficialOtherNo warnings★ 3.1K↓ —Also in 2 other repos
- 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 patterns, venue-specific checklists, reviewer guidelines, LaTeX templates, and conference deadlines. Use this skill for all systems conference paper writing.ScienceNo warnings★ 14K↓ —
- 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 laptop to supercomputer with same code. Use when you want clean training loops with built-in best practices.EngineeringNo warnings★ 14K↓ —
- faviconsickn33/agentic-awesome-skillsGenerate favicons from a source imageMediaNo warnings★ 48.6K↓ —
- 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.PlanningNo warnings★ 14K↓ —
- 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.ScienceNo warnings★ 14K↓ —
- 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 models exceed single-GPU memory or when you need DTensor-based sharding with DeviceMesh.ProductivityNo warnings★ 14K↓ —
- 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.OtherNo warnings★ 14K↓ —
- 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% sparsity with minimal accuracy loss, or enabling faster inference on hardware accelerators. Covers unstructured pruning, structured pruning, N:M sparsity, magnitude pruning, and one-shot methods.OtherNo warnings★ 14K↓ —
- 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 models), implementing sparse architectures like Mixtral 8x7B or DeepSeek-V3, or scaling model capacity without proportional compute increase. Covers MoE architectures, routing mechanisms, load balancing, expert parallelism, and inference optimization.PlanningNo warnings★ 14K↓ —
- 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+ tokens), extending pre-trained models beyond original context limits, or implementing efficient positional encodings. Covers rotary embeddings, attention biases, interpolation methods, and extrapolation strategies for LLMs.ProductivityNo warnings★ 14K↓ —
- 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 Ray Tune, fault tolerance, elastic scaling. Use when training massive models across multiple machines or running distributed hyperparameter sweeps.OtherNo warnings★ 14K↓ —
- 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 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.DevOpsNo warnings★ 14K↓ —
- 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.OtherNo warnings★ 14K↓ —
- 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.OtherNo warnings★ 14K↓ —
- 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 (>512 tokens), encountering GPU memory issues with attention, or need faster inference. Supports PyTorch native SDPA, flash-attn library, H100 FP8, and sliding window attention.ProductivityNo warnings★ 14K↓ —
- weibo-uploadNewdreammis/social-auto-upload使用 social-auto-upload 的 `sau weibo` 登录微博并发布视频，可指定封面。Use when 用户要向微博发布视频或检查微博账号状态。OtherNo warnings★ 15.9K↓ —
- 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 inference speed with Outlines - dottxt.ai's structured generation libraryEngineeringNo warnings★ 14K↓ —
- mongodbsickn33/agentic-awesome-skillsAdminister MongoDB databases. Configure replica sets, sharding, and backups. Use when managing MongoDB deployments.DevOpsNo warnings★ 48.6K↓ —
- 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).PlanningNo warnings★ 14K↓ —
- 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 evaluation on local Docker, Slurm HPC, or cloud platforms. NVIDIA's enterprise-grade platform with container-first architecture for reproducible benchmarking.DevOpsNo warnings★ 14K↓ —
- 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 faster inference. Supports INT8, NF4, FP4 formats, QLoRA training, and 8-bit optimizers. Works with HuggingFace Transformers.ProductivityNo warnings★ 14K↓ —
- 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 supportEngineeringNo warnings★ 14K↓ —
- 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 headless GPU evaluations with EGL rendering, or profiling inference latency on cluster or local GPU machines.MediaNo warnings★ 14K↓ —
fine-tuning-serving-openpi
Orchestra-Research/AI-Research-SKILLs
EngineeringUpdated Oct 11, 2026
From the author
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, converting JAX checkpoints to PyTorch, running policy inference servers, or debugging norm stats and GPU memory issues.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill fine-tuning-serving-openpi -a claude-code
Installs to .claude/skills/fine-tuning-serving-openpi/ · Each command fetches the skill straight from GitHub with the open skills CLI.
Download .zip
Byte-identical to the scanned commit, with the repository’s licence and a SOURCE.txt.
What it can touch
Instructions onlyUses the networkLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 93
Security100
Provenance90
Maintenance100
Licence100
Adoption65
Files (6)
- SKILL.md
- references/checkpoints-and-env-map.md
- references/config-recipes.md
- references/pytorch-gotchas.md
- references/remote-client-pattern.md
- references/training-debugging.md