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.
46,100 skills from 2,198 repositories · updated 3 hours ago
46,098 skills
- 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★ 14.1K↓ —
- interview-cheatsheetwanshuiyin/Auto-claude-code-research-in-sleepGenerate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.PlanningNo warnings★ 18.3K↓ —
- 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★ 14.1K↓ —
- wiki-changelogmicrosoft/skillsAnalyzes git commit history and generates structured changelogs categorized by change type. Use when the user asks about recent changes, wants a changelog, or needs to understand what changed in the repository.OfficialEngineeringNo warnings★ 3.2K↓ —
- qdrant-vector-searchOrchestra-Research/AI-Research-SKILLsHigh-performance vector similarity search engine for RAG and semantic search. Use when building production RAG systems requiring fast nearest neighbor search, hybrid search with filtering, or scalable vector storage with Rust-powered performance.OtherNo warnings★ 14.1K↓ —
- dart-fix-runtime-errorsflutter/agent-pluginsUses get_runtime_errors and lsp to fetch an active stack trace, locate the failing line, apply a fix, and verify resolution via hot_reload.OfficialOtherNo warnings★ 3.1K↓ —
- azure-eventgrid-javamicrosoft/skillsBuild event-driven applications with Azure Event Grid SDK for Java. Use when publishing events, implementing pub/sub patterns, or integrating with Azure services via events.OfficialDevOpsNo warnings★ 3.2K↓ —
- embodiment-descriptionwanshuiyin/Auto-claude-code-research-in-sleepWrite detailed embodiment descriptions for patent specifications. Use when user says "撰写实施例", "write embodiment", "实施例描述", "detailed description", or wants to describe how to practice an invention.WritingNo warnings★ 18.3K↓ —Also in 1 other repo
- 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★ 14.1K↓ —
- krillinai-ttskrillinai/OpenCreatorUse when generating target-language dubbing with KrillinAI CLI from SRT subtitles, including TTS audio creation and optional dubbed video generation.MediaNo 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★ 14.1K↓ —
- speculative-decodingOrchestra-Research/AI-Research-SKILLsAccelerate LLM inference using speculative decoding, Medusa multiple heads, and lookahead decoding techniques. Use when optimizing inference speed (1.5-3.6× speedup), reducing latency for real-time applications, or deploying models with limited compute. Covers draft models, tree-based attention, Jacobi iteration, parallel token generation, and production deployment strategies.PlanningNo warnings★ 14.1K↓ —
- knowledge-distillationOrchestra-Research/AI-Research-SKILLsCompress large language models using knowledge distillation from teacher to student models. Use when deploying smaller models with retained performance, transferring GPT-4 capabilities to open-source models, or reducing inference costs. Covers temperature scaling, soft targets, reverse KLD, logit distillation, and MiniLLM training strategies.DevOpsNo warnings★ 14.1K↓ —
- sentence-transformersOrchestra-Research/AI-Research-SKILLsFramework for state-of-the-art sentence, text, and image embeddings. Provides 5000+ pre-trained models for semantic similarity, clustering, and retrieval. Supports multilingual, domain-specific, and multimodal models. Use for generating embeddings for RAG, semantic search, or similarity tasks. Best for production embedding generation.MediaNo warnings★ 14.1K↓ —
- dart-use-doc-examplesflutter/agent-pluginsHow to inject external code examples into Dartdoc using the {@example} directive, and how to filter those files using #hide, #region, and #endregion tags.OfficialEngineeringNo warnings★ 3.1K↓ —
- faissOrchestra-Research/AI-Research-SKILLsFacebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.OtherNo warnings★ 14.1K↓ —
- research-refine-pipelinewanshuiyin/Auto-claude-code-research-in-sleepRun an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.ScienceNo warnings★ 18.3K↓ —
- cloud-solution-architectmicrosoft/skillsTransform the agent into a Cloud Solution Architect following Azure Architecture Center best practices. Use when designing cloud architectures, reviewing system designs, selecting architecture styles, applying cloud design patterns, making technology choices, or conducting Well-Architected Framework reviews.OfficialPlanningNo warnings★ 3.2K↓ —
- ablation-plannerwanshuiyin/Auto-claude-code-research-in-sleepUse when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.PlanningNo warnings★ 18.3K↓ —
- cost-optimizationmicrosoft/skillsOptimize existing Azure resources and analyze Reservations or Savings Plans. WHEN: "optimize Azure costs", "reduce cloud spending", "rightsize resources", "find idle resources", "orphaned disk", "deleted VM still charged", "public IP still charging", "reservation utilization", "Savings Plan coverage", "commitment recommendation", "why is pay-as-you-go still charged". DO NOT USE FOR: cost spikes, forecasts, pricing estimates, budgets, or governance.OfficialDevOpsNo warnings★ 3.2K↓ —Also in 1 other repo
- azure-communication-callautomation-javamicrosoft/skillsBuild call automation workflows with Azure Communication Services Call Automation Java SDK. Use when implementing IVR systems, call routing, call recording, DTMF recognition, text-to-speech, or AI-powered call flows.OfficialDevOpsNo warnings★ 3.2K↓ —
- workers-profilingcloudflare/skillsProfile or debug CPU usage and memory allocation in deployed Cloudflare Workers and Durable Objects. Then use this information to optimize your code.OfficialDevOpsNo warnings★ 3.2K↓ —
- 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★ 14.1K↓ —
- sglangOrchestra-Research/AI-Research-SKILLsFast structured generation and serving for LLMs with RadixAttention prefix caching. Use for JSON/regex outputs, constrained decoding, agentic workflows with tool calls, or when you need 5× faster inference than vLLM with prefix sharing. Powers 300,000+ GPUs at xAI, AMD, NVIDIA, and LinkedIn.MarketingNo warnings★ 14.1K↓ —
distributed-llm-pretraining-torchtitan
Orchestra-Research/AI-Research-SKILLs
OtherUpdated Oct 11, 2026
From the author
Provides 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.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill distributed-llm-pretraining-torchtitan -a claude-code
Installs to .claude/skills/distributed-llm-pretraining-torchtitan/ · 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 (5)
- SKILL.md
- references/checkpoint.md
- references/custom-models.md
- references/float8.md
- references/fsdp.md