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.
45,585 skills from 2,204 repositories · updated 6 minutes ago
45,583 skills
- expo-domexpo/skillsUse Expo DOM components to run web code in a webview on native and as-is on web. Migrate web code to native incrementally. For the end-to-end migration of a whole web app, use the expo-web-to-native skill.OfficialEngineeringNo warnings★ 3K↓ —
- 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★ 13.9K↓ —
- 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.TestingNo warnings★ 13.9K↓ —
- grill-with-docsflutter/agent-pluginsGrilling session that challenges your plan against the existing domain model, sharpens terminology, and updates documentation (CONTEXT.md, ADRs) inline as decisions crystallise. Use when user wants to stress-test a plan against their project's language and documented decisions.OfficialTestingNo warnings★ 3.1K↓ —
- 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★ 13.9K↓ —
- 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★ 13.9K↓ —
- natural-writingflutter/agent-pluginsContains well-defined rules for creating natural, accurate, and readable writing. Use whenever authoring longer text, like analysis documents, PR or CL descriptions, or documentation.OfficialWritingNo warnings★ 3.1K↓ —
- ara-compilerOrchestra-Research/AI-Research-SKILLsCompiles any research input — PDF papers, GitHub repositories, experiment logs, code directories, or raw notes — into a complete Agent-Native Research Artifact (ARA) with cognitive layer (claims, concepts, heuristics), physical layer (configs, code stubs), exploration graph, and grounded evidence. Use when ingesting a paper or codebase into a structured, machine-executable knowledge package, building an ARA from scratch, or converting research outputs into a falsifiable, agent-traversable form.DocumentsNo warnings★ 13.9K↓ —
- winui-appopenai/skillsBootstrap, develop, and design modern WinUI 3 desktop applications with C# and the Windows App SDK using official Microsoft guidance, WinUI Gallery patterns, Windows App SDK samples, and CommunityToolkit components. Use when creating a brand new app, preparing a machine for WinUI, reviewing, refactoring, planning, troubleshooting, environment-checking, or setting up WinUI 3 XAML, controls, navigation, windowing, theming, accessibility, responsiveness, performance, deployment, or related Windows app design and development work.OfficialDevOpsNo warnings★ 28.3K↓ —Also in 1 other repo
- code-documentationflutter/agent-pluginsGuide for writing effective code documentation, including docstrings, JSDoc, dartdoc, and implementation comments. Use this skill when writing new code, adding features, or improving existing documentation in Dart, Python, or TypeScript to ensure clarity and maintainability.OfficialEngineeringNo warnings★ 3.1K↓ —
- arxivwanshuiyin/Auto-claude-code-research-in-sleepSearch, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv to the local paper library.ScienceNo warnings★ 18K↓ —
- training-llms-megatronOrchestra-Research/AI-Research-SKILLsTrains 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/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.ProductivityNo warnings★ 13.9K↓ —
- eas-observeexpo/skillsUse for anything related to EAS Observe - adding `expo-observe` to an Expo project (AppMetricsRoot/ObserveRoot HOC, markInteractive and ObserveInteractiveMarker, the useObserve hook, the Expo Router / React Navigation integrations for per-route metrics, user-defined events via `Observe.logEvent`, error reporting via ObserveErrorBoundary and `Observe.reportError`, native crash reporting, source map upload for symbolicated stack traces, and runtime config such as sampleRate and dispatchInDebug), querying via the EAS CLI (`eas observe:metrics-summary`, `observe:metrics`, `observe:routes`, `observe:events`, `observe:session`, `observe:versions`, `observe:errors`, `observe:event`), interpreting the resulting metrics (cold/warm launch, TTR, TTI, navigation cold/warm TTR, update download, and the TTI frameRate/device/network params for triaging slow startups), or shipping an Observe integration inside a third-party package.OfficialEngineeringNo warnings★ 3K↓ —
- 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★ 13.9K↓ —
- model-mergingOrchestra-Research/AI-Research-SKILLsMerge 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 experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task Arithmetic, linear merging, and production deployment strategies.DevOpsNo warnings★ 13.9K↓ —
- 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★ 13.9K↓ —
- 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★ 13.9K↓ —
- api-reviewflutter/agent-pluginsReviews the specified code against the canonical API Design guidelines. Use this skill when the user asks for an API review or to check code against API design principles.OfficialEngineeringNo warnings★ 3.1K↓ —
- wiki-enrichwanshuiyin/Auto-claude-code-research-in-sleepFill in the per-paper TODO sections of research-wiki/papers/<slug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers/ as TODO scaffolds.ScienceNo warnings★ 18K↓ —
- flutter-build-responsive-layoutflutter/agent-pluginsUse `LayoutBuilder`, `MediaQuery`, or `Expanded/Flexible` to create a layout that adapts to different screen sizes. Use when you need the UI to look good on both mobile and tablet/desktop form factors.OfficialDesignNo warnings★ 3.1K↓ —
- ml-paper-writingOrchestra-Research/AI-Research-SKILLsWrite 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, NSDI, ASPLOS, SOSP), use systems-paper-writing instead.ScienceNo warnings★ 13.9K↓ —
- flutter-setup-declarative-routingflutter/agent-pluginsConfigure `MaterialApp.router` using a package like `go_router` for advanced URL-based navigation. Use when developing web applications or mobile apps that require specific deep linking and browser history support.OfficialBrowserNo warnings★ 3.1K↓ —
- dart-resolve-package-conflictsflutter/agent-pluginsWorkflow for fixing package version conflicts. Use this when `pub get` fails due to incompatible package versions.OfficialProductivityNo warnings★ 3.1K↓ —
- flutter-implement-json-serializationflutter/agent-pluginsCreate model classes with `fromJson` and `toJson` methods using `dart:convert`. Use when manually mapping JSON keys to class properties for simple data structures.OfficialOtherNo warnings★ 3.1K↓ —
training-llms-megatron
Orchestra-Research/AI-Research-SKILLs
ProductivityUpdated Oct 11, 2026
From the author
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/sequence/context/expert parallelism. Production-ready framework used for Nemotron, LLaMA, DeepSeek.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill training-llms-megatron -a claude-code
Installs to .claude/skills/training-llms-megatron/ · 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/benchmarks.md
- references/parallelism-guide.md
- references/production-examples.md
- references/training-recipes.md