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.
45,100 skills from 2,196 repositories · updated 7 hours ago
45,100 skills
- golden-rss-emptyyusufkaraaslan/Skill_SeekersUse when testing the empty rss golden buildTestingNo warnings★ 15.2K↓ —
- 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↓ —
- auto-review-loop-llmwanshuiyin/Auto-claude-code-research-in-sleepAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".EngineeringNo warnings★ 18.1K↓ —
- invention-structuringwanshuiyin/Auto-claude-code-research-in-sleepStructure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough idea into a patent-ready structure.OtherNo warnings★ 18.1K↓ —
- skill-builderyusufkaraaslan/Skill_SeekersAutomatically detect source types and build AI skills using Skill Seekers. Use when the user wants to create skills from documentation, repos, PDFs, videos, or other knowledge sources.OtherNo warnings★ 15.2K↓ —
- 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↓ —
- 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★ 18.1K↓ —
- golden-chat-emptyyusufkaraaslan/Skill_SeekersUse when testing the golden_chat_empty golden buildTestingNo warnings★ 15.2K↓ —
- stripe-docsstripe/aiUse when the user or agent needs to read, search, or look up Stripe documentation or API reference. Prefer this over curl or WebFetch for any docs.stripe.com content. Use to fetch gated documentation.OfficialEngineeringNo warnings★ 2K↓ —Also in 4 other repos
- research-pipelinewanshuiyin/Auto-claude-code-research-in-sleepFull end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.ScienceNo warnings★ 18.1K↓ —
- 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↓ —
- 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.SecurityNo warnings★ 14K↓ —
- instructorOrchestra-Research/AI-Research-SKILLsExtract structured data from LLM responses with Pydantic validation, retry failed extractions automatically, parse complex JSON with type safety, and stream partial results with Instructor - battle-tested structured output libraryOtherNo warnings★ 14K↓ —
- monitor-experimentwanshuiyin/Auto-claude-code-research-in-sleepMonitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.OtherNo warnings★ 18.1K↓ —
- golden-pdf-kwyusufkaraaslan/Skill_SeekersUse when testing keyword categorizationDocumentsNo warnings★ 15.2K↓ —
- expo-design-systemexpo/skillsBuild and maintain a design system inside an Expo app - a reusable theme of design tokens (color, spacing, typography, radius, shadow, motion), reusable component structure with variant/size/state prop conventions, and rules for when to extract a repeated view into a shared component. Use when creating or organizing theme files and design tokens (theme.ts / theme/), extending an existing theme or styling library (NativeWind, Tamagui, Restyle, Unistyles) in its own idiom, standardizing styles so screens (including AI-generated ones) look consistent and polished, fixing an app that looks AI-generated or generic instead of native (the named native-slop tells), building an in-app component library, or auditing an app for design-system drift (hardcoded colors, spacing, fonts). For platform styling specifics (semantic colors, HIG rules, native controls) use expo-native-ui; for folder layout of a new app use expo-project-structure.OfficialDesignNo warnings★ 3K↓ —
- eas-update-insightsexpo/skillsCheck the health of published EAS Update: crash rates, install/launch counts, unique users, payload size, and the split between embedded and OTA users per channel. Use when the user asks how an update is performing, whether a rollout is healthy, how many users are on the embedded build vs OTA, or wants to gate CI on update health.OfficialOtherNo warnings★ 3K↓ —
- 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↓ —
- paper-illustrationwanshuiyin/Auto-claude-code-research-in-sleepGenerate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图", "paper illustration", "generate diagram", or needs visual figures for papers.MediaNo warnings★ 18.1K↓ —
- golden-epub-kwyusufkaraaslan/Skill_SeekersUse when testing keyword categorizationTestingNo warnings★ 15.2K↓ —
- expo-overviewexpo/skillsEntry point and router for every Expo or EAS task. Load this skill first — before writing code and before choosing another expo-* / eas-* skill — when the request, PRD, or spec mentions Expo, EAS, Expo Go, or an expo-* package, or the project has an `expo` dependency in `package.json`. Within that gate it also covers app specs and designs to implement (tabs, stacks, maps, lists, navigation, building from a screenshot), and phrasings like 'implement a mobile app', 'make my app look native', 'add navigation', 'fetch some data', 'upgrade my SDK', 'add Expo to my existing native app', 'ship to the App Store', or 'I'm new to Expo, where do I start'. A fully specified request (SDK pinned, libraries named, layout given) still routes through here — the shared setup rules still apply. Do NOT load it when neither signal is present: a bare React Native project with no `expo` dependency is not Expo work. Detects the real goal, routes to the right expo-* / eas-* skill, and owns the shared setup rules.OfficialWritingNo warnings★ 3K↓ —
- proof-orchestratorwanshuiyin/Auto-claude-code-research-in-sleepManage a stateful, run-directory-based proof project: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional DeepSeek second opinion as additional evidence only. Use when the user asks for proof-run orchestration, a GPT Pro handoff, or cross-run proof continuation — use /proof-writer for ordinary proof drafting and /proof-checker for rigorous verification or submission acceptance.WritingNo warnings★ 18.1K↓ —
- expo-brownfieldexpo/skillsIntegrate Expo and React Native into an existing native iOS or Android app. Use for brownfield, embedding a React Native screen in SwiftUI/UIKit or Kotlin, or AAR/XCFramework packaging. Covers isolated and integrated approaches. For building or distributing a purely native app with EAS, use eas-app-stores.OfficialEngineeringNo warnings★ 3K↓ —
evaluating-llms-harness
Orchestra-Research/AI-Research-SKILLs
OtherUpdated Oct 11, 2026
From the author
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 EleutherAI, HuggingFace, and major labs. Supports HuggingFace, vLLM, APIs.
Install
npx skills add Orchestra-Research/AI-Research-SKILLs --skill evaluating-llms-harness -a claude-code
Installs to .claude/skills/evaluating-llms-harness/ · 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/api-evaluation.md
- references/benchmark-guide.md
- references/custom-tasks.md
- references/distributed-eval.md