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 17 hours ago
46,700 skills
- azure-ai-voicelive-tsmicrosoft/skillsAzure AI Voice Live SDK for JavaScript/TypeScript. Build real-time voice AI applications with bidirectional WebSocket communication. Use for voice assistants, conversational AI, real-time speech-to-speech, and voice-enabled chatbots in Node.js or browser environments. Triggers: "voice live", "real-time voice", "VoiceLiveClient", "VoiceLiveSession", "voice assistant TypeScript", "bidirectional audio", "speech-to-speech JavaScript".OfficialDevOpsNo warnings★ 3.1K↓ —
- 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↓ —
- agent-platform-migrate-from-ai-studiogoogle/skillsGuides agents and users through migrating from Gemini API in Google AI Studio to Gemini Enterprise Agent Platform (formerly Vertex AI). Use this skill when moving applications to Google Cloud, to leverage Cloud credits, or to unify inferencing with other Cloud infrastructure (IAM, billing, telemetry).OfficialDevOpsNo warnings★ 21.6K↓ —
- nemo-curatorOrchestra-Research/AI-Research-SKILLsGPU-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 with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.MediaNo 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↓ —
- 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↓ —
- wiki-retrieveAgriciDaniel/claude-obsidianBuild and query a vault-local contextual BM25 retrieval index with optional multilingual Nomic cosine reranking; use for retrieve, hybrid retrieval, BM25, rerank, contextual retrieval, chunk search, vault search, semantic search, find relevant passages, or retrieval diagnostics. Derived caches stay under .vault-meta, remote egress requires explicit consent, and unavailable reranking falls back deterministically.OtherNo warnings★ 15.8K↓ —
- rebuttalwanshuiyin/Auto-claude-code-research-in-sleepWorkflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.ProductivityNo warnings★ 18.2K↓ —
- 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↓ —
- 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★ 18.2K↓ —
- alphaxivwanshuiyin/Auto-claude-code-research-in-sleepQuick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.ScienceNo warnings★ 18.2K↓ —
- peft-fine-tuningOrchestra-Research/AI-Research-SKILLsParameter-efficient fine-tuning for LLMs using LoRA, QLoRA, and 25+ methods. Use when fine-tuning large models (7B-70B) with limited GPU memory, when you need to train <1% of parameters with minimal accuracy loss, or for multi-adapter serving. HuggingFace's official library integrated with transformers ecosystem.ProductivityNo warnings★ 14K↓ —
- skillkrillinai/OpenCreatorFormerly KrillinAI, VideoTranslation and Dubbing Tool. Open-source AI workspace for creators, powered by Codex. Video downloading, video translation, create videos, images, voice, avatars, and edits with Agents in one place. Suitable for your Social Media like YouTube, TikTok, Instagram, etc.MediaNo warnings★ 13.9K↓ —
- llavaOrchestra-Research/AI-Research-SKILLsLarge 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 instruction following. Use for vision-language chatbots or image understanding tasks. Best for conversational image analysis.MediaNo 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↓ —
- idea-discovery-robotwanshuiyin/Auto-claude-code-research-in-sleepWorkflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says "robotics idea discovery", "机器人找idea", "embodied AI idea", "机器人方向探索", "sim2real 选题", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.EngineeringNo warnings★ 18.2K↓ —
- prompt-masternidhinjs/prompt-masterGenerates optimized prompts for AI tools. Activates only when the user explicitly asks to write, fix, improve, or adapt a prompt for a specific AI tool (LLM, Cursor, Midjourney, image AI, video AI, coding agents, etc.). Does not activate for general conversation, coding tasks, document writing, or other non-prompt-engineering work.MediaNo warnings★ 15.1K↓ —
- proof-writerwanshuiyin/Auto-claude-code-research-in-sleepWrites rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can actually be completed under the stated assumptions.WritingNo warnings★ 18.2K↓ —
- integrity-forensicswanshuiyin/Auto-claude-code-research-in-sleepRun the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger → GPT auditors propose findings → a rules-only reporter that lists every proposal with what the auditor said about it) against a paper via a SHA-pinned thin launcher — then convert the verdict into a typed policy gate (BLOCK/WARN/NO_NEW_BLOCKER) and an append-only obligations ledger. Use when user says "integrity forensics", "forensic audit this paper", "投稿前自查诚信", "审这篇论文的诚信", or says "anti-autoresearch" when the upstream repo's own skills are not installed. Also invoked by /paper-writing (submission self-forensics, default ON), /peer-review (forensic appendix), /resubmit-pipeline.SecurityNo warnings★ 18.2K↓ —
- 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, the expo-image and Reanimated integrations, 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`) or the Expo MCP `observe_*` tools, 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.OfficialMediaNo warnings★ 3.3K↓ —
- transformer-lens-interpretabilityOrchestra-Research/AI-Research-SKILLsProvides guidance for mechanistic interpretability research using TransformerLens to inspect and manipulate transformer internals via HookPoints and activation caching. Use when reverse-engineering model algorithms, studying attention patterns, or performing activation patching experiments.ScienceNo warnings★ 14K↓ —Also in 1 other repo
- kill-argumentwanshuiyin/Auto-claude-code-research-in-sleepTwo-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2 simulation", or before submitting a theory paper that has already passed standard review rounds.ScienceNo warnings★ 18.2K↓ —
- evaluating-code-modelsOrchestra-Research/AI-Research-SKILLsEvaluates code generation models across HumanEval, MBPP, MultiPL-E, and 15+ benchmarks with pass@k metrics. Use when benchmarking code models, comparing coding abilities, testing multi-language support, or measuring code generation quality. Industry standard from BigCode Project used by HuggingFace leaderboards.EngineeringNo warnings★ 14K↓ —Also in 1 other repo
- security-best-practicesopenai/skillsPerform language and framework specific security best-practice reviews and suggest improvements. Trigger only when the user explicitly requests security best practices guidance, a security review/report, or secure-by-default coding help. Trigger only for supported languages (python, javascript/typescript, go). Do not trigger for general code review, debugging, or non-security tasks.OfficialSecurityNo warnings★ 28.3K↓ —Also in 1 other repo
run-experiment
wanshuiyin/Auto-claude-code-research-in-sleep
DevOpsUpdated 4 days ago
From the author
Deploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.
Install
npx skills add wanshuiyin/Auto-claude-code-research-in-sleep --skill run-experiment -a claude-code
Installs to .claude/skills/run-experiment/ · 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
Provenance91
Maintenance100
Licence100
Adoption66
Files (1)
- SKILL.md