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.
47,298 skills from 2,272 repositories · updated 25 minutes ago
47,298 skills
- golden-man-kwyusufkaraaslan/Skill_SeekersUse when testing the man golden buildTestingNo warnings★ 15.2K↓ —
- paper-planwanshuiyin/Auto-claude-code-research-in-sleepGenerate a structured paper outline from review conclusions and experiment results. Use when user says "写大纲", "paper outline", "plan the paper", "论文规划", or wants to create a paper plan before writing.ScienceNo warnings★ 18.2K↓ —
- golden-pptxyusufkaraaslan/Skill_SeekersUse when testing the pptx golden buildDocumentsNo warnings★ 15.2K↓ —
- experiment-tracking-swanlabOrchestra-Research/AI-Research-SKILLsProvides guidance for experiment tracking with SwanLab. Use when you need open-source run tracking, local or self-hosted dashboards, and lightweight media logging for ML workflows.OtherNo warnings★ 14K↓ —
- gsap-performancegreensock/gsap-skillsOfficial GSAP skill for performance — prefer transforms, avoid layout thrashing, will-change, batching. Use when optimizing GSAP animations, reducing jank, or when the user asks about animation performance, FPS, or smooth 60fps.OfficialMediaNo warnings★ 17.4K↓ —
- ml-training-recipesOrchestra-Research/AI-Research-SKILLsBattle-tested PyTorch training recipes for all domains — LLMs, vision, diffusion, medical imaging, protein/drug discovery, spatial omics, genomics. Covers training loops, optimizer selection (AdamW, Muon), LR scheduling, mixed precision, debugging, and systematic experimentation. Use when training or fine-tuning neural networks, debugging loss spikes or OOM, choosing architectures, or optimizing GPU throughput.ScienceNo warnings★ 14K↓ —Also in 1 other repo
- 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↓ —
- sparse-autoencoder-trainingOrchestra-Research/AI-Research-SKILLsProvides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.OtherNo warnings★ 14K↓ —Also in 1 other repo
- 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★ 18.2K↓ —
- nemo-guardrailsOrchestra-Research/AI-Research-SKILLsNVIDIA's runtime safety framework for LLM applications. Features jailbreak detection, input/output validation, fact-checking, hallucination detection, PII filtering, toxicity detection. Uses Colang 2.0 DSL for programmable rails. Production-ready, runs on T4 GPU.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↓ —
- agentselevenlabs/skillsBuild voice AI agents with ElevenLabs. Use when creating voice assistants, customer service bots, interactive voice characters, or any real-time voice conversation experience, and when configuring an agent's tools, workflows, or procedures, including creating, editing, and publishing free-form and structured procedure drafts on an agent branch over the SDKs or REST API.OfficialWritingNo warnings★ 515↓ —
- skill-improverGentleman-Programming/gentle-aiTrigger: improve skills, audit skills, refactor skills, skill quality. Audit and upgrade existing LLM-first skills.EngineeringNo warnings★ 8.1K↓ —
- work-unit-commitsGentleman-Programming/gentle-aiPlan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.TestingNo warnings★ 8.1K↓ —
- ads-reportAgriciDaniel/claude-adsRender Markdown, HTML, or PDF paid-advertising reports from a validated Claude Ads JSON run bundle. Use for ads report, client report, audit PDF, executive audience reporting, or exporting prior audit and plan results.MarketingNo warnings★ 10.5K↓ —
- mobile-appnexu-io/html-anything像素级 iPhone 15 Pro 边框, 一屏 app 截图OtherNo warnings★ 9.3K↓ —
- musicelevenlabs/skillsGenerate music using ElevenLabs Music API. Use when creating instrumental tracks, songs with lyrics, background music, jingles, or any AI-generated music composition. Supports prompt-based generation, composition plans for granular control, and detailed output with metadata.OfficialMediaNo warnings★ 515↓ —
- story-short-analyzezenstory-ai/oh-story-claudecode短篇网文拆文。拆解爆款短篇小说（番茄短篇 / 故事会 / 知乎盐言 / 追妻 / 世情 / 重生 / 虐渣等通俗题材）的故事核、结构、情感线、反转设计、写作手法、共鸣层次。单一全量拆解管道：跑完 Stage 2-6 产出完整拆文报告，落盘到 拆文库/{书名}/，下游 story-short-write 同时读拆文报告 + 情节节点 + 写作手法 + 原文 + _meta.json 写下一篇。触发方式：/story-short-analyze、/短篇拆文、「拆短篇」「拆这篇短文」「短篇拆文」「精细拆解短篇」「8000 字短篇拆解」「番茄短篇拆文」「故事会拆解」「盐言故事拆解」「分析这篇短篇」——均进入同一管道。WritingNo warnings★ 8.1K↓ —Also in 1 other repo
- blog-postnexu-io/html-anything杂志感长文, 含 masthead、hero、figures、pull quote、作者署名WritingNo warnings★ 9.3K↓ —
- kanban-boardnexu-io/html-anythingTo do / In progress / In review / Done 四列, 卡片 + 头像 + 泳道EngineeringNo warnings★ 9.3K↓ —
- realtimeelevenlabs/skillsUse ElevenLabs Realtime models (`eleven_realtime_v1_mini`, `eleven_realtime_v1_max`), the low-latency models built for voice conversation. Use when the user wants to create an ElevenAgents agent on a Realtime model or switch an existing agent's Voice mode to Realtime, set `conversation_config.realtime_model`, choose between Realtime Mini and Max, or debug a Realtime agent that won't publish or transfer. Also use when migrating a voice app built on OpenAI's Realtime API and SDK (`@openai/agents-realtime`, `gpt-realtime`) to the OpenAI-compatible ElevenLabs Realtime API, including the `client_secrets` mint, the WebSocket transport, and audio after leaving WebRTC (closes with 4001/4003, no audio). Not for choosing an agent's LLM or TTS model in Custom mode, Scribe realtime speech-to-text, or migrating Chat Completions or Responses API text calls.OfficialMediaNo warnings★ 515↓ —
- offensive-fast-checkingSnailSploit/Claude-Redclaude-red is a curated library of offensive security skills designed for the Claude skills system. Each skill is a structured SKILL.md file that primes Claude with expert-level methodology for a specific attack surface — from SQLi to shellcode, EDR evasion to exploit development.SecurityNo warnings★ 9.7K↓ —
- frame-macos-notificationnexu-io/html-anything拟真 macOS 通知 banner + app icon + 标题正文, 适合 video overlay / 产品发布预告MediaNo warnings★ 9.3K↓ —
- team-okrsnexu-io/html-anything季度 banner + 3 个目标 + KR 进度条 + owner + 状态 pillOtherNo warnings★ 9.3K↓ —
fine-tuning-expert
Jeffallan/claude-skills
DevOpsUpdated 9 hours ago
From the author
Use when fine-tuning LLMs, training custom models, or adapting foundation models for specific tasks. Invoke for configuring LoRA/QLoRA adapters, preparing JSONL training datasets, setting hyperparameters for fine-tuning runs, adapter training, transfer learning, finetuning with Hugging Face PEFT, OpenAI fine-tuning, instruction tuning, RLHF, DPO, or quantizing and deploying fine-tuned models. Trigger terms include: LoRA, QLoRA, PEFT, finetuning, fine-tuning, adapter tuning, LLM training, model training, custom model.
Install
npx skills add Jeffallan/claude-skills --skill fine-tuning-expert -a claude-code
Installs to .claude/skills/fine-tuning-expert/ · 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 onlyNo network use seenLicence: MIT
Safety checks on SKILL.md
No warnings.
Why 92
Security100
Provenance89
Maintenance100
Licence100
Adoption64
Files (6)
- SKILL.md
- references/dataset-preparation.md
- references/deployment-optimization.md
- references/evaluation-metrics.md
- references/hyperparameter-tuning.md
- references/lora-peft.md