AI Agent Skill Repository

AI Agent Skills Directory

Browse reusable skills for Codex, Claude Code, Cursor, finance, research, web scraping, PPT, football analytics, data, marketing, design, and more.

Browse by scenario

Real skills, grouped by the work your agent needs to finish.

Each directory entry links to real skill pages with GitHub adoption, trust score, install handoff, risk notes, and agent-readable metadata. Use these as starting points when you want a shortlist before asking an agent to install anything.

Design to deployment

Frontend and UI skills

Design direction, Figma implementation, UI review, React performance, browser QA, and safe preview deployments.

  • This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the in…

    Trust 91Quality 100design-creative
  • Dokploy36K stars

    Open Source Alternative to Vercel, Netlify and Heroku.

    Trust 85Quality 100devops
  • (Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic b…

    Trust 84Quality 91research

Codex, Claude Code, Cursor

Coding agent skills

Code review, repo inspection, testing, planning, shipping, and engineering workflows for coding agents.

  • Agent Skills81K stars

    Production-grade engineering skills for AI coding agents.

    Trust 86Quality 100agent-skills
  • Agent Skill that transforms AI assistants into expert economics paper writers. Synthesizes 50+ guides by Coch…

    Trust 85Quality 94research
  • Deepcode Cli1.2K stars

    Deep Code 是专为 deepseek-v4 模型优化的终端 AI 编码助手,支持深度思考、推理强度控制以及 Agent Skills。

    Trust 82Quality 93agent-skills

Documents and knowledge

Research and RAG skills

Research, recent-events briefings, PDF parsing, markdown conversion, RAG ingestion, and knowledge workflows.

  • Ragbits1.6K stars

    Building blocks for rapid development of GenAI applications

    Trust 84Quality 95rag-knowledge
  • Khoj35K stars

    Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule aut…

    Trust 90Quality 100data
  • Haystack26K stars

    Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. De…

    Trust 90Quality 100data

Markets and quant

Finance and trading skills

Stock analysis, market research, quant backtesting, financial data, and investment research skills.

  • Qlib44K stars

    Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exp…

    Trust 89Quality 100finance
  • An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies us…

    Trust 88Quality 95agent-frameworks

Crawlers and extraction

Web scraping skills

Crawling, scraping, extraction, browser automation, structured data capture, and website-to-markdown workflows.

  • Easydict14K stars

    一个简洁优雅的词典翻译 macOS App。开箱即用,支持离线 OCR 识别,支持有道词典,🍎 苹果系统词典,🍎 苹果系统翻译,OpenAI,Gemini,DeepL,Google,Bing,腾讯,百度,阿里,小牛…

    Trust 90Quality 100document-processing
  • Doctr6.1K stars

    docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks po…

    Trust 88Quality 100document-processing
  • 深度学习辅助漫画翻译工具, 支持一键机翻和简单的图像/文本编辑 | Yet another computer-aided comic/manga translation tool powered by deeplear…

    Trust 88Quality 99document-processing

Slides and decks

PPT and presentation skills

Presentation generation, editable PPTX, slide decks, speaker notes, and visual storytelling workflows.

  • ClaudeSkills626 stars

    13 curated Claude Code agent skills — decks, deep research, PRDs, articles, audits. Tested like software.

    Trust 87Quality 95presentation

Prompts, B-roll, explainers

Video creation skills

Video-generation prompts, B-roll, Vox-style explainers, camera direction, captions, and creative-production workflows.

  • Edit Mind1.6K stars

    Local-first Video Knowledge Base. Index your video library with multi-modal analysis (YOLO, DeepFace, Whisper…

    Trust 83Quality 89robotics-iot

Images, video, UI

Design and creative skills

Image, video, creative production, UI design, multimodal generation, and visual workflow skills.

  • Techniques10K stars

    Techniques for deep learning with satellite & aerial imagery

    Trust 88Quality 100ml-automation
  • AI Roadmap:机器学习(Machine Learning)、深度学习(Deep Learning)、对抗神经网络(GAN),图神经网络(GNN),NLP,大数据相关的发展路书(roadmap), 并附海量源码(…

    Trust 83Quality 89ml-automation
  • Torchreid: Deep learning person re-identification in PyTorch.

    Trust 83Quality 88ml-automation

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

198

Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.

198 quality198 maintained

Research

Research and knowledge work

97

Deep research, source comparison, literature review, RAG, knowledge search, and reports.

97 quality96 maintained

Presentation

Presentation and deck workflows

2

PPTX generation, HTML slides, pitch decks, speaker notes, and presentation workflow skills.

2 quality2 maintained

Finance

Finance and quant workflows

14

Market data, SEC filings, portfolio analysis, quant research, backtesting, and risk workflows.

14 quality14 maintained

Marketing

Marketing and growth automation

10

SEO, content operations, lead generation, CRM, email automation, analytics, and growth workflows.

10 quality10 maintained

Design

Design and creative production

78

Design assets, images, video, audio, multimodal media, presentation, and creative production skills.

78 quality73 maintained

Data

Data, BI, and analytics

36

CSV, SQL, notebooks, dashboards, data pipelines, BI, ETL, and spreadsheet analysis.

36 quality36 maintained

Legal

Legal, policy, and compliance

10

Contract analysis, privacy, policy review, compliance checks, governance, and document risk review.

10 quality10 maintained

Education

Education and tutoring

7

Tutoring, course generation, quizzes, learning analytics, classrooms, and teaching workflows.

7 quality7 maintained

World Cup

Football and World Cup analytics

2

Football data, World Cup dashboards, xG, match prediction, scouting, and sports analytics.

2 quality2 maintained

High-intent entry points

Start from the task, not a keyword list.

These shortcuts use the same trust, supply, and relevance signals as the registry API, so humans and agents land on a useful shortlist faster.

Agent-readable index

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-16 of 443 ranked candidates matching "deep-dive"

Best blend of quality, stars, freshness, and agent usage

1

Deep Research

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · VERIFIEDRESEARCH

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of th…

$ npx skills add dzhng/deep-research
19.1K stars70 quality88 trustVerifiedOpenAI Agents4mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Research agents

OpenAI Agents + CLI · 4 targets

typescriptresearch-agent
by dzhngDetailsQuick view
2

DeepResearchAgent

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · VERIFIEDRESEARCH

DeepResearchAgent is a hierarchical multi-agent system designed not only for deep research tasks but also for general-purpose task solving. The framework leverages a top…

$ npx skills add SkyworkAI/DeepResearchAgent
3.5K stars63 quality88 trustVerified3mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario RAG and knowledge

CLI + Codex · 4 targets

pythonresearch-agent
by SkyworkAIDetailsQuick view
3

DeepSpeed

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDDESIGN

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

$ npx skills add deepspeedai/DeepSpeed
42.5K stars76 quality90 trustReviewed1mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by deepspeedaiDetailsQuick view
4

DeepSeek Reasonix

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

DeepSeek-native AI coding agent for your terminal. Engineered around prefix-cache stability — leave it running.

$ npx skills add esengine/DeepSeek-Reasonix
27.4K stars74 quality88 trustReviewed with permission notes8d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

CLI + Codex · 4 targets

goai-agents
by esengineDetailsQuick view
5

DeepTutor

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDRESEARCH

DeepTutor: Agent-native, Open-sourced Personalized Tutoring. https://deeptutor.info/.

$ npx skills add HKUDS/DeepTutor
24.8K stars74 quality87 trustReviewed with permission notes1mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Research agents

CLI + Codex · 4 targets

pythonai-agents
by HKUDSDetailsQuick view
6

Deepface

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDCODING

A Lightweight Face Recognition and Facial Attribute Analysis (Age, Gender, Emotion and Race) Library for Python

$ npx skills add serengil/deepface
22.9K stars74 quality90 trustReviewed2mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario GitHub automation

CLI + Codex · 4 targets

pythonmachine-learning
by serengilDetailsQuick view
7

Annotated Deep Learning Paper Implementations

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDDESIGN

🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (ad…

$ npx skills add labmlai/annotated_deep_learning_paper_implementations
66.9K stars70 quality87 trustReviewed6mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by labmlaiDetailsQuick view
8

How Claude Code Works

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDCODING

Deep dive into Claude Code internals — architecture, agent loop, context engineering, and more. / 深入解析 Claude Code 源码:架构、Agent 循环、上下文工程、工具系统等

$ npx skills add Windy3f3f3f3f/how-claude-code-works
3.3K stars66 quality89 trustReviewedClaude Code16d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + CLI · 4 targets

ai-agents
by Windy3f3f3f3fDetailsQuick view
9

Pytorch Deep Learning

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDDESIGN

Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.

$ npx skills add mrdbourke/pytorch-deep-learning
18.2K stars66 quality87 trustReviewed6mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

CLI + Codex · 4 targets

jupyter-notebookmachine-learning
by mrdbourkeDetailsQuick view
10

Deeplake

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDRESEARCH

Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling scalable retrieval and training.

$ npx skills add activeloopai/deeplake
9.2K stars69 quality87 trustReviewed2mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario RAG and knowledge

CLI + Codex · 4 targets

c++vector-search
by activeloopaiDetailsQuick view
11

Mit Deep Learning Book Pdf

VERIFIEDEXCELLENT · 94TRUST · 84SAFE · REVIEWEDRESEARCH

MIT Deep Learning Book in PDF format (complete and parts) by Ian Goodfellow, Yoshua Bengio and Aaron Courville

$ npx skills add janishar/mit-deep-learning-book-pdf
14.1K stars65 quality84 trustReviewed6mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Document processing

CLI + Codex · 4 targets

javapdf
by janisharDetailsQuick view
12

Local Deep Research

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDRESEARCH

~95% on SimpleQA (e.g. Qwen3.6-27B on a 3090). Supports all local and cloud LLMs (llama.cpp, Ollama, Google, ...). 10+ search engines - arXiv, PubMed, your private docum…

$ npx skills add LearningCircuit/local-deep-research
8.7K stars69 quality90 trustReviewedClaude Code9d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario RAG and knowledge

Claude Code + CLI · 4 targets

pythonresearch
by LearningCircuitDetailsQuick view
13

T81 558 Deep Learning

VERIFIEDEXCELLENT · 92TRUST · 83SAFE · REVIEWEDDESIGN

T81-558: Keras - Applications of Deep Neural Networks @Washington University in St. Louis

$ npx skills add jeffheaton/t81_558_deep_learning
5.7K stars65 quality83 trustReviewed3mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

CLI + Codex · 4 targets

jupyter-notebookmachine-learning
by jeffheatonDetailsQuick view
14

Deepnote

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDDATA

Deepnote is a drop-in replacement for Jupyter with an AI-first design, sleek UI, new blocks, and native data integrations. Use Python, R, and SQL locally in your favorit…

$ npx skills add deepnote/deepnote
2.9K stars66 quality86 trustReviewed2mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Data analysis

CLI + Codex · 4 targets

typescriptdata-visualization
by deepnoteDetailsQuick view
15

Deepvariant

VERIFIEDEXCELLENT · 95TRUST · 85SAFE · REVIEWEDDESIGN

DeepVariant is an analysis pipeline that uses a deep neural network to call genetic variants from next-generation DNA sequencing data.

$ npx skills add google/deepvariant
3.7K stars64 quality85 trustReviewed4mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by googleDetailsQuick view
16

Deep Person Reid

VERIFIEDEXCELLENT · 88TRUST · 83SAFE · REVIEWEDDESIGN

Torchreid: Deep learning person re-identification in PyTorch.

$ npx skills add KaiyangZhou/deep-person-reid
4.8K stars61 quality83 trustReviewed7mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by KaiyangZhouDetailsQuick view

Page 1

Showing the strongest 16 results to keep the registry fast for humans and agents. Refine by use case, platform, stars, or search query for a narrower shortlist.

Try the agent resolve API