Star200+

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.

Finance Stock analysisQuant Trading researchSlides PPT generationDocs PDF parsingExtract Web scraping
16
Shown
10
Tracks
48
Targets
Resolve APITask in, selected skill and install plan out.Skills APIMachine-readable shortlist with trust and safety signals.llms.txtA crawler-friendly entry point for agent surfaces.

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.

  • Ui490 stars

    A collection of accessible, headless primitives and beautifully-designed components for Blazor inspired by sh…

    Trust 78Quality 75design-creative
  • Tinacms13K stars

    A fully open-source headless CMS that supports Markdown and Visual Editing

    Trust 88Quality 100document-processing
  • React Native Ui Datepicker868 stars

    Customizable React Native 📅 Date Picker component for Android, iOS, and Web. It includes single, range, and…

    Trust 81Quality 84productivity-automation

Codex, Claude Code, Cursor

Coding agent skills

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

  • Finn Loop104 stars

    The Finn-loop: a 3-skill AI software factory for Claude Code — spec, build, review. Humans merge.

    Trust 84Quality 86coding-agents
  • Agentic Flow752 stars

    Easily switch between alternative low-cost AI models in Claude Code/Agent SDK. For those comfortable using Cl…

    Trust 77Quality 78coding-agents
  • Todoist Cli234 stars

    Command-line interface for Todoist.

    Trust 81Quality 87productivity

Documents and knowledge

Research and RAG skills

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

  • Pipeshub AI3.0K stars

    PipesHub is a fully extensible and explainable workplace AI platform for enterprise search and workflow autom…

    Trust 88Quality 97rag-knowledge
  • GPTCache8.1K stars

    Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

    Trust 79Quality 78rag-knowledge
  • Memos61K stars

    Open-source, self-hosted note-taking tool built for quick capture. Markdown-native, lightweight, and fully yo…

    Trust 89Quality 100document-processing

Markets and quant

Finance and trading skills

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

  • Pumpfun Bonkfun Bot956 stars

    A fully functional pump.fun / letsbonk.fun trading and sniping bot not relying on any 3rd party APIs

    Trust 81Quality 78finance
  • Alphabiz1.2K stars

    Web3 YouTube Alternative - fully decentralized media platform and blockchain-based marketplace

    Trust 88Quality 93web3-analytics
  • Bittensor1.5K stars

    Internet-scale Neural Networks

    Trust 85Quality 94web3-analytics

Crawlers and extraction

Web scraping skills

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

  • Velstore648 stars

    Free and open-source multi-vendor Laravel eCommerce solution that is fully customizable and ready to use.

    Trust 79Quality 76commerce-automation
  • Gowall2.3K stars

    A tool to convert a Wallpaper's color scheme / palette, OCR with VLM's Traditional & Hybrid, Image Compressio…

    Trust 84Quality 96document-processing
  • Openrecall2.9K stars

    OpenRecall is a fully open-source, privacy-first alternative to proprietary solutions like Microsoft's Window…

    Trust 84Quality 88document-processing

Prompts, B-roll, explainers

Video creation skills

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

  • Video Use17K stars

    Edit videos with coding agents

    Trust 88Quality 100media
  • LocalMiniDrama684 stars

    🎬 seedance2接入 开源本地 AI 短剧 & 漫剧生成工具 —— 从故事到成片一站式完成，数据不出本机，短剧工作流管理平台，高灵活度，AI真人剧，AI漫剧本地搞定。 Open-source local AI…

    Trust 81Quality 77agent-frameworks
  • Cnn Explainer9.0K stars

    Learning Convolutional Neural Networks with Interactive Visualization.

    Trust 79Quality 74ml-automation

Images, video, UI

Design and creative skills

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

  • Pixelle Video23K stars

    🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine

    Trust 88Quality 100media-automation
  • Jetson Inference8.9K stars

    Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT a…

    Trust 86Quality 87ml-automation
  • Have Fun With Machine Learning5.1K stars

    An absolute beginner's guide to Machine Learning and Image Classification with Neural Networks

    Trust 77Quality 67ml-automation

Analysis and pipelines

Data and analytics skills

Data analysis, analytics, ETL, notebooks, databases, tables, charts, and reporting workflows.

  • Litlyx1.7K stars

    Powerful Analytics Solution. Setup in 30 seconds. Display all your data on a Simple, AI-powered dashboard. Fu…

    Trust 84Quality 80data-analysis
  • The Complete FAANG Preparation12K stars

    Dive into this repository, a comprehensive resource covering Data Structures, Algorithms, 450 DSA by Love Bab…

    Trust 87Quality 100data-analysis
  • TranscriptionSuite519 stars

    A fully local and private Speech-To-Text app with cross-platform support, speaker diarization, Audio Notebook…

    Trust 79Quality 75data-analysis

Popular directories

AI agent skills libraryA real library of reusable skills with trust, audit, install, and agent metadata.Open source AI agent skillsOpen-source skill candidates filtered by task fit, GitHub quality, and install safety.Best Codex skillsRepo inspection, code review, testing, web data, and safe install workflows for Codex.Best AI agent skills for stock analysisFinance and market research skills with trust, install, and maintenance signals.Best Codex skills for web scrapingCrawler and extraction skills that agents can shortlist before installing.Best Claude Code skills for PDF parsingDocument conversion, table extraction, OCR, and markdown workflows.Best AI agent skills for football analyticsMatch data, scouting, dashboards, and World Cup analytics workflows.OpenAgentSkill vs skills.shCompare task resolution, trust signals, install handoffs, and registry APIs.OpenAgentSkill vs agentskills.ioCompare directories, agent-readable metadata, audits, and discovery workflows.

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

216

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

216 quality209 maintained

Research

Research and knowledge work

84

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

84 quality80 maintained

Presentation

Presentation and deck workflows

1

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

1 quality1 maintained

Finance

Finance and quant workflows

19

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

19 quality18 maintained

Marketing

Marketing and growth automation

18

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

18 quality18 maintained

Design

Design and creative production

62

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

62 quality56 maintained

Data

Data, BI, and analytics

39

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

39 quality38 maintained

Legal

Legal, policy, and compliance

16

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

16 quality16 maintained

Education

Education and tutoring

5

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

5 quality5 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
FinanceStock analysisQuantTrading researchSlidesPPT generationDocsPDF parsingExtractWeb scrapingCreativeDesign workflowSportsFootball analytics

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-16 of 451 ranked candidates matching "fully-convolutional-networks"

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

1

Fully Homomorphic Encryption

VERIFIEDEXCELLENT · 95TRUST · 86SAFE · REVIEWEDLEGAL

An FHE compiler for C++

$ npx skills add google/fully-homomorphic-encryption
3.6K stars64 quality86 trustReviewed3mo 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 Legal and compliance

CLI + Codex · 4 targets

privacy
by googleDetailsQuick view
2

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
3

DPED

VERIFIEDSTRONG · 75TRUST · 81SAFE · REVIEWEDDESIGN

Software and pre-trained models for automatic photo quality enhancement using Deep Convolutional Networks

$ npx skills add aiff22/DPED
1.7K stars53 quality81 trustReviewed with permission notes11mo since pushNeeds review
QualitySolid option that is likely worth shortlisting for production workflows.
TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Multimodal media

CLI + Codex · 4 targets

pythoncomputer-vision
by aiff22DetailsQuick view
4

Computer Vision Course

STRONG · 78TRUST · 80SAFE · REVIEWEDCODING

This repo is the homebase of a community driven course on Computer Vision with Neural Networks. Feel free to join us on the Hugging Face discord: hf.co/join/discord

$ npx skills add huggingface/computer-vision-course
850 stars54 quality80 trustReviewed with permission notes2mo since pushSafe to try
QualitySolid option that is likely worth shortlisting for production workflows.
TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation

CLI + Codex · 4 targets

jupyter-notebookcomputer-vision
by huggingfaceDetailsQuick view
5

Tensorflow

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDDESIGN

An Open Source Machine Learning Framework for Everyone

$ npx skills add tensorflow/tensorflow
195.7K stars78 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 Multimodal media

CLI + Codex · 4 targets

c++machine-learning
by tensorflowDetailsQuick view
6

Keras

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDDESIGN

Deep Learning for humans

$ npx skills add keras-team/keras
64.1K stars77 quality88 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 Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by keras-teamDetailsQuick view
7

Faceswap

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDDESIGN

Deepfakes Software For All

$ npx skills add deepfakes/faceswap
55.3K stars76 quality88 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 Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by deepfakesDetailsQuick view
8

Keras Tcn

VERIFIEDEXCELLENT · 95TRUST · 85SAFE · REVIEWEDDESIGN

Keras Temporal Convolutional Network. Supports Python and R.

$ npx skills add philipperemy/keras-tcn
2.0K stars65 quality85 trustReviewed2mo 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 philipperemyDetailsQuick view
9

Crawl4AI

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDRESEARCH

Web crawling built for AI

$ npx skills add unclecode/crawl4ai
4 agent calls100% success73.1K stars80 quality90 trustReviewedClaude Code + OpenAI Agents18d since pushSafe to try31.0K installs
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 Research agents

Claude Code + OpenAI Agents · 4 targets

claudegpt-4langchaincrewaiopenclaw
by unclecodeDetailsQuick view
10

Osmnx

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDCODING

Download, model, analyze, and visualize street networks and other geospatial features from OpenStreetMap.

$ npx skills add gboeing/osmnx
5.7K stars68 quality89 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 GitHub automation

CLI + Codex · 4 targets

pythongeospatial
by gboeingDetailsQuick view
11

Kubevpn

VERIFIEDEXCELLENT · 97TRUST · 87SAFE · REVIEWEDCODING

KubeVPN offers a Cloud Native Dev Environment that connects to kubernetes cluster network.

$ npx skills add kubenetworks/kubevpn
1.4K stars64 quality87 trustReviewed15d 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

CLI + Codex · 4 targets

gokubernetes
by kubenetworksDetailsQuick view
12

Chemprop

VERIFIEDEXCELLENT · 91TRUST · 82SAFE · REVIEWEDDESIGN

Message Passing Neural Networks for Molecule Property Prediction

$ npx skills add chemprop/chemprop
2.4K stars65 quality82 trustReviewed with permission notes2mo since pushNeeds review
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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by chempropDetailsQuick view
13

Snntorch

VERIFIEDEXCELLENT · 92TRUST · 86SAFE · REVIEWEDDESIGN

Deep and online learning with spiking neural networks in Python

$ npx skills add jeshraghian/snntorch
2.0K stars62 quality86 trustReviewed3mo 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 jeshraghianDetailsQuick view
14

Bittensor

VERIFIEDEXCELLENT · 94TRUST · 85SAFE · REVIEWEDFINANCE

Internet-scale Neural Networks

$ npx skills add latent-to/bittensor
1.5K stars64 quality85 trustReviewed2mo 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 Finance and quant

CLI + Codex · 4 targets

pythonblockchain
by latent-toDetailsQuick view
15

Concrete Ml

VERIFIEDSTRONG · 82TRUST · 82SAFE · REVIEWEDLEGAL

Concrete ML: Privacy Preserving ML framework using Fully Homomorphic Encryption (FHE), built on top of Concrete, with bindings to traditional ML frameworks.

$ npx skills add zama-ai/concrete-ml
1.4K stars57 quality82 trustReviewed6mo since pushSafe to try
QualitySolid option that is likely worth shortlisting for production workflows.
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 Legal and compliance

CLI + Codex · 4 targets

pythonprivacy
by zama-aiDetailsQuick view
16

Agent Skills

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDCODING

Production-grade engineering skills for AI coding agents.

$ npx skills add addyosmani/agent-skills
9 agent calls88.89% success80.6K stars88 quality86 trustReviewed with permission notesClaude Code + Cursor7d 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

Claude Code + Cursor · 4 targets

shellai-agents
by addyosmaniDetailsQuick 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