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.

  • Vuls12K stars

    Agent-less vulnerability scanner for Linux, FreeBSD, Container, WordPress, Programming language libraries, Ne…

    Trust 88Quality 100security
  • Mano P2.3K stars

    Mano-P: Open-source GUI-VLA agent for edge devices. #1 on OSWorld (specialized, 58.2%). Runs locally on Apple…

    Trust 87Quality 100productivity-automation
  • Shellhub2.0K stars

    :computer: Get seamless remote access to any Linux device. Centralized SSH for the edge and cloud computing

    Trust 87Quality 95robotics-iot

Codex, Claude Code, Cursor

Coding agent skills

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

  • Omnigent8.4K stars

    Omnigent is an open-source AI agent framework and meta-harness: orchestrate Claude Code, Codex, Cursor, Pi, a…

    Trust 90Quality 100coding-agents
  • Token Monitor255 stars

    Real-time token, cost, and AI limits widget with multi-device sync for Claude Code, Codex, OpenCode, Hermes,…

    Trust 73Quality 72development
  • Claude Dnd Skill124 stars

    Unofficial D&D 5e Dungeon Master for Claude Code — persistent campaigns, full 5e mechanics, and an optional c…

    Trust 85Quality 87utility

Documents and knowledge

Research and RAG skills

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

  • Chronicler641 stars

    Chronicler is a free, offline worldbuilding tool and local wiki for writers, game masters, and tabletop RPG c…

    Trust 77Quality 77document-processing
  • LEANN13K stars

    [MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100%…

    Trust 90Quality 100data
  • LEANN12K stars

    [MLsys2026]: RAG on Everything with LEANN. Enjoy 97% storage savings while running a fast, accurate, and 100%…

    Trust 90Quality 100data

Markets and quant

Finance and trading skills

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

  • Pennywiseai Tracker491 stars

    PennyWise automatically reads transaction SMS messages and transforms them into organized financial data with…

    Trust 78Quality 75finance
  • Android Money Manager Ex690 stars

    Local-first personal finance app. Encrypted, self-hosted, sync across devices.

    Trust 79Quality 77finance

Crawlers and extraction

Web scraping skills

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

  • Kuri331 stars

    Browser automation, web crawling, and iOS + Android device control for AI agents. Zig-native, token-efficient…

    Trust 70Quality 68web-automation
  • Koreader27K stars

    An ebook reader application supporting PDF, DjVu, EPUB, FB2 and many more formats, running on Cervantes, Kind…

    Trust 89Quality 100document-processing
  • Xournalpp15K stars

    Xournal++ is a handwriting notetaking software with PDF annotation support. Written in C++ with GTK3, support…

    Trust 89Quality 100document-processing

Prompts, B-roll, explainers

Video creation skills

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

  • Handbrake Web779 stars

    A self-hosted platform to use HandBrake on your headless devices via a bespoke web interface. Harness the pro…

    Trust 78Quality 74media-automation

Images, video, UI

Design and creative skills

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

  • ClipCascade1.8K stars

    ClipCascade is a lightweight utility that automatically syncs the clipboard across devices, no key press requ…

    Trust 85Quality 92productivity-automation
  • Whisperboard1.0K stars

    The open-source iOS app that's making quality voice transcription more accessible on mobile devices.

    Trust 84Quality 77media-automation
  • Porda AI307 stars

    The World's First Realtime onDevice AI Project to maintian Modestey and Religious values. Everyday AI compani…

    Trust 78Quality 79ml-automation

Analysis and pipelines

Data and analytics skills

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

  • Sqlsync2.9K stars

    SQLSync is a collaborative offline-first wrapper around SQLite. It is designed to synchronize web application…

    Trust 82Quality 82data-analysis
  • Logger175 stars

    Logger is a Flutter-based Android app that enables you to view and export call logs in CSV or JSON format and…

    Trust 77Quality 71data-analysis
  • Nimbus Eth1629 stars

    Nimbus: an Ethereum Execution Client for Resource-Restricted Devices

    Trust 79Quality 76web3-analytics

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

223

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

222 quality220 maintained

Research

Research and knowledge work

85

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

85 quality82 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

33

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

33 quality33 maintained

Marketing

Marketing and growth automation

11

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

11 quality11 maintained

Design

Design and creative production

67

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

67 quality64 maintained

Data

Data, BI, and analytics

35

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

35 quality34 maintained

Legal

Legal, policy, and compliance

22

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

22 quality20 maintained

Education

Education and tutoring

8

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

8 quality6 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 476 ranked candidates matching "on-device-ml"

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

1

K8s Device Plugin

VERIFIEDEXCELLENT · 98TRUST · 86SAFE · REVIEWEDCODING

NVIDIA device plugin for Kubernetes

$ npx skills add NVIDIA/k8s-device-plugin
3.8K stars67 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 GitHub automation

CLI + Codex · 4 targets

gokubernetes
by NVIDIADetailsQuick view
2

Device Activity Tracker

VERIFIEDSTRONG · 83TRUST · 81SAFE · REVIEWEDLEGAL

A phone number can reveal whether a device is active, in standby or offline (and more). This PoC demonstrates how delivery receipts + RTT timing leak sensitive device-ac…

$ npx skills add gommzystudio/device-activity-tracker
5.0K stars61 quality81 trustReviewed with permission notes7mo 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 Legal and compliance

CLI + Codex · 4 targets

typescriptprivacy
by gommzystudioDetailsQuick view
3

Device Os

VERIFIEDEXCELLENT · 93TRUST · 86SAFE · REVIEWEDCODING

Device OS (Firmware) for Particle Devices

$ npx skills add particle-iot/device-os
1.1K stars63 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 Coding agents

CLI + Codex · 4 targets

c++iot
by particle-iotDetailsQuick view
4

VieNeu TTS

VERIFIEDEXCELLENT · 95TRUST · 88SAFE · REVIEWEDDESIGN

Vietnamese TTS with instant voice cloning • On-device • Real-time CPU inference • 24kHz audio quality • Chuyển văn bản thành giọng nói tiếng Việt • Text to speech tiếng…

$ npx skills add pnnbao97/VieNeu-TTS
1.9K stars65 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

pythonvoice
by pnnbao97DetailsQuick view
5

MNN

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDDESIGN

MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI.

$ npx skills add alibaba/MNN
15.5K stars73 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 Multimodal media

CLI + Codex · 4 targets

c++machine-learning
by alibabaDetailsQuick view
6

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 Agents26d 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
7

Porcupine

VERIFIEDEXCELLENT · 99TRUST · 86SAFE · REVIEWEDDESIGN

On-device wake word detection powered by deep learning

$ npx skills add Picovoice/porcupine
4.9K stars68 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 Multimodal media

CLI + Codex · 4 targets

pythonspeech
by PicovoiceDetailsQuick view
8

Openremote

VERIFIEDEXCELLENT · 90TRUST · 84SAFE · REVIEWEDRESEARCH

100% open-source IoT Platform - Integrate your devices, add intelligence, build custom apps

$ npx skills add openremote/openremote
1.8K stars64 quality84 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: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents

CLI + Codex · 4 targets

javaiot
by openremoteDetailsQuick view
9

React Native Executorch

VERIFIEDEXCELLENT · 89TRUST · 84SAFE · REVIEWEDRESEARCH

Declarative way to run AI models in React Native on device, powered by ExecuTorch.

$ npx skills add software-mansion/react-native-executorch
1.6K stars64 quality84 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: 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

c++ocr
by software-mansionDetailsQuick view
10

Kafkactl

VERIFIEDEXCELLENT · 90TRUST · 82SAFE · REVIEWEDCODING

Command Line Tool for managing Apache Kafka

$ npx skills add deviceinsight/kafkactl
1.1K stars60 quality82 trustReviewed with permission notes3mo 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

CLI + Codex · 4 targets

gokubernetes
by deviceinsightDetailsQuick view
11

Typewhisper Mac

VERIFIEDEXCELLENT · 94TRUST · 85SAFE · REVIEWEDLEGAL

Local speech-to-text for macOS on-device AI, fully private, optional cloud

$ npx skills add TypeWhisper/typewhisper-mac
1.4K 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 Legal and compliance

CLI + Codex · 4 targets

swiftprivacy
by TypeWhisperDetailsQuick view
12

Agent Skills

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDCODING

Production-grade engineering skills for AI coding agents.

$ npx skills add addyosmani/agent-skills
9 agent calls88.89% success85.5K stars88 quality86 trustReviewed with permission notesClaude Code + Cursor2d 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
13

Playwright Browser Skill

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDCODING

Automate a real browser from the terminal for navigation, form filling, snapshots, screenshots, extraction, and UI-flow debugging.

$ npx skills add openai/skills --skill playwright
24.0K stars91 quality86 trustReviewed with permission notesClaude Code + OpenAI Agents27d since pushSafe to try28.8K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Browser automation can submit data; confirm the target environment and review a…
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Browser automation can submit data; confirm the target environment and review a…
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Testing and QA

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursorplaywright
by openaiDetailsQuick view
14

TheWhisper

STRONG · 78TRUST · 79SAFE · REVIEWEDDESIGN

Optimized Whisper models for streaming and on-device use

$ npx skills add TheStageAI/TheWhisper
888 stars54 quality79 trustReviewed2mo 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 gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

CLI + Codex · 4 targets

pythonspeech
by TheStageAIDetailsQuick view
15

PokeClaw

STRONG · 75TRUST · 77SAFE · EXPERIMENTALCODING

PokeClaw (PocketClaw) — first on-device AI that controls your Android phone. Gemma 4, no cloud, no API key. Poke is short for Pocket.

$ npx skills add agents-io/PokeClaw
1.0K stars52 quality77 trustExperimental2mo 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: Quality score needs review
Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents

CLI + Codex · 4 targets

kotlinai-agents
by agents-ioDetailsQuick view
16

Maestro Runner

STRONG · 74TRUST · 78SAFE · REVIEWEDCODING

Fast mobile UI test automation for Android, iOS, React Native, Flutter & Expo. Open-source Maestro alternative — 100% free, no features behind a paywall. Supports real i…

$ npx skills add devicelab-dev/maestro-runner
370 stars52 quality78 trustReviewed2mo 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 gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Testing and QA

CLI + Codex · 4 targets

gotesting
by devicelab-devDetailsQuick 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