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.

  • Frontend Design166K stars

    Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product…

    Trust 88Quality 100design-creative
  • Material Ui98K stars

    Material UI: Comprehensive React component library that implements Google's Material Design. Free forever.

    Trust 90Quality 100design-creative
  • Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful r…

    Trust 91Quality 100design-creative

Codex, Claude Code, Cursor

Coding agent skills

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

  • Code Review169K stars

    Review a diff separately for code standards and spec compliance.

    Trust 91Quality 100coding-agents
  • Open Design83K stars

    🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design…

    Trust 91Quality 100agent-skills
  • Agent Skills81K stars

    Production-grade engineering skills for AI coding agents.

    Trust 86Quality 100agent-skills

Documents and knowledge

Research and RAG skills

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

  • Markitdown156K stars

    Python tool for converting files and office documents to Markdown.

    Trust 87Quality 100document-processing
  • PaddleOCR83K stars

    Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bri…

    Trust 89Quality 100document-processing
  • Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, s…

    Trust 88Quality 100rag-knowledge

Markets and quant

Finance and trading skills

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

  • TradingAgents88K stars

    TradingAgents: Multi-Agents LLM Financial Trading Framework

    Trust 88Quality 100finance
  • Best Proprietary MT4/MT5 Prop Fund Manager 2026 for Multi-Phase Challenge Tracking

    Trust 76Quality 68finance
  • Union74K stars

    The trust-minimized, zero-knowledge bridging protocol, designed for censorship resistance, extremely high sec…

    Trust 91Quality 100web3-analytics

Crawlers and extraction

Web scraping skills

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

  • Firecrawl139K stars

    The API to search, scrape, and interact with the web at scale. 🔥

    Trust 87Quality 100agent-frameworks
  • Crawl4AI73K stars

    Web crawling built for AI

    Trust 90Quality 100web-automation
  • Scrapling70K stars

    Adaptive web scraping for agent data collection

    Trust 85Quality 100web-automation

Slides and decks

PPT and presentation skills

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

  • Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact ter…

    Trust 91Quality 100design-creative
  • Canvas Design166K stars

    Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.

    Trust 87Quality 100design-creative

Prompts, B-roll, explainers

Video creation skills

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

  • 利用AI大模型,一键生成高清短视频 Generate short videos with one click using AI LLM.

    Trust 88Quality 100automation
  • List of Computer Science courses with video lectures.

    Trust 85Quality 100ml-automation
  • SoccerNet@CVPR | 1st place solution for Ball Action Spotting Challenge 2023

    Trust 68Quality 42sports-analytics

Images, video, UI

Design and creative skills

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

  • Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related arti…

    Trust 88Quality 100design-creative
  • Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

    Trust 85Quality 100ml-automation
  • Taste Skill65K stars

    Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

    Trust 91Quality 100development

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

200

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

186 quality182 maintained

Research

Research and knowledge work

69

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

67 quality65 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

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

49

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

49 quality47 maintained

Data

Data, BI, and analytics

35

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

32 quality31 maintained

Legal

Legal, policy, and compliance

12

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

12 quality11 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

3

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 388 ranked candidates matching "challenge"

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

1

Friendly Challenge

STRONG · 75TRUST · 78SAFE · REVIEWEDLEGAL

The widget and docs for the proof of work challenge used in Friendly Captcha. Protect your websites and online services from spam and abuse with Friendly Captcha, a priv…

$ npx skills add FriendlyCaptcha/friendly-challenge
448 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 Legal and compliance

CLI + Codex · 4 targets

typescriptprivacy
by FriendlyCaptchaDetailsQuick view
2

Rse Grand Challenge

STRONG · 71TRUST · 77SAFE · REVIEWEDCODING

A platform for end-to-end development of machine learning solutions in biomedical imaging

$ npx skills add DIAGNijmegen/rse-grand-challenge
191 stars50 quality77 trustReviewed with permission notes1mo 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

CLI + Codex · 4 targets

pythoncomputer-vision
by DIAGNijmegenDetailsQuick view
3

SQL Leetcode Challenge

PROMISING · 65TRUST · 75SAFE · REVIEWEDCODING

Contains all the 117 Leetcode questions with their solutions ranging from Easy to Hard in MySQL.

$ npx skills add mrinal1704/SQL-Leetcode-Challenge
830 stars47 quality75 trustReviewed with permission notes5mo since pushNeeds review
QualityUseful candidate, but compare it with alternatives before adopting.
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 Coding agents

CLI + Codex · 4 targets

rich-text-formatsql
by mrinal1704DetailsQuick view
4

Rank1 Ali Tianchi Real World Image Forgery Localization Challenge

NEEDS REVIEW · 38TRUST · 65SAFE · BLOCKEDCODING

2022阿里天池真实场景篡改图像检测挑战赛-冠军方案(1/1149)

$ npx skills add Junjue-Wang/Rank1-Ali-Tianchi-Real-World-Image-Forgery-Localization-Challenge
200 stars35 quality65 trustBlocked for auto-install4y since pushRisky
QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale
TrustPotentially useful, but at least one trust signal needs human inspection.Review: License is unclear
Safety gateThis skill should not be selected by an agent without explicit human security review.

Scenario GitHub automation

CLI + Codex · 4 targets

pythoncomputer-vision
by Junjue-WangDetailsQuick view
5

Code Audit Challenges

NEEDS REVIEW · 45TRUST · 66SAFE · BLOCKEDDATA

Code-Audit-Challenges

$ npx skills add CHYbeta/Code-Audit-Challenges
988 stars40 quality66 trustBlocked for auto-install8y since pushRisky
QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale
TrustPotentially useful, but at least one trust signal needs human inspection.Review: License is unclear
Safety gateThis skill should not be selected by an agent without explicit human security review.

Scenario Database and SQL

CLI + Codex · 4 targets

sql
by CHYbetaDetailsQuick view
6

HackerRank SQL Challenges Solutions

NEEDS REVIEW · 49TRUST · 69SAFE · EXPERIMENTALDATA

The solutions of all SQL hackerrank challenges using MySQL environment

$ npx skills add Thomas-George-T/HackerRank-SQL-Challenges-Solutions
818 stars39 quality69 trustExperimental2y since pushNeeds review
QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale
TrustPotentially useful, but at least one trust signal needs human inspection.Review: Repository looks stale
Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Database and SQL

CLI + Codex · 4 targets

sql
by Thomas-George-TDetailsQuick view
7

Challenges Kubernetes

NEEDS REVIEW · 44TRUST · 66SAFE · BLOCKEDCODING

:cloud: Challenges Your Kubernetes Skills And Knowledge

$ npx skills add dennyzhang/challenges-kubernetes
229 stars35 quality66 trustBlocked for auto-installClaude Code7y since pushRisky
QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale
TrustPotentially useful, but at least one trust signal needs human inspection.Review: Repository looks stale
Safety gateThis skill should not be selected by an agent without explicit human security review.

Scenario GitHub automation

Claude Code + CLI · 4 targets

shellkubernetes
by dennyzhangDetailsQuick view
8

MATLAB Simulink Challenge Project Hub

VERIFIEDEXCELLENT · 91TRUST · 84SAFE · REVIEWEDRESEARCH

This MATLAB and Simulink Challenge Project Hub contains a list of research and design project ideas. These projects will help you gain practical experience and insight i…

$ npx skills add mathworks/MATLAB-Simulink-Challenge-Project-Hub
2.1K stars65 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

htmlcomputer-vision
by mathworksDetailsQuick view
9

Hcaptcha Challenger

VERIFIEDEXCELLENT · 85TRUST · 81SAFE · REVIEWEDCODING

🥂 Gracefully face hCaptcha challenge with multimodal large language model.

$ npx skills add QIN2DIM/hcaptcha-challenger
2.3K stars58 quality81 trustReviewed with permission notesOpenAI Agents + Browser agents6mo 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: Documentation summary is thin
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Testing and QA

OpenAI Agents + Browser agents · 4 targets

pythonplaywright
by QIN2DIMDetailsQuick view
10

BrainTree SQL Coding Challenge Data Analyst

NEEDS REVIEW · 41TRUST · 66SAFE · BLOCKEDDATA

A Challenge To Test My SQL Skills For A Braintree Data Analyst Interview Process

$ npx skills add AlexanderConnelly/BrainTree_SQL_Coding_Challenge_Data_Analyst
397 stars37 quality66 trustBlocked for auto-installClaude Code8y since pushRisky
QualityInspect the repository carefully before adding it to an agent workflow.Check: Repository looks stale
TrustPotentially useful, but at least one trust signal needs human inspection.Review: License is unclear
Safety gateThis skill should not be selected by an agent without explicit human security review.

Scenario Database and SQL

Claude Code + CLI · 4 targets

plpgsqlsql
by AlexanderConnellyDetailsQuick view
11

Challenge Bypass Extension

VERIFIEDPROMISING · 65TRUST · 76SAFE · EXPERIMENTALLEGAL

DEPRECATED - Client for Privacy Pass protocol providing unlinkable cryptographic tokens

$ npx skills add privacypass/challenge-bypass-extension
1.3K stars48 quality76 trustExperimentalBrowser agents1y since pushNeeds review
QualityUseful candidate, but compare it with alternatives before adopting.Check: Repository looks stale
TrustGood trust signals with a few areas worth checking before rollout.Review: Repository looks stale
Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Legal and compliance

Browser agents + CLI · 4 targets

javascriptprivacy
by privacypassDetailsQuick view
12

Toolkit

STRONG · 71TRUST · 77SAFE · REVIEWEDCODING

The official VOT Challenge evaluation and analysis toolkit

$ npx skills add votchallenge/toolkit
204 stars50 quality77 trustReviewed with permission notes2mo 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation

CLI + Codex · 4 targets

pythoncomputer-vision
by votchallengeDetailsQuick view
13

Ctf Skills

VERIFIEDEXCELLENT · 93TRUST · 83SAFE · REVIEWEDRESEARCH

Agent skills for solving CTF challenges - web exploitation, binary pwn, crypto, reverse engineering, forensics, OSINT, and more

$ npx skills add ljagiello/ctf-skills
2.4K stars62 quality83 trustReviewed with permission notesClaude Code + OpenAI Agents3mo 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 RAG and knowledge

Claude Code + OpenAI Agents · 4 targets

pythonai-agents
by ljagielloDetailsQuick view
14

Xview Yolov3

STRONG · 73TRUST · 77SAFE · REVIEWEDDESIGN

xView 2018 Object Detection Challenge: YOLOv3 Training and Inference.

$ npx skills add ultralytics/xview-yolov3
333 stars51 quality77 trustReviewed with permission notes2mo 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by ultralyticsDetailsQuick view
15

Flutter Animations

PROMISING · 58TRUST · 75SAFE · REVIEWEDDESIGN

Exploring "Animations In Flutter", having fun building and writing about them while doing design challenges to see the extent of what Flutter can achieve.

$ npx skills add rutvik110/Flutter-Animations
306 stars40 quality75 trustReviewed with permission notes10mo since pushNeeds review
QualityUseful candidate, but compare it with alternatives before adopting.
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 Design and creative

CLI + Codex · 4 targets

dartcreative-coding
by rutvik110DetailsQuick view
16

SWE Agent

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDCODING

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding chal…

$ npx skills add SWE-agent/SWE-agent
19.5K 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 Coding agents

CLI + Codex · 4 targets

pythondeveloper-tools
by SWE-agentDetailsQuick 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