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.

  • Vercel React Best Practices30K stars

    React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.

    Trust 91Quality 100coding-agents
  • Portaljs2.3K stars

    🌀 AI-native framework for building data portals. Scaffold a full portal from a brief and load datasets in mi…

    Trust 89Quality 99agent-skills
  • Xcode Build Optimization Agent Skill1.1K stars

    An Agent Skill helping you to optimize Xcode incremental and clean builds by running benchmarks and optimizin…

    Trust 85Quality 90agent-skills

Codex, Claude Code, Cursor

Coding agent skills

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

  • Evo1.2K stars

    turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then ru…

    Trust 87Quality 93agent-skills
  • Aaron Marketing Skills2.5K stars

    38 marketing skills + 5 commands for Claude Code & 35+ AI agents: SEO/GEO + influencer marketing (IMPACT). Fr…

    Trust 89Quality 100productivity
  • Agentmemory23K stars

    #1 Persistent memory for AI coding agents based on real-world benchmarks

    Trust 88Quality 100coding-agents

Documents and knowledge

Research and RAG skills

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

  • Awesome GraphRAG2.5K stars

    Awesome-GraphRAG: A curated list of resources (surveys, papers, benchmarks, and opensource projects) on graph…

    Trust 87Quality 96rag-knowledge
  • Mteb3.3K stars

    MTEB: Massive Text Embedding Benchmark

    Trust 86Quality 98rag-knowledge
  • VectorDBBench1.1K stars

    Benchmark for vector databases.

    Trust 84Quality 93rag-knowledge

Markets and quant

Finance and trading skills

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

  • Introduction To Quantitative Finance1.5K stars

    入门资料整理：1.多因子股票量化框架开源教程 2.学界和业界的经典资料收录 3.AI + 金融的相关工作，包括LLM, Agent, benchmark(evaluation), etc.

    Trust 87Quality 94finance
  • FinRL Meta1.9K stars

    FinRL­®-Meta: Dynamic datasets and market environments for FinRL.

    Trust 86Quality 92finance

Crawlers and extraction

Web scraping skills

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

  • Docext2.0K stars

    An on-premises, OCR-free unstructured data extraction, markdown conversion and benchmarking toolkit. (https:/…

    Trust 85Quality 88document-processing
  • OpenOCR1.4K stars

    OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and…

    Trust 86Quality 97document-processing
  • Deep Text Recognition Benchmark3.9K stars

    Text recognition (optical character recognition) with deep learning methods, ICCV 2019

    Trust 80Quality 70document-processing

Slides and decks

PPT and presentation skills

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

  • Design Judge Skills111 stars

    Evidence-driven Agent Skills for design award research, evaluation, award matching, entry writing, and submis…

    Trust 86Quality 87design-creative

Prompts, B-roll, explainers

Video creation skills

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

  • RNSkill Video Title1.1K stars

    Generate topic-first, two-part video-title candidates from an approved video brief or final script.

    Trust 74Quality 81Video Creation
  • Fiftyone11K stars

    Refine high-quality datasets and visual AI models

    Trust 88Quality 100coding-agents
  • Video ChatGPT1.5K stars

    [ACL 2024 🔥] Video-ChatGPT is a video conversation model capable of generating meaningful conversation about…

    Trust 84Quality 85support-automation

Images, video, UI

Design and creative skills

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

  • Fastdup1.9K stars

    fastdup is a powerful, free tool designed to rapidly generate valuable insights from image and video datasets…

    Trust 82Quality 93ml-automation
  • Datumaro680 stars

    Dataset Management Framework, a Python library and a CLI tool to build, analyze and manage Computer Vision da…

    Trust 77Quality 77robotics-iot
  • FireRedASR1.9K stars

    Open-source industrial-grade ASR models supporting Mandarin, Chinese dialects and English, achieving a new SO…

    Trust 86Quality 88media-automation

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

218

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

218 quality211 maintained

Research

Research and knowledge work

90

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

90 quality86 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

15

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

15 quality15 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

65

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

65 quality60 maintained

Data

Data, BI, and analytics

43

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

43 quality41 maintained

Legal

Legal, policy, and compliance

11

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

11 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

4

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

4 quality4 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 448 ranked candidates matching "benchmark-datasets"

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

1

CLUEDatasetSearch

VERIFIEDPROMISING · 66TRUST · 75SAFE · EXPERIMENTALRESEARCH

搜索所有中文NLP数据集，附常用英文NLP数据集

$ npx skills add CLUEbenchmark/CLUEDatasetSearch
4.5K stars52 quality75 trustExperimental4y 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: License is unclear
Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario RAG and knowledge

CLI + Codex · 4 targets

pythonknowledge-graph
by CLUEbenchmarkDetailsQuick view
2

Datasets

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDDESIGN

🤗 The largest hub of ready-to-use datasets for AI models with fast, easy-to-use and efficient data manipulation tools

$ npx skills add huggingface/datasets
21.6K 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 Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by huggingfaceDetailsQuick view
3

Chinese Llm Benchmark

VERIFIEDEXCELLENT · 100TRUST · 85SAFE · REVIEWEDCODING

非线智能 NoneLinear - ReLE评测：中文AI大模型能力评测（持续更新）：目前已囊括374个大模型，覆盖chatgpt、gpt-5.4、谷歌gemini-3.1-pro、Claude-4.6、文心ERNIE-X1.1、ERNIE-5.0、qwen3.6-max、qwen3.6-plus、百川、讯飞星火、商汤senseChat…

$ npx skills add jeinlee1991/chinese-llm-benchmark
6.2K stars68 quality85 trustReviewedClaude Code + OpenAI Agents2mo 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 GitHub automation

Claude Code + OpenAI Agents · 4 targets

llm
by jeinlee1991DetailsQuick view
4

Deep Text Recognition Benchmark

VERIFIEDSTRONG · 70TRUST · 80SAFE · EXPERIMENTALRESEARCH

Text recognition (optical character recognition) with deep learning methods, ICCV 2019

$ npx skills add clovaai/deep-text-recognition-benchmark
3.9K stars52 quality80 trustExperimental2y since pushNeeds review
QualitySolid option that is likely worth shortlisting for production workflows.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 Document processing

CLI + Codex · 4 targets

jupyter-notebookocr
by clovaaiDetailsQuick view
5

Mteb

VERIFIEDEXCELLENT · 98TRUST · 86SAFE · REVIEWEDRESEARCH

MTEB: Massive Text Embedding Benchmark

$ npx skills add embeddings-benchmark/mteb
3.3K stars66 quality86 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 RAG and knowledge

CLI + Codex · 4 targets

pythonsemantic-search
by embeddings-benchmarkDetailsQuick view
6

Speech To Text Benchmark

STRONG · 74TRUST · 77SAFE · REVIEWEDDESIGN

speech to text benchmark framework

$ npx skills add Picovoice/speech-to-text-benchmark
693 stars51 quality77 trustReviewed with permission notes5mo 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

pythonspeech
by PicovoiceDetailsQuick view
7

Transfermarkt Datasets

STRONG · 78TRUST · 78SAFE · REVIEWEDWORLD CUP

⚽️ Extract, prepare and publish Transfermarkt datasets.

$ npx skills add dcaribou/transfermarkt-datasets
444 stars52 quality78 trustReviewed22d 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 Sports analytics

CLI + Codex · 4 targets

pythonsports-data
by dcaribouDetailsQuick view
8

Browsers Benchmark

STRONG · 73TRUST · 77SAFE · REVIEWEDCODING

Browser automation engine benchmark - Test bypass rates, performance & stealth against Cloudflare, DataDome, reCAPTCHA, Kasada, Imperva, Akamai, PerimeterX and other bot…

$ npx skills add techinz/browsers-benchmark
335 stars51 quality77 trustReviewed with permission notesBrowser agents2mo 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 Testing and QA

Browser agents + CLI · 4 targets

pythonplaywright
by techinzDetailsQuick view
9

Beir

VERIFIEDSTRONG · 81TRUST · 84SAFE · REVIEWEDRESEARCH

A Heterogeneous Benchmark for Information Retrieval. Easy to use, evaluate your models across 15+ diverse IR datasets.

$ npx skills add beir-cellar/beir
2.2K stars54 quality84 trustReviewed with permission notes10mo 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 RAG and knowledge

CLI + Codex · 4 targets

pythonrag
by beir-cellarDetailsQuick view
10

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 Agents19d 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
11

Kube Bench

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDCODING

Checks whether Kubernetes is deployed according to security best practices as defined in the CIS Kubernetes Benchmark

$ npx skills add aquasecurity/kube-bench
8.1K stars69 quality90 trustReviewed20d 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 aquasecurityDetailsQuick view
12

Torchgeo

VERIFIEDEXCELLENT · 99TRUST · 88SAFE · REVIEWEDCODING

TorchGeo: datasets, samplers, transforms, and pre-trained models for geospatial data

$ npx skills add torchgeo/torchgeo
4.1K stars67 quality88 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 Coding agents

CLI + Codex · 4 targets

pythoncomputer-vision
by torchgeoDetailsQuick view
13

Fashion Mnist

VERIFIEDSTRONG · 77TRUST · 79SAFE · EXPERIMENTALRESEARCH

A MNIST-like fashion product database. Benchmark :point_down:

$ npx skills add zalandoresearch/fashion-mnist
12.8K stars57 quality79 trustExperimental4y since pushNeeds review
QualitySolid option that is likely worth shortlisting for production workflows.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 Research agents

CLI + Codex · 4 targets

pythonmachine-learning
by zalandoresearchDetailsQuick view
14

Roapi

VERIFIEDEXCELLENT · 95TRUST · 84SAFE · REVIEWEDDATA

Create full-fledged APIs for slowly moving datasets without writing a single line of code.

$ npx skills add roapi/roapi
3.4K stars63 quality84 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 Database and SQL

CLI + Codex · 4 targets

rustsql
by roapiDetailsQuick view
15

Objectron

VERIFIEDEXCELLENT · 90TRUST · 83SAFE · REVIEWEDRESEARCH

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and pla…

$ npx skills add google-research-datasets/Objectron
2.3K stars58 quality83 trustReviewed5mo 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

jupyter-notebookcomputer-vision
by google-research-datasetsDetailsQuick view
16

Cleverhans

VERIFIEDSTRONG · 73TRUST · 82SAFE · REVIEWEDCODING

An adversarial example library for constructing attacks, building defenses, and benchmarking both

$ npx skills add cleverhans-lab/cleverhans
6.4K stars53 quality82 trustReviewed with permission notes2y since pushNeeds review
QualitySolid option that is likely worth shortlisting for production workflows.Check: Repository looks stale
TrustGood trust signals with a few areas worth checking before rollout.Review: Repository looks stale
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation

CLI + Codex · 4 targets

jupyter-notebookmachine-learning
by cleverhans-labDetailsQuick 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