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.

  • Abc Def103 stars

    ABC Def is an efficient design system using a three-tier token structure and Headless UI to create web compon…

    Trust 74Quality 68design-creative
  • Werf4.7K stars

    A solution for implementing efficient and consistent software delivery to Kubernetes facilitating best practi…

    Trust 88Quality 100devops
  • DevOps Guide9.3K stars

    DevOps Guide - Development to Production all configurations with basic notes to debug efficiently.

    Trust 88Quality 99devops

Codex, Claude Code, Cursor

Coding agent skills

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

  • Ownyourcode177 stars

    Claude Code workflow for AI-mentored development. Work efficiently with Spec-Driven Development and the 6 Gat…

    Trust 75Quality 71coding-agents
  • Skills377 stars

    Agent Skills for VueUse

    Trust 81Quality 92coding-agents
  • Opentelemetry Agent Skills65 stars

    Vendor-neutral OpenTelemetry skills for AI coding agents, grounded in upstream sources

    Trust 75Quality 70coding-agents

Documents and knowledge

Research and RAG skills

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

  • RAG Retrieval1.1K stars

    Unify Efficient Fine-tuning of RAG Retrieval, including Embedding, ColBERT, ReRanker.

    Trust 87Quality 93rag-knowledge
  • Hora2.7K stars

    🚀 efficient approximate nearest neighbor search algorithm collections library written in Rust 🦀 .

    Trust 86Quality 90rag-knowledge
  • Keras TextClassification1.8K stars

    中文长文本分类、短句子分类、多标签分类、两句子相似度（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classi…

    Trust 80Quality 73rag-knowledge

Markets and quant

Finance and trading skills

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

  • PyPortfolioOpt5.8K stars

    Financial portfolio optimisation in python, including classical efficient frontier, Black-Litterman, Hierarch…

    Trust 89Quality 100finance
  • FISCO BCOS2.6K stars

    FISCO BCOS（发音为/ˈfɪskl bi:ˈkɒz/）是一个稳定、高效、安全的许可区块链平台，已被广泛应用于现实的行业应用。截至目前，已拥有5000多家企事业单位，400多个产业数字化标杆应用，涵盖文化版权、司…

    Trust 89Quality 100finance
  • Iotex Core1.6K stars

    Official implementation of IoTeX blockchain protocol in Go. An ultra-efficient EVM blockchain offering 1000 T…

    Trust 88Quality 100web3-analytics

Crawlers and extraction

Web scraping skills

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

  • DotnetSpider4.1K stars

    DotnetSpider, a .NET standard web crawling library. It is lightweight, efficient and fast high-level web craw…

    Trust 86Quality 96web-automation
  • Kuri331 stars

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

    Trust 70Quality 68web-automation
  • Extractous1.8K stars

    Fast and efficient unstructured data extraction. Written in Rust with bindings for many languages.

    Trust 81Quality 67data

Prompts, B-roll, explainers

Video creation skills

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

  • Sana8.3K stars

    SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

    Trust 89Quality 100media-automation
  • SpargeAttn1.0K stars

    [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

    Trust 86Quality 85media-automation
  • SageAttention3.4K stars

    [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAtt…

    Trust 84Quality 87media-automation

Images, video, UI

Design and creative skills

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

  • Mlx Openai Server345 stars

    A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Pytho…

    Trust 77Quality 80media-automation
  • Vllm Omni5.2K stars

    A framework for efficient model inference with omni-modality models

    Trust 87Quality 100media-automation
  • Recurrent Interface Network Pytorch209 stars

    Implementation of Recurrent Interface Network (RIN), for highly efficient generation of images and video with…

    Trust 77Quality 71media-automation

Analysis and pipelines

Data and analytics skills

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

  • ReplicaDB487 stars

    ReplicaDB is open source tool for database replication, designed for efficiently transferring bulk data betwe…

    Trust 77Quality 75data-analysis
  • Olake1.4K stars

    OLake - Fastest Databases, Kafka & S3 Replication to Apache Iceberg with Table optimization (Called OLake Fus…

    Trust 86Quality 100data-analysis
  • Efficient Data Processing Spark385 stars

    Code for "Efficient Data Processing in Spark" Course

    Trust 73Quality 69data-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

230

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

229 quality219 maintained

Research

Research and knowledge work

80

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

80 quality72 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

17

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

17 quality17 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 quality61 maintained

Data

Data, BI, and analytics

41

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

41 quality38 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

3

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

3 quality3 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 455 ranked candidates matching "efficient-attention"

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

1

SageAttention

VERIFIEDEXCELLENT · 87TRUST · 84SAFE · REVIEWEDDESIGN

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, i…

$ npx skills add thu-ml/SageAttention
3.4K stars59 quality84 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 Design and creative

CLI + Codex · 4 targets

cudavideo-generation
by thu-mlDetailsQuick view
2

Efficient Dl Systems

VERIFIEDEXCELLENT · 92TRUST · 85SAFE · REVIEWEDDESIGN

Efficient Deep Learning Systems course materials (HSE, YSDA)

$ npx skills add mryab/efficient-dl-systems
1.0K stars63 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

jupyter-notebookmlops
by mryabDetailsQuick view
3

Data Efficient Gans

VERIFIEDPROMISING · 65TRUST · 79SAFE · REVIEWEDDESIGN

[NeurIPS 2020] Differentiable Augmentation for Data-Efficient GAN Training

$ npx skills add mit-han-lab/data-efficient-gans
1.3K stars49 quality79 trustReviewed with permission notes2y 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Multimodal media

CLI + Codex · 4 targets

pythonimage-generation
by mit-han-labDetailsQuick view
4

Efficient Segmentation Networks

VERIFIEDPROMISING · 64TRUST · 79SAFE · REVIEWEDCODING

Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CG…

$ npx skills add xiaoyufenfei/Efficient-Segmentation-Networks
1.0K stars48 quality79 trustReviewed with permission notes2y 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation

CLI + Codex · 4 targets

pythoncomputer-vision
by xiaoyufenfeiDetailsQuick view
5

Knowledge Graph Attention Network

VERIFIEDPROMISING · 65TRUST · 77SAFE · EXPERIMENTALRESEARCH

KGAT: Knowledge Graph Attention Network for Recommendation, KDD2019

$ npx skills add xiangwang1223/knowledge_graph_attention_network
1.2K stars48 quality77 trustExperimental6y 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 RAG and knowledge

CLI + Codex · 4 targets

pythonknowledge-graph
by xiangwang1223DetailsQuick view
6

Efficientsam3

STRONG · 71TRUST · 77SAFE · REVIEWEDRESEARCH

EfficientSAM3 compresses SAM3 into lightweight, edge-friendly models via progressive knowledge distillation for fast promptable concept segmentation and tracking.

$ npx skills add SimonZeng7108/efficientsam3
610 stars53 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: License is unclear
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario RAG and knowledge

CLI + Codex · 4 targets

jupyter-notebookcomputer-vision
by SimonZeng7108DetailsQuick view
7

Attention Ocr

VERIFIEDPROMISING · 65TRUST · 79SAFE · EXPERIMENTALRESEARCH

A Tensorflow model for text recognition (CNN + seq2seq with visual attention) available as a Python package and compatible with Google Cloud ML Engine.

$ npx skills add emedvedev/attention-ocr
1.1K stars48 quality79 trustExperimental3y 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 Document processing

CLI + Codex · 4 targets

pythonocr
by emedvedevDetailsQuick view
8

Go Attention

STRONG · 75TRUST · 76SAFE · REVIEWEDCODING

A full attention mechanism and transformer in pure go.

$ npx skills add takara-ai/go-attention
476 stars52 quality76 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

gomachine-learning
by takara-aiDetailsQuick view
9

Efficient Data Processing Spark

PROMISING · 69TRUST · 73SAFE · REVIEWEDDATA

Code for "Efficient Data Processing in Spark" Course

$ npx skills add josephmachado/efficient_data_processing_spark
385 stars52 quality73 trustReviewed with permission notes2mo 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 Data analysis

CLI + Codex · 4 targets

pythondata-pipeline
by josephmachadoDetailsQuick view
10

LLMs From Scratch

VERIFIEDEXCELLENT · 100TRUST · 85SAFE · REVIEWEDDESIGN

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

$ npx skills add rasbt/LLMs-from-scratch
97.3K stars78 quality85 trustReviewed with permission notesOpenAI Agents2mo 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

OpenAI Agents + CLI · 4 targets

jupyter-notebookmachine-learning
by rasbtDetailsQuick view
11

Reformer Pytorch

VERIFIEDPROMISING · 68TRUST · 78SAFE · REVIEWEDCODING

Reformer, the efficient Transformer, in Pytorch

$ npx skills add lucidrains/reformer-pytorch
2.2K stars50 quality78 trustReviewed with permission notes3y 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation

CLI + Codex · 4 targets

pythonmachine-learning
by lucidrainsDetailsQuick view
12

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
13

Fault Diagnosis For Small Samples Based On Attention Mechanism

PROMISING · 68TRUST · 73SAFE · REVIEWEDDESIGN

基于注意力机制的少量样本故障诊断 pytorch

$ npx skills add liguge/Fault-diagnosis-for-small-samples-based-on-attention-mechanism
288 stars51 quality73 trustReviewed with permission notes2mo 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 Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by ligugeDetailsQuick view
14

PyPortfolioOpt

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDFINANCE

Financial portfolio optimisation in python, including classical efficient frontier, Black-Litterman, Hierarchical Risk Parity

$ npx skills add PyPortfolio/PyPortfolioOpt
5.8K stars68 quality89 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 Finance and quant

CLI + Codex · 4 targets

jupyter-notebookfinance
by PyPortfolioDetailsQuick view
15

Magnitude

VERIFIEDPROMISING · 67TRUST · 77SAFE · EXPERIMENTALCODING

A fast, efficient universal vector embedding utility package.

$ npx skills add plasticityai/magnitude
1.7K stars49 quality77 trustExperimental3y 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 GitHub automation

CLI + Codex · 4 targets

pythonembeddings
by plasticityaiDetailsQuick 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