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.

  • Stable Diffusion2.7K stars

    FLUX, Stable Diffusion, SDXL, SD3, LoRA, Fine Tuning, DreamBooth, Training, Automatic1111, Forge WebUI, Swarm…

    Trust 88Quality 100education
  • FedML4.0K stars

    FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federate…

    Trust 84Quality 89agent-frameworks
  • Kinova Isaaclab Sim2real222 stars

    Codebase for Kinova Gen3 training in Isaac Lab, sim2real transfer and ROS deployment.

    Trust 72Quality 48robotics-iot

Codex, Claude Code, Cursor

Coding agent skills

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

  • Opentelemetry Agent Skills65 stars

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

    Trust 75Quality 70coding-agents
  • AI Agent Camp344 stars

    AI Agent Camp — non-engineer-friendly AI agent training curriculum. Lessons, skills, commands, and hooks for…

    Trust 75Quality 69agent-frameworks
  • Dstack2.2K stars

    Vendor-agnostic orchestration for training, inference and agentic workloads across NVIDIA, AMD, TPU, and Tens…

    Trust 88Quality 99agent-skills

Documents and knowledge

Research and RAG skills

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

  • Deeplake9.2K stars

    Deeplake is AI Data Runtime for Agents. It provides serverless postgres with a multimodal datalake, enabling…

    Trust 87Quality 100rag-knowledge
  • S3837 stars

    [EMNLP'25] s3 - ⚡ Efficient & Effective Search Agent Training via RL for RAG (RLVR for Search with Minimal Da…

    Trust 78Quality 63rag-knowledge
  • VLM2Vec655 stars

    This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Ta…

    Trust 80Quality 76rag-knowledge

Markets and quant

Finance and trading skills

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

  • Stock Analysis Engine1.2K stars

    Backtest 1000s of minute-by-minute trading algorithms for training AI with automated pricing data from: IEX,…

    Trust 74Quality 66finance
  • TradingGym1.9K stars

    Trading and Backtesting environment for training reinforcement learning agent or simple rule base algo.

    Trust 78Quality 67finance
  • Gym ContinuousDoubleAuction153 stars

    A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one anothe…

    Trust 77Quality 63finance

Crawlers and extraction

Web scraping skills

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

  • MinerU HTML260 stars

    MinerU-HTML: An SLM-powered HTML main content extractor that outputs clean HTML bodies. Perfect for Deep Rese…

    Trust 75Quality 69web-automation
  • Crawl4AI66K stars

    Open-source LLM-friendly web crawler and scraper for agent workflows.

    Trust 82Quality 100Web Scraping
  • Craw4LLM653 stars

    Official repository for "Craw4LLM: Efficient Web Crawling for LLM Pretraining"

    Trust 72Quality 48web-automation

Slides and decks

PPT and presentation skills

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

  • Gitpitch5.5K stars

    Markdown Presentations for Tech Conferences, Training, Developer Advocates, and Educators.

    Trust 78Quality 67document-processing
  • Container.Training3.9K stars

    Slides and code samples for training, tutorials, and workshops about Docker, containers, and Kubernetes.

    Trust 80Quality 93devops

Prompts, B-roll, explainers

Video creation skills

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

  • FastVideo3.7K stars

    A unified inference and post-training framework for accelerated video generation.

    Trust 88Quality 98media-automation
  • SpargeAttn1.0K stars

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

    Trust 86Quality 85media-automation
  • Lmms Engine791 stars

    A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.

    Trust 77Quality 72media-automation

Images, video, UI

Design and creative skills

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

  • Story Iter958 stars

    [ICLR 2026] A Training-free Iterative Framework for Long Story Visualization

    Trust 77Quality 75media-automation
  • SeedVR2790 stars

    [ICLR2026] SeedVR2: One-Step Video Restoration via Diffusion Adversarial Post-Training

    Trust 77Quality 66media-automation
  • STT2.6K stars

    🐸STT - The deep learning toolkit for Speech-to-Text. Training and deploying STT models has never been so eas…

    Trust 78Quality 69media-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

51

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

46 quality36 maintained

Research

Research and knowledge work

27

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

27 quality19 maintained

Presentation

Presentation and deck workflows

0

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

0 quality0 maintained

Finance

Finance and quant workflows

8

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

8 quality4 maintained

Marketing

Marketing and growth automation

0

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

0 quality0 maintained

Design

Design and creative production

69

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

68 quality44 maintained

Data

Data, BI, and analytics

0

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

0 quality0 maintained

Legal

Legal, policy, and compliance

1

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

1 quality1 maintained

Education

Education and tutoring

1

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

1 quality1 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 159 ranked candidates matching "ai-training"

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

1

Python Training

VERIFIEDSTRONG · 77TRUST · 80SAFE · REVIEWEDFINANCE

Python training for business analysts and traders

$ npx skills add jpmorganchase/python-training
13.6K stars57 quality80 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 Finance and quant

CLI + Codex · 4 targets

jupyter-notebookfinance
by jpmorganchaseDetailsQuick view
2

Container.Training

VERIFIEDEXCELLENT · 93TRUST · 80SAFE · REVIEWEDCODING

Slides and code samples for training, tutorials, and workshops about Docker, containers, and Kubernetes.

$ npx skills add jpetazzo/container.training
3.9K stars67 quality80 trustReviewed with permission notes2mo 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

CLI + Codex · 4 targets

shellkubernetes
by jpetazzoDetailsQuick view
3

Training

VERIFIEDEXCELLENT · 92TRUST · 86SAFE · REVIEWEDDESIGN

Reference implementations of MLPerf® training benchmarks

$ npx skills add mlcommons/training
1.8K stars61 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 mlcommonsDetailsQuick view
4

Training Extensions

VERIFIEDEXCELLENT · 93TRUST · 86SAFE · REVIEWEDDESIGN

Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™

$ npx skills add open-edge-platform/training_extensions
1.2K 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 Multimodal media

CLI + Codex · 4 targets

pythoncomputer-vision
by open-edge-platformDetailsQuick view
5

Ort

VERIFIEDEXCELLENT · 96TRUST · 85SAFE · REVIEWEDDESIGN

Fast ML inference & training for ONNX models in Rust

$ npx skills add pykeio/ort
2.3K 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

rustmachine-learning
by pykeioDetailsQuick view
6

Industrial Training

STRONG · 72TRUST · 77SAFE · REVIEWEDCODING

ROS-Industrial Training Material

$ npx skills add ros-industrial/industrial_training
475 stars49 quality77 trustReviewed with permission notes3mo 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

c++ros
by ros-industrialDetailsQuick view
7

LLaSA Training

PROMISING · 60TRUST · 74SAFE · REVIEWEDDESIGN

LLaSA: Scaling Train-time and Inference-time Compute for LLaMA-based Speech Synthesis

$ npx skills add zhenye234/LLaSA_training
661 stars46 quality74 trustReviewed with permission notes6mo 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

pythonvoice
by zhenye234DetailsQuick view
8

BMW YOLOv4 Training Automation

NEEDS REVIEW · 54TRUST · 69SAFE · EXPERIMENTALCODING

This repository allows you to get started with training a state-of-the-art Deep Learning model with little to no configuration needed! You provide your labeled dataset o…

$ npx skills add BMW-InnovationLab/BMW-YOLOv4-Training-Automation
653 stars38 quality69 trustExperimental3y 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 Coding agents

CLI + Codex · 4 targets

pythonmonitoring
by BMW-InnovationLabDetailsQuick view
9

Crawl4AI

EXCELLENT · 100TRUST · 82SAFE · REVIEWEDRESEARCH

Open-source LLM-friendly web crawler and scraper for agent workflows.

$ npx skills add unclecode/crawl4ai
4 agent calls100% success66.0K stars96 quality82 trustReviewedClaude Code + OpenAI Agents2mo since pushSafe to try79.2K installs
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 Research agents

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursor
by unclecodeDetailsQuick view
10

Composer

VERIFIEDEXCELLENT · 97TRUST · 85SAFE · REVIEWEDDESIGN

Supercharge Your Model Training

$ npx skills add mosaicml/composer
5.5K stars65 quality85 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: 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 mosaicmlDetailsQuick view
11

FastVideo

VERIFIEDEXCELLENT · 98TRUST · 88SAFE · REVIEWEDDESIGN

A unified inference and post-training framework for accelerated video generation.

$ npx skills add hao-ai-lab/FastVideo
3.7K stars67 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 Design and creative

CLI + Codex · 4 targets

pythonvideo-generation
by hao-ai-labDetailsQuick view
12

Agent Skills

EXCELLENT · 100TRUST · 78SAFE · REVIEWEDCODING

Production-grade engineering skills and quality gates for AI coding agents.

$ npx skills add addyosmani/agent-skills
9 agent calls88.89% success61.8K stars94 quality78 trustReviewed with permission notesClaude Code + OpenAI Agents2mo since pushSafe to try74.2K installs
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

Claude Code + OpenAI Agents · 4 targets

claude-codecursorgemini-clicodex
by addyosmaniDetailsQuick view
13

StyleTTS2

VERIFIEDSTRONG · 72TRUST · 83SAFE · REVIEWEDDESIGN

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

$ npx skills add yl4579/StyleTTS2
6.3K stars53 quality83 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 Multimodal media

CLI + Codex · 4 targets

pythonvoice
by yl4579DetailsQuick view
14

FedML

VERIFIEDEXCELLENT · 89TRUST · 84SAFE · REVIEWEDCODING

FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further e…

$ npx skills add FedML-AI/FedML
4.0K stars56 quality84 trustReviewed9mo 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.
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

CLI + Codex · 4 targets

pythonai-agents
by FedML-AIDetailsQuick view
15

Determined

VERIFIEDPROMISING · 69TRUST · 82SAFE · REVIEWEDCODING

Determined is an open-source machine learning platform that simplifies distributed training, hyperparameter tuning, experiment tracking, and resource management. Works w…

$ npx skills add determined-ai/determined
3.2K stars51 quality82 trustReviewed with permission notes1y 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

gokubernetes
by determined-aiDetailsQuick view
16

Dreambooth Stable Diffusion

VERIFIEDPROMISING · 69TRUST · 80SAFE · REVIEWEDDESIGN

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/ab…

$ npx skills add JoePenna/Dreambooth-Stable-Diffusion
3.2K stars51 quality80 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 Multimodal media

CLI + Codex · 4 targets

jupyter-notebookmachine-learning
by JoePennaDetailsQuick 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