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.

  • Yoga243 stars

    Yoga design-system: a scientific system of practices made to help each one of us achieve our highest potentia…

    Trust 78Quality 72design-creative
  • all ComfyUI http/ws APIs. support NodeJS / Browser environments. and advanced programmable workflow.

    Trust 77Quality 67media-automation
  • Cloudnative Pg9.0K stars

    CloudNativePG is a comprehensive platform designed to seamlessly manage PostgreSQL databases within Kubernete…

    Trust 89Quality 100devops

Codex, Claude Code, Cursor

Coding agent skills

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

  • 🐙 One brain, many arms — a curated prompt library for long-horizon agent work, compiled to each host (Claude…

    Trust 74Quality 65coding-agents
  • Cc Thingz35 stars

    Portable skills, agents, hooks, and Pi extensions for Claude Code, Codex CLI, Copilot, Cursor, Grok, and Pi.

    Trust 74Quality 65coding-agents
  • ReiPenFlow168 stars

    Codex skill for local sandbox, CTF, authorized pentest and reverse-engineering workflows.

    Trust 85Quality 87security

Documents and knowledge

Research and RAG skills

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

  • GraphRAG4OpenWebUI integrates Microsoft's GraphRAG technology into Open WebUI, providing a versatile informat…

    Trust 73Quality 54rag-knowledge
  • Java RAG160 stars

    This RAG (Retrieval-Augmented Generation) project is implemented using pure Java. This approach makes it easi…

    Trust 72Quality 42rag-knowledge
  • AI In A Box600 stars

    AI-in-a-Box leverages the expertise of Microsoft across the globe to develop and provide AI and ML solutions…

    Trust 75Quality 54support-automation

Markets and quant

Finance and trading skills

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

  • Gym Anytrading2.4K stars

    The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)

    Trust 80Quality 68finance
  • Trading Environment(OpenAI Gym) + PPO(TensorForce)

    Trust 65Quality 39finance
  • Gym Mtsim519 stars

    A general-purpose, flexible, and easy-to-use simulator alongside an OpenAI Gym trading environment for MetaTr…

    Trust 75Quality 47finance

Crawlers and extraction

Web scraping skills

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

  • OPAL AI Agent Skills Collection (Skills.md Compliant)

    Trust 78Quality 64utility
  • Mobilegym637 stars

    MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器…

    Trust 79Quality 76automation
  • Azure Arc809 stars

    Automated Azure Arc, Azure Local, IoT, and Kubernetes environments

    Trust 78Quality 74devops

Prompts, B-roll, explainers

Video creation skills

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

  • Official deployment packages to install the Kaltura platform on a server or cluster environments using native…

    Trust 71Quality 48media-automation

Images, video, UI

Design and creative skills

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

  • VIAME337 stars

    Video and Image Analytics for Multiple Environments

    Trust 73Quality 68ml-automation
  • Ml Agents19K stars

    The Unity Machine Learning Agents Toolkit (ML-Agents) is an open-source project that enables games and simula…

    Trust 87Quality 100ml-automation
  • Minimal implementation of Decision Transformer: Reinforcement Learning via Sequence Modeling in PyTorch for m…

    Trust 70Quality 45ml-automation

Analysis and pipelines

Data and analytics skills

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

  • Ipyvizzu969 stars

    Build animated charts in Jupyter Notebook and similar environments with a simple Python syntax.

    Trust 75Quality 50data-analysis
  • Data View Web474 stars

    data view/report screen(数据可视化大屏,数据报表设计器)

    Trust 69Quality 47data-analysis
  • DacFx451 stars

    DacFx, SqlPackage, and other SQL development libraries enable declarative database development and database p…

    Trust 77Quality 75data-analysis

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

245

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

231 quality217 maintained

Research

Research and knowledge work

75

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

74 quality69 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

23

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

21 quality16 maintained

Marketing

Marketing and growth automation

13

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

13 quality13 maintained

Design

Design and creative production

54

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

51 quality50 maintained

Data

Data, BI, and analytics

35

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

34 quality32 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

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

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-16 of 453 ranked candidates matching "gym-environments"

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

1

Gym Anytrading

VERIFIEDPROMISING · 68TRUST · 80SAFE · REVIEWEDFINANCE

The most simple, flexible, and comprehensive OpenAI Gym trading environment (Approved by OpenAI Gym)

$ npx skills add AminHP/gym-anytrading
2.4K stars50 quality80 trustReviewed with permission notesOpenAI Agents2y 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 Finance and quant

OpenAI Agents + CLI · 4 targets

pythontrading
by AminHPDetailsQuick view
2

Robo Gym

NEEDS REVIEW · 51TRUST · 73SAFE · EXPERIMENTALCODING

An open source toolkit for Distributed Deep Reinforcement Learning on real and simulated robots.

$ npx skills add jr-robotics/robo-gym
478 stars41 quality73 trustExperimentalOpenAI Agents1y since pushNeeds review
QualityInspect the repository carefully before adding it to an agent workflow.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

OpenAI Agents + CLI · 4 targets

pythonrobotics
by jr-roboticsDetailsQuick view
3

Gym Trading Env

NEEDS REVIEW · 47TRUST · 67SAFE · EXPERIMENTALFINANCE

A simple, easy, customizable Gymnasium environment for trading.

$ npx skills add ClementPerroud/Gym-Trading-Env
494 stars38 quality67 trustExperimental1y 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 Finance and quant

CLI + Codex · 4 targets

pythontrading
by ClementPerroudDetailsQuick view
4

Gym Pybullet Drones

VERIFIEDEXCELLENT · 95TRUST · 88SAFE · REVIEWEDCODING

PyBullet Gymnasium environments for single and multi-agent reinforcement learning of quadcopter control

$ npx skills add learnsyslab/gym-pybullet-drones
2.0K 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 Coding agents

CLI + Codex · 4 targets

pythonmulti-agent
by learnsyslabDetailsQuick view
5

FinRL Meta

VERIFIEDEXCELLENT · 92TRUST · 86SAFE · REVIEWEDFINANCE

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

$ npx skills add AI4Finance-Foundation/FinRL-Meta
1.9K stars62 quality86 trustReviewedOpenAI Agents2mo 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

OpenAI Agents + CLI · 4 targets

pythonfinance
by AI4Finance-FoundationDetailsQuick view
6

Ma Gym

NEEDS REVIEW · 48TRUST · 71SAFE · EXPERIMENTALCODING

A collection of multi agent environments based on OpenAI gym.

$ npx skills add koulanurag/ma-gym
632 stars38 quality71 trustExperimentalOpenAI Agents2y 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 GitHub automation

OpenAI Agents + CLI · 4 targets

pythonmulti-agent
by koulanuragDetailsQuick view
7

Ksim Gym

PROMISING · 58TRUST · 74SAFE · REVIEWEDCODING

K-Sim Gym: Making robots useful with RL. Built on top of K-Sim.

$ npx skills add kscalelabs/ksim-gym
314 stars40 quality74 trustReviewed with permission notes12mo 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 GitHub automation

CLI + Codex · 4 targets

jupyter-notebookrobotics
by kscalelabsDetailsQuick view
8

Mobilegym

STRONG · 76TRUST · 79SAFE · REVIEWEDRESEARCH

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research · 浏览器里运行的安卓模拟器 · Browser-hosted Android Simulator · Verifiable Evaluation ·…

$ npx skills add Purewhiter/mobilegym
637 stars53 quality79 trustReviewed with permission notesBrowser agents1mo 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Research agents

Browser agents + CLI · 4 targets

typescriptautomation
by PurewhiterDetailsQuick view
9

Gymie

STRONG · 70TRUST · 74SAFE · REVIEWEDMARKETING

👨‍💻 Gym & Club Management System https://gymie.in

$ npx skills add lubusIN/gymie
470 stars52 quality74 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: License is unclear
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Marketing and growth

CLI + Codex · 4 targets

phpcrm
by lubusINDetailsQuick view
10

Laravel Gymie

STRONG · 70TRUST · 74SAFE · REVIEWEDMARKETING

👨‍💻 Gym & Club Management System https://gymie.in

$ npx skills add lubusIN/laravel-gymie
467 stars52 quality74 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 Marketing and growth

CLI + Codex · 4 targets

phpcrm
by lubusINDetailsQuick view
11

Llm Rl Environments Lil Course

STRONG · 71TRUST · 78SAFE · REVIEWEDCODING

🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models

$ npx skills add anakin87/llm-rl-environments-lil-course
213 stars50 quality78 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 Coding agents

CLI + Codex · 4 targets

pythonllm
by anakin87DetailsQuick view
12

Gym Mtsim

NEEDS REVIEW · 47TRUST · 75SAFE · EXPERIMENTALFINANCE

A general-purpose, flexible, and easy-to-use simulator alongside an OpenAI Gym trading environment for MetaTrader 5 trading platform (Approved by OpenAI Gym)

$ npx skills add AminHP/gym-mtsim
519 stars38 quality75 trustExperimentalOpenAI Agents2y since pushNeeds review
QualityInspect the repository carefully before adding it to an agent workflow.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 Finance and quant

OpenAI Agents + CLI · 4 targets

pythontrading
by AminHPDetailsQuick view
13

Freqtrade Gym

PROMISING · 61TRUST · 75SAFE · REVIEWEDFINANCE

A customized gym environment for developing and comparing reinforcement learning algorithms in crypto trading.

$ npx skills add hugocen/freqtrade-gym
230 stars43 quality75 trustReviewed with permission notes7mo 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 Finance and quant

CLI + Codex · 4 targets

pythontrading
by hugocenDetailsQuick view
14

Gym ContinuousDoubleAuction

PROMISING · 63TRUST · 77SAFE · REVIEWEDFINANCE

A custom MARL (multi-agent reinforcement learning) environment where multiple agents trade against one another (self-play) in a zero-sum continuous double auction. Ray […

$ npx skills add ChuaCheowHuan/gym-continuousDoubleAuction
153 stars42 quality77 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: Quality score needs review
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 ChuaCheowHuanDetailsQuick view
15

Humanoid Gym

VERIFIEDPROMISING · 62TRUST · 78SAFE · REVIEWEDDESIGN

Humanoid-Gym: Reinforcement Learning for Humanoid Robot with Zero-Shot Sim2Real Transfer https://arxiv.org/abs/2404.05695

$ npx skills add roboterax/humanoid-gym
2.0K stars50 quality78 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: 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 roboteraxDetailsQuick view
16

TradingGym

VERIFIEDPROMISING · 67TRUST · 78SAFE · REVIEWEDFINANCE

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

$ npx skills add Yvictor/TradingGym
1.9K stars50 quality78 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 Finance and quant

CLI + Codex · 4 targets

pythontrading-bot
by YvictorDetailsQuick 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