Star0

Skill Registry

Find the right skill for the job your agent is doing.

Search by task, platform, trust profile, or GitHub adoption. OpenAgentSkill keeps the interface human-readable and the API ready for agents.

36
Shown
0
Tracks
92
Targets

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

142

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

142 quality142 maintained

Research

Research and knowledge work

41

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

41 quality41 maintained

Finance

Finance and quant workflows

6

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

6 quality6 maintained

Marketing

Marketing and growth automation

4

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

4 quality4 maintained

Design

Design and creative production

11

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

11 quality11 maintained

Data

Data, BI, and analytics

21

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

21 quality21 maintained

Legal

Legal, policy, and compliance

5

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

5 quality5 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

0

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

0 quality0 maintained

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-36 of 158 ranked candidates matching "ea"

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

1

Seedance 2.0 Skill OS

EXCELLENT · 100TRUST · 85SAFE · REVIEWEDDESIGN

Direct the model. Do not micro-manage the frame.

$ python scripts/install_codex_skill.py --force
796 stars88 quality85 trustReviewed with permission notesClaude Code + OpenAI AgentsPushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Installer replaces an existing local seedance-20 skill directory when --force is used; review scripts/install_codex_skill.py before running.
TrustGood trust signals with a few areas worth checking before rollout.Review: Installer replaces an existing local seedance-20 skill directory when --force is used; review scripts/install_codex_skill.py before running.
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.Action: Require human approval before installing into a real workspace.

Scenario

Multimodal media

I need my agent to process images, video, or audio and extract useful information.

Agents

Claude Code + OpenAI Agents + CLI

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

Installer replaces an existing local seedance-20 skill directory when --force is used; review scripts/install_codex_skill.py before running.

Gate

review

Reviewed with permission notes

codexclaude-codeopenclawgemini-cligithub-copilot
by Emily2040DetailsQuick view
2

Crawl4AI

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · REVIEWEDRESEARCH

Web crawling built for AI

$ npx skills add unclecode/crawl4ai
66.2K stars79 quality95 trustReviewedClaude Code + OpenAI Agents25d 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 risk, and install availability.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Document processing

I need my agent to read PDFs, extract tables, and turn documents into structured data.

Agents

Claude Code + OpenAI Agents + LangChain

4 install targets

Maintenance

fresh

25d since push

Risk

Safe to try

Documentation summary is thin

Gate

review

Reviewed

claudegpt-4langchaincrewaiopenclaw
by unclecodeDetailsQuick view
3

AutoGPT

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDCODING

Build and run autonomous AI agents for open-ended tasks

$ npx skills add Significant-Gravitas/AutoGPT
184.9K stars79 quality87 trustReviewed with permission notesClaude Code + OpenAI Agents4d since pushNeeds review
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: License is unclear · Documentation summary is thin
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.Action: Require human approval before installing into a real workspace.

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agents

Claude Code + OpenAI Agents + CLI

4 install targets

Maintenance

fresh

4d since push

Risk

Needs review

License is unclear

Gate

review

Reviewed with permission notes

autogptpythonllm
by Significant-GravitasDetailsQuick view
4

Gemini CLI

VERIFIEDEXCELLENT · 100TRUST · 85SAFE · REVIEWEDCODING

Bring a coding agent directly into the terminal

$ npx skills add google-gemini/gemini-cli
105.0K stars79 quality85 trustReviewed with permission notesClaude Code10d 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 · Documentation summary is thin
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.Action: Require human approval before installing into a real workspace.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

10d since push

Risk

Needs review

License is unclear

Gate

review

Reviewed with permission notes

geminiclitypescript
by google-geminiDetailsQuick view
5

FreeCodeCamp

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDCODING

freeCodeCamp.org's open-source codebase and curriculum. Learn math, programming, and computer science for free.

$ npx skills add freeCodeCamp/freeCodeCamp
448.2K stars78 quality98 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

typescripteducation
by freeCodeCampDetailsQuick view
6

Free Programming Books

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDCODING

:books: Freely available programming books

$ npx skills add EbookFoundation/free-programming-books
390.3K stars78 quality95 trustVerifiedClaude Code3d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

3d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythoneducation
by EbookFoundationDetailsQuick view
7

Python

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDCODING

All Algorithms implemented in Python

$ npx skills add TheAlgorithms/Python
222.0K stars78 quality95 trustVerifiedClaude Code15d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

15d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythoneducation
by TheAlgorithmsDetailsQuick view
8

Tensorflow

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDCODING

An Open Source Machine Learning Framework for Everyone

$ npx skills add tensorflow/tensorflow
195.7K stars78 quality95 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

c++machine-learning
by tensorflowDetailsQuick view
9

Hermes Agent

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · REVIEWEDCODING

The agent that grows with you

$ npx skills add NousResearch/hermes-agent
192.1K stars78 quality95 trustReviewedClaude Code + OpenAI Agents3d 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 risk, and install availability.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + OpenAI Agents + CLI

4 install targets

Maintenance

fresh

3d since push

Risk

Safe to try

Documentation summary is thin

Gate

review

Reviewed

pythonai-agents
by NousResearchDetailsQuick view
10

Ohmyzsh

VERIFIEDEXCELLENT · 100TRUST · 94SAFE · REVIEWEDCODING

🙃 A delightful community-driven (with 2,500+ contributors) framework for managing your zsh configuration. Includes 300+ optional plugins (rails, git, macOS, hub, docker, homebrew, node, php, python, etc), 140+ themes to spice up your morning, and an auto-update tool that makes it easy to keep up with the latest updates from the community.

$ npx skills add ohmyzsh/ohmyzsh
188.1K stars78 quality94 trustReviewed with permission notesClaude Code1d 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 risk, and install availability.
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.Action: Require human approval before installing into a real workspace.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

1d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

review

Reviewed with permission notes

shellproductivity
by ohmyzshDetailsQuick view
11

Transformers

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDDESIGN

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

$ npx skills add huggingface/transformers
161.6K stars78 quality98 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Multimodal media

I need my agent to process images, video, or audio and extract useful information.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonmachine-learning
by huggingfaceDetailsQuick view
12

Markitdown

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDRESEARCH

Python tool for converting files and office documents to Markdown.

$ npx skills add microsoft/markitdown
154.2K stars78 quality95 trustVerifiedClaude Code + OpenAI Agents20d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Document processing

I need my agent to read PDFs, extract tables, and turn documents into structured data.

Agents

Claude Code + OpenAI Agents + LangChain

4 install targets

Maintenance

fresh

20d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonpdf
by microsoftDetailsQuick view
13

Skills

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDCODING

Public repository for Agent Skills

$ npx skills add anthropics/skills
150.5K stars78 quality91 trustReviewedClaude Code7d 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 risk, and install availability.Review: License is unclear · License clarity: Unknown
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

7d since push

Risk

Safe to try

License is unclear

Gate

review

Reviewed

pythonai-agents
by anthropicsDetailsQuick view
14

System Prompts And Models Of AI Tools

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDCODING

FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Trae, Traycer AI, VSCode Agent, Warp.dev, Windsurf, Xcode, Z.ai Code, Dia & v0. (And other Open Sourced) System Prompts, Internal Tools & AI Models

$ npx skills add x1xhlol/system-prompts-and-models-of-ai-tools
138.9K stars78 quality98 trustVerifiedClaude Code + Cursor24d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + Cursor + CLI

4 install targets

Maintenance

fresh

24d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

claude-code
by x1xhlolDetailsQuick view
15

Firecrawl

VERIFIEDEXCELLENT · 100TRUST · 94SAFE · VERIFIEDCODING

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

$ npx skills add firecrawl/firecrawl
132.0K stars78 quality94 trustVerifiedClaude Code3d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

3d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

typescriptai-agents
by firecrawlDetailsQuick view
16

30 Seconds Of Code

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDCODING

Coding articles to level up your development skills

$ npx skills add Chalarangelo/30-seconds-of-code
128.1K stars78 quality95 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

javascripteducation
by ChalarangeloDetailsQuick view
17

Generative AI For Beginners

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDRESEARCH

21 Lessons, Get Started Building with Generative AI

$ npx skills add microsoft/generative-ai-for-beginners
112.0K stars78 quality95 trustVerifiedClaude Code + OpenAI Agents5d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

RAG and knowledge

I need my agent to build a RAG workflow over documents and retrieve reliable context.

Agents

Claude Code + OpenAI Agents + CLI

4 install targets

Maintenance

fresh

5d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

jupyter-notebooksemantic-search
by microsoftDetailsQuick view
18

Pytorch

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDCODING

Tensors and Dynamic neural networks in Python with strong GPU acceleration

$ npx skills add pytorch/pytorch
100.8K stars78 quality91 trustReviewedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: License is unclear · License clarity: Unknown
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

License is unclear

Gate

review

Reviewed

pythonmachine-learning
by pytorchDetailsQuick view
19

Browser Use

VERIFIEDEXCELLENT · 100TRUST · 94SAFE · VERIFIEDCODING

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

$ npx skills add browser-use/browser-use
98.7K stars78 quality94 trustVerifiedClaude Code + Browser agents3d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + Browser agents + CLI

4 install targets

Maintenance

fresh

3d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonai-agents
by browser-useDetailsQuick view
20

Material Ui

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDDESIGN

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

$ npx skills add mui/material-ui
98.4K stars78 quality98 trustVerifiedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Design and creative

I need my agent to produce design assets, UI directions, presentations, or creative media workflows.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

javascriptdesign-systems
by muiDetailsQuick view
21

LLMs From Scratch

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDCODING

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

$ npx skills add rasbt/LLMs-from-scratch
97.3K stars78 quality91 trustReviewedClaude Code + OpenAI Agents14d 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 risk, and install availability.Review: License is unclear · License clarity: Unknown
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agents

Claude Code + OpenAI Agents + CLI

4 install targets

Maintenance

fresh

14d since push

Risk

Safe to try

License is unclear

Gate

review

Reviewed

jupyter-notebookmachine-learning
by rasbtDetailsQuick view
22

Web Dev For Beginners

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDEDUCATION

24 Lessons, 12 Weeks, Get Started as a Web Developer

$ npx skills add microsoft/Web-Dev-For-Beginners
95.9K stars78 quality95 trustVerifiedClaude Code2d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

2d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

javascripteducation
by microsoftDetailsQuick view
23

Puppeteer

VERIFIEDEXCELLENT · 100TRUST · 94SAFE · VERIFIEDCODING

JavaScript API for Chrome and Firefox

$ npx skills add puppeteer/puppeteer
94.8K stars78 quality94 trustVerifiedClaude Code1d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

1d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

typescriptdeveloper-tools
by puppeteerDetailsQuick view
24

ML For Beginners

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDCODING

12 weeks, 26 lessons, 52 quizzes, classic Machine Learning for all

$ npx skills add microsoft/ML-For-Beginners
86.9K stars78 quality95 trustVerifiedClaude Code7d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

GitHub automation

I need my agent to triage GitHub issues, review pull requests, and summarize repository changes.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

7d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

jupyter-notebookmachine-learning
by microsoftDetailsQuick view
25

TradingAgents

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · VERIFIEDFINANCE

TradingAgents: Multi-Agents LLM Financial Trading Framework

$ npx skills add TauricResearch/TradingAgents
86.0K stars78 quality95 trustVerifiedClaude Code2d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Finance and quant

I need my agent to analyze markets, financial data, filings, portfolios, and quant strategies.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

2d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonfinance
by TauricResearchDetailsQuick view
26

Ragflow

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDCODING

RAGFlow is a leading open-source Retrieval-Augmented Generation (RAG) engine that fuses cutting-edge RAG with Agent capabilities to create a superior context layer for LLMs

$ npx skills add infiniflow/ragflow
82.6K stars78 quality98 trustVerifiedClaude Code3d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

3d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonai-agents
by infiniflowDetailsQuick view
27

PaddleOCR

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDRESEARCH

Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.

$ npx skills add PaddlePaddle/PaddleOCR
82.1K stars78 quality98 trustVerifiedClaude Code4d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Document processing

I need my agent to read PDFs, extract tables, and turn documents into structured data.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

4d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonocr
by PaddlePaddleDetailsQuick view
28

Cs Video Courses

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDDESIGN

List of Computer Science courses with video lectures.

$ npx skills add Developer-Y/cs-video-courses
81.8K stars78 quality91 trustReviewedClaude Code1d 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 risk, and install availability.Review: License is unclear · License clarity: Unknown
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Multimodal media

I need my agent to process images, video, or audio and extract useful information.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

1d since push

Risk

Safe to try

License is unclear

Gate

review

Reviewed

machine-learning
by Developer-YDetailsQuick view
29

Stirling PDF

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDRESEARCH

#1 PDF Application on GitHub that lets you edit PDFs on any device anywhere

$ npx skills add Stirling-Tools/Stirling-PDF
81.1K stars78 quality90 trustReviewedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: License is unclear · License clarity: Unknown
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Document processing

I need my agent to read PDFs, extract tables, and turn documents into structured data.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

License is unclear

Gate

review

Reviewed

typescriptpdf
by Stirling-ToolsDetailsQuick view
30

OpenHands

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

🙌 OpenHands: AI-Driven Development

$ npx skills add OpenHands/OpenHands
77.3K stars77 quality88 trustReviewed with permission notesClaude Code + OpenAI AgentsPushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: License is unclear · License clarity: Unknown
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.Action: Require human approval before installing into a real workspace.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + OpenAI Agents + CLI

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

License is unclear

Gate

review

Reviewed with permission notes

pythondeveloper-tools
by OpenHandsDetailsQuick view
31

Elasticsearch

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDRESEARCH

Free and Open Source, Distributed, RESTful Search Engine

$ npx skills add elastic/elasticsearch
77.0K stars77 quality91 trustReviewedClaude CodePushed todaySafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency risk, and install availability.Review: License is unclear · License clarity: Unknown
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

RAG and knowledge

I need my agent to build a RAG workflow over documents and retrieve reliable context.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

Pushed today

Risk

Safe to try

License is unclear

Gate

review

Reviewed

javasearch
by elasticDetailsQuick view
32

Tesseract

VERIFIEDEXCELLENT · 100TRUST · 95SAFE · REVIEWEDRESEARCH

Tesseract Open Source OCR Engine (main repository)

$ npx skills add tesseract-ocr/tesseract
74.7K stars77 quality95 trustReviewedClaude Code3d 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 risk, and install availability.Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Document processing

I need my agent to read PDFs, extract tables, and turn documents into structured data.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

3d since push

Risk

Safe to try

Documentation summary is thin

Gate

review

Reviewed

c++ocr
by tesseract-ocrDetailsQuick view
33

Grafana

VERIFIEDEXCELLENT · 100TRUST · 97SAFE · VERIFIEDDATA

The open and composable observability and data visualization platform. Visualize metrics, logs, and traces from multiple sources like Prometheus, Loki, Elasticsearch, InfluxDB, Postgres and many more.

$ npx skills add grafana/grafana
74.4K stars77 quality97 trustVerifiedClaude Code1d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Data analysis

I need my agent to analyze CSV data, produce insights, and explain trends.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

1d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

typescriptbi
by grafanaDetailsQuick view
34

Front End Checklist

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDCODING

🗂 The essential checklist for modern web development, for humans and AI agents

$ npx skills add thedaviddias/Front-End-Checklist
72.9K stars77 quality91 trustReviewedClaude Code7d 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 risk, and install availability.Review: License is unclear · License clarity: Unknown
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

7d since push

Risk

Safe to try

License is unclear

Gate

review

Reviewed

mdxai-agents
by thedaviddiasDetailsQuick view
35

Deer Flow

VERIFIEDEXCELLENT · 100TRUST · 98SAFE · VERIFIEDCODING

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of tasks that could take minutes to hours.

$ npx skills add bytedance/deer-flow
71.1K stars77 quality98 trustVerifiedClaude Code2d 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 risk, and install availability.
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.Action: Allow agent install in a sandbox or low-risk workspace, then promote after one successful narrow task.

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

2d since push

Risk

Safe to try

No major risk signals from available metadata

Gate

allow

Verified

pythonmulti-agent
by bytedanceDetailsQuick view
36

AFFiNE

VERIFIEDEXCELLENT · 100TRUST · 94SAFE · REVIEWEDRESEARCH

There can be more than Notion and Miro. AFFiNE(pronounced [ə‘fain]) is a next-gen knowledge base that brings planning, sorting and creating all together. Privacy first, open-source, customizable and ready to use.

$ npx skills add toeverything/AFFiNE
69.4K stars77 quality94 trustReviewedClaude Code1d 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 risk, and install availability.Review: License is unclear · License clarity: Unknown
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.Action: Review the audit page, then allow agent install in a sandboxed workflow.

Scenario

RAG and knowledge

I need my agent to build a RAG workflow over documents and retrieve reliable context.

Agents

Claude Code + CLI + Codex

4 install targets

Maintenance

fresh

1d since push

Risk

Safe to try

License is unclear

Gate

review

Reviewed

typescriptmarkdown
by toeverythingDetailsQuick view

Page 1

Showing the strongest 36 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