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.

  • Frontend Design166K stars

    Guidance for distinctive, intentional UI design, typography, visual direction, and non-template-like product…

    Trust 88Quality 100design-creative
  • Material Ui98K stars

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

    Trust 90Quality 100design-creative
  • Taste Skill: Anti-Slop Frontend71K stars

    Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful r…

    Trust 91Quality 100design-creative

Codex, Claude Code, Cursor

Coding agent skills

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

  • Honey For Devs177 stars

    Honey (I Shrunk the AI) by GreenPT: a cross-tool coding skill that cuts AI coding-agent token usage and LLM A…

    Trust 72Quality 80coding-agents
  • Code Review169K stars

    Review a diff separately for code standards and spec compliance.

    Trust 91Quality 100coding-agents
  • Planning With Files26K stars

    Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plan…

    Trust 89Quality 100agent-skills

Documents and knowledge

Research and RAG skills

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

  • Markitdown156K stars

    Python tool for converting files and office documents to Markdown.

    Trust 87Quality 100document-processing
  • PaddleOCR83K stars

    Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bri…

    Trust 89Quality 100document-processing
  • Understand Anything75K stars

    Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, s…

    Trust 88Quality 100rag-knowledge

Markets and quant

Finance and trading skills

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

  • TradingAgents88K stars

    TradingAgents: Multi-Agents LLM Financial Trading Framework

    Trust 88Quality 100finance
  • Crypto AI Trading Bot141 stars

    Crypto liquidity detection & algorithmic trading bot. Order book analysis, stop-loss clusters, liquidity swee…

    Trust 75Quality 62finance
  • Solana Sniper Trading Mev Bot148 stars

    Solana trading bot for sniping new tokens on Raydium AMM v4 and pump.fun. Features real-time on-chain monitor…

    Trust 78Quality 67finance

Crawlers and extraction

Web scraping skills

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

  • Firecrawl139K stars

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

    Trust 87Quality 100agent-frameworks
  • Crawl4AI73K stars

    Web crawling built for AI

    Trust 90Quality 100web-automation
  • Scrapling70K stars

    Adaptive web scraping for agent data collection

    Trust 85Quality 100web-automation

Slides and decks

PPT and presentation skills

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

  • Open Design83K stars

    🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design…

    Trust 91Quality 100agent-skills
  • MegaParse7.4K stars

    File Parser optimised for LLM Ingestion with no loss 🧠 Parse PDFs, Docx, PPTx in a format that is ideal for…

    Trust 82Quality 73document-processing
  • Apple Design18K stars

    Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or…

    Trust 91Quality 100design-creative

Prompts, B-roll, explainers

Video creation skills

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

  • RNSkill Local TTS Narration1.1K stars

    Generate a controlled local narration workflow with auditions, version tracking, and subtitle-ready final aud…

    Trust 72Quality 80Video Creation
  • MoneyPrinterTurbo89K stars

    利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

    Trust 88Quality 100automation
  • Cs Video Courses82K stars

    List of Computer Science courses with video lectures.

    Trust 85Quality 100ml-automation

Images, video, UI

Design and creative skills

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

  • Anthropic Brand Guidelines166K stars

    Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related arti…

    Trust 88Quality 100design-creative
  • Canvas Design166K stars

    Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.

    Trust 87Quality 100design-creative
  • Class Balanced Loss615 stars

    Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

    Trust 71Quality 48robotics-iot

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

182

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

178 quality174 maintained

Research

Research and knowledge work

73

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

70 quality66 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

18

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

16 quality16 maintained

Marketing

Marketing and growth automation

11

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

10 quality10 maintained

Design

Design and creative production

51

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

50 quality47 maintained

Data

Data, BI, and analytics

31

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

31 quality31 maintained

Legal

Legal, policy, and compliance

10

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

10 quality10 maintained

Education

Education and tutoring

6

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

6 quality6 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 373 ranked candidates matching "triplet-loss"

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

1

Tensorflow Triplet Loss

VERIFIEDPROMISING · 65TRUST · 78SAFE · EXPERIMENTALRESEARCH

Implementation of triplet loss in TensorFlow

$ npx skills add omoindrot/tensorflow-triplet-loss
1.1K stars48 quality78 trustExperimental7y 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

pythonembeddings
by omoindrotDetailsQuick view
2

Siamese Triplet

VERIFIEDPROMISING · 69TRUST · 77SAFE · REVIEWEDDESIGN

Siamese and triplet networks with online pair/triplet mining in PyTorch

$ npx skills add adambielski/siamese-triplet
3.2K stars51 quality77 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

pythonmachine-learning
by adambielskiDetailsQuick view
3

Pytorch Center Loss

NEEDS REVIEW · 50TRUST · 71SAFE · EXPERIMENTALCODING

Pytorch implementation of Center Loss

$ npx skills add KaiyangZhou/pytorch-center-loss
992 stars40 quality71 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 GitHub automation

CLI + Codex · 4 targets

pythoncomputer-vision
by KaiyangZhouDetailsQuick view
4

Class Balanced Loss Pytorch

NEEDS REVIEW · 49TRUST · 73SAFE · EXPERIMENTALCODING

Pytorch implementation of the paper "Class-Balanced Loss Based on Effective Number of Samples"

$ npx skills add vandit15/Class-balanced-loss-pytorch
803 stars39 quality73 trustExperimental2y 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

CLI + Codex · 4 targets

pythoncomputer-vision
by vandit15DetailsQuick view
5

Blossom

VERIFIEDEXCELLENT · 87TRUST · 84SAFE · REVIEWEDRESEARCH

A markdown editor that you can deploy on your own servers to achieve cloud storage and device synchronization（支持私有部署的云端存储双链笔记软件）

$ npx skills add blossom-editor/blossom
3.8K stars60 quality84 trustReviewed with permission notes7mo 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Document processing

CLI + Codex · 4 targets

javamarkdown
by blossom-editorDetailsQuick view
6

Ml Glossary

VERIFIEDPROMISING · 69TRUST · 79SAFE · REVIEWEDCODING

Machine learning glossary

$ npx skills add bfortuner/ml-glossary
3.1K stars51 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

pythonmachine-learning
by bfortunerDetailsQuick view
7

Focal Frequency Loss

NEEDS REVIEW · 49TRUST · 72SAFE · EXPERIMENTALDESIGN

[ICCV 2021] Focal Frequency Loss for Image Reconstruction and Synthesis

$ npx skills add EndlessSora/focal-frequency-loss
710 stars39 quality72 trustExperimental2y 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 Multimodal media

CLI + Codex · 4 targets

pythonimage-generation
by EndlessSoraDetailsQuick view
8

Class Balanced Loss

NEEDS REVIEW · 48TRUST · 71SAFE · EXPERIMENTALDESIGN

Class-Balanced Loss Based on Effective Number of Samples. CVPR 2019

$ npx skills add richardaecn/class-balanced-loss
615 stars38 quality71 trustExperimental5y 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 Multimodal media

CLI + Codex · 4 targets

pythoncomputer-vision
by richardaecnDetailsQuick view
9

Colossus

NEEDS REVIEW · 48TRUST · 71SAFE · EXPERIMENTALMARKETING

Self-hosted email marketing solution

$ npx skills add vitorfs/colossus
563 stars38 quality71 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 Marketing and growth

CLI + Codex · 4 targets

pythonemail-automation
by vitorfsDetailsQuick view
10

Triplet Attention

NEEDS REVIEW · 47TRUST · 73SAFE · EXPERIMENTALRESEARCH

Official PyTorch Implementation for "Rotate to Attend: Convolutional Triplet Attention Module." [WACV 2021]

$ npx skills add landskape-ai/triplet-attention
442 stars37 quality73 trustExperimental1y 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 Research agents

CLI + Codex · 4 targets

jupyter-notebookresearch
by landskape-aiDetailsQuick view
11

Robot Colosseum

NEEDS REVIEW · 37TRUST · 67SAFE · BLOCKEDCODING

A Benchmark for Evaluating Generalization for Robotic Manipulation

$ npx skills add robot-colosseum/robot-colosseum
149 stars34 quality67 trustBlocked for auto-install1y since pushRisky
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: License is unclear
Safety gateThis skill should not be selected by an agent without explicit human security review.

Scenario GitHub automation

CLI + Codex · 4 targets

pythonrobotics
by robot-colosseumDetailsQuick view
12

Gitleaks

VERIFIEDEXCELLENT · 100TRUST · 85SAFE · REVIEWEDCODING

Find secrets with Gitleaks 🔑

$ npx skills add gitleaks/gitleaks
27.7K stars74 quality85 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: Documentation summary is thin
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation

CLI + Codex · 4 targets

goci/cd
by gitleaksDetailsQuick view
13

Crawl4AI

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDRESEARCH

Web crawling built for AI

$ npx skills add unclecode/crawl4ai
4 agent calls100% success73.1K stars80 quality90 trustReviewedClaude Code + OpenAI Agents19d since pushSafe to try31.0K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents

Claude Code + OpenAI Agents · 4 targets

claudegpt-4langchaincrewaiopenclaw
by unclecodeDetailsQuick view
14

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
15

Playwright Browser Skill

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDCODING

Automate a real browser from the terminal for navigation, form filling, snapshots, screenshots, extraction, and UI-flow debugging.

$ npx skills add openai/skills --skill playwright
24.0K stars91 quality86 trustReviewed with permission notesClaude Code + OpenAI Agents19d since pushSafe to try28.8K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Browser automation can submit data; confirm the target environment and review a…
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Browser automation can submit data; confirm the target environment and review a…
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Testing and QA

Claude Code + OpenAI Agents · 4 targets

codexclaude-codecursorplaywright
by openaiDetailsQuick view
16

Firecrawl

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDRESEARCH

Web data for AI applications

$ npx skills add firecrawl/firecrawl
134.2K stars76 quality87 trustReviewedClaude Code + OpenAI Agents2mo since pushSafe to try25.0K 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 Document processing

Claude Code + OpenAI Agents · 4 targets

claudegpt-4langchainopenclaw
by mendableaiDetailsQuick 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