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.

  • This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the in…

    Trust 91Quality 100design-creative
  • Blinko11K stars

    An open-source, self-hosted personal AI note tool prioritizing privacy, built using TypeScript .

    Trust 88Quality 100document-processing
  • Typebot.Io10K stars

    💬 Typebot is a powerful chatbot builder that you can self-host.

    Trust 85Quality 99support-automation

Codex, Claude Code, Cursor

Coding agent skills

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

  • Baoyu Design2.7K stars

    Run Claude Design locally as an Agent Skill — Cursor, Claude Code & more. Produce polished UI mockups, protot…

    Trust 89Quality 100agent-skills
  • Reverse Skill6.9K stars

    Reverse Engineering / Authorized Penetration Testing / Security Research Skill Router Pack AI-powered routing…

    Trust 86Quality 100development
  • 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

Documents and knowledge

Research and RAG skills

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

  • Llm Wiki Agent3.0K stars

    A personal knowledge base that builds and maintains itself. Drop in sources — Claude (or Codex/Gemini) reads…

    Trust 79Quality 100rag-knowledge
  • Claude Obsidian7.2K stars

    Self-organizing AI second brain for Obsidian + Claude Code. Drop any source and Claude reads, links, and file…

    Trust 89Quality 100rag-knowledge
  • Cognee30K stars

    Cognee is the open-source AI memory platform for agents. Give your AI agents persistent long-term memory acro…

    Trust 90Quality 100rag-knowledge

Markets and quant

Finance and trading skills

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

  • Qlib44K stars

    Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exp…

    Trust 89Quality 100finance
  • A Stock Data8.1K stars

    A股全栈数据工具包 · 10层架构 · 43端点(含3官方备胎) · 15数据源 · 行情/研报/资金面/筹码/公告/打板/ETF期权/舆情互动全覆盖+备用源降级 | China A-Share full-stack…

    Trust 89Quality 100finance-quant
  • Finance Skills2.9K stars

    A collection of skills for AI financial analysis and trading.

    Trust 86Quality 97finance

Crawlers and extraction

Web scraping skills

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

  • TiddlyWiki58.6K stars

    A self-contained JavaScript wiki for the browser, Node.js, AWS Lambda etc.

    Trust 82Quality 97productivity-automation
  • RuVector4.3K stars

    RuVector is a High Performance, Real-Time, Self-Learning Ai, Vector GNN, Memory DB built in Rust.

    Trust 88Quality 99document-processing
  • PdfDing1.8K stars

    Selfhosted PDF manager, viewer and editor offering a seamless user experience on multiple devices.

    Trust 88Quality 98document-processing

Slides and decks

PPT and presentation skills

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

  • ClaudeSkills626 stars

    13 curated Claude Code agent skills — decks, deep research, PRDs, articles, audits. Tested like software.

    Trust 87Quality 95presentation
  • Rundeck6.1K stars

    Enable Self-Service Operations: Give specific users access to your existing tools, services, and scripts

    Trust 89Quality 100automation
  • Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact ter…

    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.

  • Video Use17K stars

    Edit videos with coding agents

    Trust 88Quality 100media
  • Voxelmorph2.7K stars

    Unsupervised Learning for Image Registration

    Trust 86Quality 97ml-automation

Images, video, UI

Design and creative skills

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

  • Kill Ai Slop786 stars

    A field guide to the visual & copy tics of AI-generated products — and an Agent Skill that scans your project…

    Trust 87Quality 95design-creative
  • Self-host the powerful Chatterbox TTS model. This server offers a user-friendly Web UI, flexible API endpoint…

    Trust 86Quality 99media-automation
  • PaddleSpeech13K stars

    Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Str…

    Trust 90Quality 100media-automation

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

223

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

223 quality222 maintained

Research

Research and knowledge work

86

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

86 quality85 maintained

Presentation

Presentation and deck workflows

2

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

2 quality2 maintained

Finance

Finance and quant workflows

18

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

18 quality18 maintained

Marketing

Marketing and growth automation

15

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

15 quality15 maintained

Design

Design and creative production

55

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

55 quality55 maintained

Data

Data, BI, and analytics

36

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

36 quality36 maintained

Legal

Legal, policy, and compliance

16

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

16 quality16 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 448 ranked candidates matching "self-supervised"

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

1

PaddleSpeech

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDDESIGN

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System,…

$ npx skills add PaddlePaddle/PaddleSpeech
12.6K stars72 quality90 trustReviewed1mo 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

pythonspeech
by PaddlePaddleDetailsQuick view
2

Self Hosted AI Starter Kit

VERIFIEDEXCELLENT · 95TRUST · 87SAFE · REVIEWEDCODING

The Self-hosted AI Starter Kit is an open-source template that quickly sets up a local AI environment. Curated by n8n, it provides essential tools for creating secure, s…

$ npx skills add n8n-io/self-hosted-ai-starter-kit
15.0K stars65 quality87 trustReviewed7mo 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

ai-agents
by n8n-ioDetailsQuick view
3

Unilm

VERIFIEDEXCELLENT · 97TRUST · 86SAFE · REVIEWEDRESEARCH

Large-scale Self-supervised Pre-training Across Tasks, Languages, and Modalities

$ npx skills add microsoft/unilm
22.2K stars67 quality86 trustReviewed6mo 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 Document processing

CLI + Codex · 4 targets

pythondocument-ai
by microsoftDetailsQuick view
4

Lightly

VERIFIEDEXCELLENT · 98TRUST · 86SAFE · REVIEWEDDESIGN

A python library for self-supervised learning on images.

$ npx skills add lightly-ai/lightly
3.8K stars67 quality86 trustReviewed1mo 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 lightly-aiDetailsQuick view
5

Mljar Supervised

VERIFIEDEXCELLENT · 98TRUST · 86SAFE · REVIEWEDCODING

Python package for AutoML on Tabular Data with Feature Engineering, Hyper-Parameters Tuning, Explanations and Automatic Documentation

$ npx skills add mljar/mljar-supervised
3.3K stars66 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 GitHub automation

CLI + Codex · 4 targets

pythonmachine-learning
by mljarDetailsQuick view
6

Semi Supervised Learning

VERIFIEDEXCELLENT · 94TRUST · 85SAFE · REVIEWEDCODING

A Unified Semi-Supervised Learning Codebase (NeurIPS'22)

$ npx skills add microsoft/Semi-supervised-learning
1.6K stars64 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 Coding agents

CLI + Codex · 4 targets

pythoncomputer-vision
by microsoftDetailsQuick view
7

自己.Skill

VERIFIEDEXCELLENT · 93TRUST · 84SAFE · REVIEWEDCODING

把最好的自己封装成 AI

$ npx skills add notdog1998/yourself-skill
3.0K stars62 quality84 trustReviewed4mo 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 GitHub automation

CLI + Codex · 4 targets

python
by notdog1998DetailsQuick view
8

Photoprism

VERIFIEDEXCELLENT · 100TRUST · 85SAFE · REVIEWEDDESIGN

AI-Powered Photos App for the Decentralized Web 🌈💎✨

$ npx skills add photoprism/photoprism
39.8K stars75 quality85 trustReviewed with permission notes2mo since pushNeeds review
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Multimodal media

CLI + Codex · 4 targets

gomachine-learning
by photoprismDetailsQuick view
9

Open Notebook

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDDATA

An Open Source implementation of Notebook LM with more flexibility and features

$ npx skills add lfnovo/open-notebook
32.0K stars75 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 Data analysis

CLI + Codex · 4 targets

typescriptnotebook
by lfnovoDetailsQuick view
10

Dokku

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDCODING

A docker-powered PaaS that helps you build and manage the lifecycle of applications

$ npx skills add dokku/dokku
31.9K stars75 quality86 trustReviewed with permission notes2mo 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

CLI + Codex · 4 targets

shellkubernetes
by dokkuDetailsQuick view
11

Blinko

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDRESEARCH

An open-source, self-hosted personal AI note tool prioritizing privacy, built using TypeScript .

$ npx skills add blinkospace/blinko
10.6K stars71 quality88 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 Document processing

OpenAI Agents + CLI · 4 targets

typescriptmarkdown
by blinkospaceDetailsQuick view
12

Crawl4AI

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDRESEARCH

Web crawling built for AI

$ npx skills add unclecode/crawl4ai
4 agent calls100% success73.1K stars80 quality90 trustReviewedClaude Code + OpenAI Agents18d since pushSafe to try31.0K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents

Claude Code + OpenAI Agents · 4 targets

claudegpt-4langchaincrewaiopenclaw
by unclecodeDetailsQuick view
13

Wallos

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDFINANCE

Wallos: Open-source, self-hostable personal subscription tracker. Visualize your recurring expenses, manage your budget, and save money.

$ npx skills add ellite/Wallos
8.1K stars69 quality88 trustReviewed1mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Finance and quant

CLI + Codex · 4 targets

phpfinance
by elliteDetailsQuick view
14

Librephotos

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDDESIGN

A self-hosted open source photo management service.

$ npx skills add LibrePhotos/librephotos
8.0K stars69 quality87 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

pythonmachine-learning
by LibrePhotosDetailsQuick view
15

Finance Skills

VERIFIEDEXCELLENT · 97TRUST · 86SAFE · REVIEWEDCODING

A collection of skills for AI financial analysis and trading.

$ npx skills add himself65/finance-skills
2.9K stars66 quality86 trustReviewedClaude Code2mo 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 GitHub automation

Claude Code + CLI · 4 targets

javascripttrading
by himself65DetailsQuick view
16

Wakapi

VERIFIEDEXCELLENT · 99TRUST · 84SAFE · REVIEWEDCODING

📊 A minimalist, self-hosted WakaTime-compatible backend for coding statistics

$ npx skills add muety/wakapi
4.3K stars67 quality84 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 Coding agents

CLI + Codex · 4 targets

goproductivity
by muetyDetailsQuick 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