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.

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

    Trust 91Quality 100design-creative
  • Taste Skill65K stars

    Taste-Skill - gives your AI good taste. stops the AI from generating boring, generic slop

    Trust 91Quality 100development
  • Automate a real browser from the terminal for navigation, form filling, snapshots, screenshots, extraction, a…

    Trust 83Quality 100browser-automation

Codex, Claude Code, Cursor

Coding agent skills

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

  • Orca5.0K stars

    Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription.…

    Trust 84Quality 99coding-agents
  • Multi-agent orchestration platform for Gemini CLI, Claude Code, Codex, and Qwen Code — 39 specialists, parall…

    Trust 75Quality 75development
  • Evo1.2K stars

    turns your codebase into an autoresearch loop — discovers what to measure, instruments the benchmark, then ru…

    Trust 87Quality 93agent-skills

Documents and knowledge

Research and RAG skills

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

  • Chronicler641 stars

    Chronicler is a free, offline worldbuilding tool and local wiki for writers, game masters, and tabletop RPG c…

    Trust 77Quality 77document-processing
  • MarkdownEditing3.3K stars

    Powerful Markdown package for Sublime Text with better syntax understanding and good color schemes.

    Trust 88Quality 98document-processing
  • Markdown-first CMS for bloggers, minimalists and startups. Open Source alternative to Medium, Mailchimp and S…

    Trust 78Quality 74document-processing

Markets and quant

Finance and trading skills

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

  • Sol Trade Sdk324 stars

    Rust SDK for low-latency Solana DEX trading bots with PumpFun, PumpSwap, Bonk, Raydium, Meteora, Jito, and SW…

    Trust 80Quality 76finance
  • Lago10K stars

    Open Source Metering and Usage Based Billing API ⭐️ Consumption tracking, Subscription management, Pricing it…

    Trust 89Quality 100finance
  • Wallos8.1K stars

    Wallos: Open-source, self-hostable personal subscription tracker. Visualize your recurring expenses, manage y…

    Trust 88Quality 100finance

Crawlers and extraction

Web scraping skills

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

  • ScopeSentry1.5K stars

    ScopeSentry-Cyberspace mapping, subdomain enumeration, port scanning, sensitive information discovery, vulner…

    Trust 84Quality 89web-automation
  • Mouseover Translate Any Language At Once - Chrome Extension: PDF Translator, EBOOK, EPUB, OCR, TTS, NETFLIX,…

    Trust 85Quality 99document-processing
  • Translumo5.4K stars

    Advanced real-time screen translator for games, hardcoded subtitles in videos, static text and etc.

    Trust 89Quality 100document-processing

Slides and decks

PPT and presentation skills

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

  • Slides_maker355 stars

    Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native ch…

    Trust 80Quality 77presentation
  • ClaudeSkills626 stars

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

    Trust 87Quality 95presentation
  • Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering ph…

    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.

  • Seedance 2.0 prompt skill,使用该Skill生成Seedance 2.0 视频提示词

    Trust 82Quality 85media
  • Generate real-timestamp subtitle artifacts from final narration audio or merged video with a caption quality…

    Trust 74Quality 81Video Creation
  • Vox Director486 stars

    Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Clo…

    Trust 85Quality 95utility

Images, video, UI

Design and creative skills

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

  • UNO1.4K stars

    [ICCV 2025] 🔥🔥 UNO: A Universal Customization Method for Both Single and Multi-Subject Conditioning

    Trust 84Quality 79media-automation
  • Generate a controlled local narration workflow with auditions, version tracking, and subtitle-ready final aud…

    Trust 72Quality 80Video Creation
  • 用 Claude Code Skills 做的视频剪辑 Agent

    Trust 87Quality 99utility

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

227

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

227 quality225 maintained

Research

Research and knowledge work

78

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

78 quality78 maintained

Presentation

Presentation and deck workflows

3

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

3 quality3 maintained

Finance

Finance and quant workflows

17

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

17 quality17 maintained

Marketing

Marketing and growth automation

16

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

16 quality16 maintained

Design

Design and creative production

60

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

60 quality57 maintained

Data

Data, BI, and analytics

37

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

37 quality37 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

7

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

7 quality7 maintained

World Cup

Football and World Cup analytics

3

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

3 quality3 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 447 ranked candidates matching "sub-agents"

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

1

Claude Code Sub Agents

VERIFIEDSTRONG · 79TRUST · 84SAFE · REVIEWEDCODING

Collection of specialized AI subagents for Claude Code for personal use (full-stack development).

$ npx skills add lst97/claude-code-sub-agents
1.6K stars53 quality84 trustReviewed with permission notesClaude Code12mo since pushNeeds review
QualitySolid option that is likely worth shortlisting for production workflows.
TrustGood trust signals with a few areas worth checking before rollout.Review: Quality score needs review
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation

Claude Code + CLI · 4 targets

ai-agents
by lst97DetailsQuick view
2

Awesome Claude Code Subagents

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDCODING

A collection of 100+ specialized Claude Code subagents covering a wide range of development use cases

$ npx skills add VoltAgent/awesome-claude-code-subagents
22.4K stars74 quality87 trustReviewed with permission notesClaude Code1mo 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 + CLI · 4 targets

shellai-agents
by VoltAgentDetailsQuick view
3

Awesome Codex Subagents

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDCODING

A collection of 130+ specialized Codex subagents covering a wide range of development use cases.

$ npx skills add VoltAgent/awesome-codex-subagents
5.4K stars68 quality89 trustReviewedClaude Code + OpenAI Agents1mo 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 + OpenAI Agents · 4 targets

ai-agents
by VoltAgentDetailsQuick view
4

Orkas

EXCELLENT · 86TRUST · 80SAFE · REVIEWEDCODING

Open-source multi-agent AI desktop client — build and command your AI agent team through conversation. A commander LLM dispatches sub-agents in parallel or in series; ag…

$ npx skills add Orkas-AI/Orkas
806 stars54 quality80 trustReviewed with permission notesClaude Code + OpenAI Agents6d 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: Quality score needs review
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Local desktop

Claude Code + OpenAI Agents · 4 targets

typescriptai-agents
by Orkas-AIDetailsQuick view
5

AI Agents For Beginners

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

12 Lessons to Get Started Building AI Agents

$ npx skills add microsoft/ai-agents-for-beginners
67.3K stars77 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

jupyter-notebookai-agents
by microsoftDetailsQuick view
6

500 AI Agents Projects

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDCODING

The 500 AI Agents Projects is a curated collection of AI agent use cases across various industries. It showcases practical applications and provides links to open-source…

$ npx skills add ashishpatel26/500-AI-Agents-Projects
33.3K stars75 quality90 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

pythonai-agents
by ashishpatel26DetailsQuick view
7

AgentScope

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDCODING

Build agents that are visible, understandable, and trusted

$ npx skills add agentscope-ai/agentscope
28.0K stars75 quality86 trustReviewed with permission notes18d 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/…Review: License is unclear
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

CLI + Codex · 4 targets

agentscopepythonllm
by agentscope-aiDetailsQuick view
8

Pentest AI Agents

VERIFIEDEXCELLENT · 93TRUST · 84SAFE · REVIEWEDCODING

Turn Claude Code into your offensive security research assistant. Specialized AI subagents for authorized penetration testing plan engagements, analyze recon, research e…

$ npx skills add 0xSteph/pentest-ai-agents
2.1K stars62 quality84 trustReviewed with permission notesClaude Code1mo 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 Testing and QA

Claude Code + CLI · 4 targets

shellai-agents
by 0xStephDetailsQuick view
9

Video Subtitle Extractor

VERIFIEDEXCELLENT · 99TRUST · 86SAFE · REVIEWEDRESEARCH

视频硬字幕提取,生成srt文件。无需申请第三方API,本地实现文本识别。基于深度学习的视频字幕提取框架,包含字幕区域检测、字幕内容提取。A GUI tool for extracting hard-coded subtitle (hardsub) from videos and generating srt files.

$ npx skills add YaoFANGUK/video-subtitle-extractor
9.0K stars66 quality86 trustReviewed4mo 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

pythonocr
by YaoFANGUKDetailsQuick view
10

Claude Seo

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

Universal SEO skill for Claude Code. 25 sub-skills + 18 sub-agents covering technical SEO, E-E-A-T, schema, GEO/AEO, backlinks, local SEO, maps intelligence, semantic cl…

$ npx skills add AgriciDaniel/claude-seo
8.9K stars69 quality88 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 Coding agents

Claude Code + CLI · 4 targets

pythonclaude-code
by AgriciDanielDetailsQuick view
11

Raptor

VERIFIEDEXCELLENT · 98TRUST · 85SAFE · REVIEWEDCODING

Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents, and skills, and orchestrating s…

$ npx skills add gadievron/raptor
3.0K stars66 quality85 trustReviewedClaude Code2mo since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.
TrustGood trust signals with a few areas worth checking before rollout.Review: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + CLI · 4 targets

pythonclaude-code
by gadievronDetailsQuick view
12

Dotnet Skills

VERIFIEDEXCELLENT · 89TRUST · 81SAFE · REVIEWEDCODING

Claude Code skills and sub-agents for .NET Developers

$ npx skills add Aaronontheweb/dotnet-skills
1.0K stars60 quality81 trustReviewed with permission notesClaude Code4mo 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 Coding agents

Claude Code + CLI · 4 targets

shellclaude-code
by AarononthewebDetailsQuick view
13

Openagentskill

VERIFIEDEXCELLENT · 90TRUST · 86SAFE · REVIEWEDCODING

The skill layer for AI agents: npm for AI Agent Skills.

$ npx skills add Leon-Drq/openagentskill
220 stars60 quality86 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/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + CLI · 4 targets

typescript
by Leon-DrqDetailsQuick view
14

RNSkill Audio to Subtitles

STRONG · 81TRUST · 74SAFE · REVIEWEDDESIGN

Generate real-timestamp subtitle artifacts from final narration audio or merged video with a caption quality gate.

$ npx -y skills add Pluviobyte/rnskill --skill ra-audio-to-subtitles
1.1K stars54 quality74 trustReviewed with permission notesClaude Code + OpenAI Agents8d since pushNeeds review
QualitySolid option that is likely worth shortlisting for production workflows.Check: External ASR may require API credentials and may process uploaded media.
TrustGood trust signals with a few areas worth checking before rollout.Review: External ASR may require API credentials and may process uploaded media.
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Video creation

Claude Code + OpenAI Agents · 4 targets

codexclaude-codeskills.sh
by PluviobyteDetailsQuick view
15

Submitty

STRONG · 77TRUST · 79SAFE · REVIEWEDEDUCATION

Homework Submission, Automated Grading, and TA grading system.

$ npx skills add Submitty/Submitty
774 stars54 quality79 trustReviewed2mo 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 gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Education and tutoring

CLI + Codex · 4 targets

phpeducation
by SubmittyDetailsQuick view
16

Subtrackr

STRONG · 75TRUST · 76SAFE · REVIEWEDFINANCE

Self-hosted Subscription Tracker

$ npx skills add bscott/subtrackr
446 stars52 quality76 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 Finance and quant

CLI + Codex · 4 targets

gofinance
by bscottDetailsQuick 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