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.

  • Translate Figma designs into production-ready UI code with close visual fidelity and component-level detail.

    Trust 88Quality 100design-creative
  • Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful r…

    Trust 91Quality 100design-creative
  • This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the in…

    Trust 91Quality 100design-creative

Codex, Claude Code, Cursor

Coding agent skills

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

  • Cc Sdd3.6K stars

    Turn approved specs into long-running autonomous implementation. A minimal, adaptable SDD harness with Agent…

    Trust 84Quality 95agent-skills
  • Code Review169K stars

    Review a diff separately for code standards and spec compliance.

    Trust 91Quality 100coding-agents
  • Oh My Agent1.2K stars

    Portable, vendor-agnostic agent harness for project-specific skills, workflows, and agent teams aligned with…

    Trust 89Quality 96agent-frameworks

Documents and knowledge

Research and RAG skills

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

  • Pdf Inspector1.5K stars

    Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs t…

    Trust 83Quality 89document-processing
  • Searx14K stars

    Privacy-respecting metasearch engine

    Trust 88Quality 100rag-knowledge
  • A self-hosted, ad-free, privacy-respecting metasearch engine

    Trust 87Quality 100rag-knowledge

Markets and quant

Finance and trading skills

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

  • Lifeforge1.6K stars

    A self-hosted solution to streamline and organize all aspects of your life.

    Trust 82Quality 89productivity-automation
  • Bolts2.2K stars

    BOLT: Basis of Lightning Technology (Lightning Network Specifications)

    Trust 81Quality 91web3-analytics
  • A set of ready to use Agent Skills for research, science, engineering, analysis, finance and writing.

    Trust 87Quality 100utility

Crawlers and extraction

Web scraping skills

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

  • Crawl4AI73K stars

    Web crawling built for AI

    Trust 90Quality 100web-automation
  • Automates PWA asset generation and image declaration. Automatically generates icon and splash screen images,…

    Trust 85Quality 100browser-automation
  • Wpt6.0K stars

    Test suites for Web platform specs — including WHATWG, W3C, and others

    Trust 84Quality 98testing-qa

Slides and decks

PPT and presentation skills

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

  • Rundeck6.1K stars

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

    Trust 89Quality 100automation
  • 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
  • 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
  • 用 Claude Code Skills 做的视频剪辑 Agent

    Trust 87Quality 99utility
  • Cosmos-Predict2.5, the latest version of the Cosmos World Foundation Models (WFMs) family, specialized for si…

    Trust 87Quality 93media-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
  • Skills194 stars

    Agent Skills for theming AI desktop apps: reference image → reversible Codex/WorkBuddy skin → verify, repair,…

    Trust 86Quality 89design-creative
  • Community Group2.0K stars

    This is the official DTCG repository for the design tokens site and specification.

    Trust 83Quality 90design-creative

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

233

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

233 quality232 maintained

Research

Research and knowledge work

77

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

77 quality77 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

15

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

15 quality15 maintained

Marketing

Marketing and growth automation

11

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

11 quality11 maintained

Design

Design and creative production

58

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

58 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

14

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

14 quality14 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 437 ranked candidates matching "spec"

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

1

Inspec

VERIFIEDEXCELLENT · 92TRUST · 82SAFE · REVIEWEDCODING

InSpec: Auditing and Testing Framework

$ npx skills add inspec/inspec
3.1K stars66 quality82 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 Testing and QA

CLI + Codex · 4 targets

rubydevops
by inspecDetailsQuick view
2

Compose Spec

VERIFIEDEXCELLENT · 97TRUST · 85SAFE · REVIEWEDCODING

The Compose specification

$ npx skills add compose-spec/compose-spec
2.7K stars66 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 GitHub automation

CLI + Codex · 4 targets

dockerfilekubernetes
by compose-specDetailsQuick view
3

To Spec

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

Synthesize settled context into a behavior-focused spec for an engineering agent.

$ npx skills add mattpocock/skills --skill to-spec
164.7K stars79 quality88 trustReviewedClaude Code + OpenAI Agents23d since pushSafe to try
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: May create or update content in a configured issue tracker.
TrustStrong OpenAgentSkill Trust Score across adoption, recent maintenance, license clarity, documentation, dependency/…Review: May create or update content in a configured issue tracker.
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

claude-codecodexcursor
by Matt PocockDetailsQuick view
4

RNSkill Content Retrospective

EXCELLENT · 100TRUST · 75SAFE · REVIEWEDCODING

Turn creator performance data into a documented retrospective, grounded hypotheses, and reusable content learnings.

$ npx -y skills add Pluviobyte/rnskill --skill ra-复盘
797 stars74 quality75 trustReviewed with permission notesClaude Code + OpenAI Agents7d since pushNeeds review1.0K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: The workflow can touch private platform metrics and workspace files; review the…
TrustGood trust signals with a few areas worth checking before rollout.Review: The workflow can touch private platform metrics and workspace files; review the…
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

codexclaude-codeskills.sh
by PluviobyteDetailsQuick view
5

Machine Learning Specialization Coursera

VERIFIEDEXCELLENT · 90TRUST · 86SAFE · REVIEWEDDESIGN

Contains Solutions and Notes for the Machine Learning Specialization By Stanford University and Deeplearning.ai - Coursera (2022) by Prof. Andrew NG

$ npx skills add greyhatguy007/Machine-Learning-Specialization-Coursera
7.5K stars62 quality86 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 Multimodal media

CLI + Codex · 4 targets

jupyter-notebookmachine-learning
by greyhatguy007DetailsQuick view
6

Perspective

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDDATA

A data visualization and analytics component, especially well-suited for large and/or streaming datasets.

$ npx skills add perspective-dev/perspective
11.0K stars71 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 Data analysis

CLI + Codex · 4 targets

c++data-visualization
by perspective-devDetailsQuick view
7

Pdf Inspector

VERIFIEDEXCELLENT · 89TRUST · 83SAFE · REVIEWEDRESEARCH

Fast Rust library for PDF inspection, classification, and text extraction. Intelligently detects scanned vs text-based PDFs to enable smart routing decisions.

$ npx skills add firecrawl/pdf-inspector
1.5K stars64 quality83 trustReviewed1mo 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 Document processing

CLI + Codex · 4 targets

rustpdf
by firecrawlDetailsQuick view
8

Spec Kitty

VERIFIEDEXCELLENT · 94TRUST · 87SAFE · REVIEWEDCODING

Spec-Driven Development for serious software developers. Spec Coding with with Claude, Cursor, Gemini, Codex. Kanban dashboard, git worktrees, auto-merge and more.

$ npx skills add Priivacy-ai/spec-kitty
1.4K stars64 quality87 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 Coding agents

Claude Code + OpenAI Agents · 4 targets

pythonai-agents
by Priivacy-aiDetailsQuick view
9

Fuel Specs

VERIFIEDEXCELLENT · 92TRUST · 86SAFE · REVIEWEDCODING

📝 Specifications for the Fuel protocol and the FuelVM, a blazingly fast blockchain VM.

$ npx skills add FuelLabs/fuel-specs
1.8K stars61 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 GitHub automation

CLI + Codex · 4 targets

blockchain
by FuelLabsDetailsQuick view
10

Spectrum Css

VERIFIEDEXCELLENT · 93TRUST · 85SAFE · REVIEWEDDESIGN

The standard CSS implementation of the Spectrum design language.

$ npx skills add adobe/spectrum-css
1.3K stars63 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 Design and creative

CLI + Codex · 4 targets

cssdesign-systems
by adobeDetailsQuick view
11

Jspecify

VERIFIEDEXCELLENT · 93TRUST · 87SAFE · REVIEWEDCODING

An artifact of fully-specified annotations to power static-analysis checks, beginning with nullness analysis.

$ npx skills add jspecify/jspecify
1.1K stars63 quality87 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 Testing and QA

CLI + Codex · 4 targets

javastatic-analysis
by jspecifyDetailsQuick view
12

ApplicationInspector

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

A source code analyzer built for surfacing features of interest and other characteristics to answer the question 'What's in the code?' quickly using static analysis with…

$ npx skills add microsoft/ApplicationInspector
4.4K stars67 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 GitHub automation

CLI + Codex · 4 targets

c#static-analysis
by microsoftDetailsQuick view
13

SkillSpector

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDCODING

Security scanner for AI agent skills. Detect vulnerabilities, malicious patterns, and security risks.

$ npx skills add NVIDIA/SkillSpector
13.8K stars71 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/…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

pythonai-agents
by NVIDIADetailsQuick view
14

Getspecstory

VERIFIEDEXCELLENT · 93TRUST · 84SAFE · REVIEWEDCODING

Install our local first extensions for your favorite AI IDE or Terminal Agent. Process your histories into reusable skills with Lore. Sync your conversations to the clou…

$ npx skills add specstoryai/getspecstory
1.2K stars63 quality84 trustReviewed with permission notesClaude Code + OpenAI Agents2mo 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 + OpenAI Agents · 4 targets

goai-agents
by specstoryaiDetailsQuick view
15

Code Review

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · REVIEWEDCODING

Review a diff separately for code standards and spec compliance.

$ npx skills add mattpocock/skills --skill code-review
168.6K stars79 quality91 trustReviewedClaude 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/…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 + OpenAI Agents · 4 targets

claude-codecodexcursor
by Matt PocockDetailsQuick view
16

Zot

VERIFIEDEXCELLENT · 96TRUST · 86SAFE · REVIEWEDCODING

zot - A scale-out production-ready vendor-neutral OCI-native container image/artifact registry (purely based on OCI Distribution Specification)

$ npx skills add project-zot/zot
2.4K stars65 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

gokubernetes
by project-zotDetailsQuick 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