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.

  • Frontend Design166K stars

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

    Trust 88Quality 100design-creative
  • Dokploy36K stars

    Open Source Alternative to Vercel, Netlify and Heroku.

    Trust 85Quality 100devops
  • Open Dungeon191 stars

    Open Dungeon — the first easy-to-use, fully local AI roleplay app. Story and inline scene images generated 10…

    Trust 77Quality 71media-automation

Codex, Claude Code, Cursor

Coding agent skills

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

  • Code Review169K stars

    Review a diff separately for code standards and spec compliance.

    Trust 91Quality 100coding-agents
  • Agent Skills81K stars

    Production-grade engineering skills for AI coding agents.

    Trust 86Quality 100agent-skills
  • Implement176K stars

    Execute an approved engineering ticket with tests, review, and a branch commit.

    Trust 88Quality 100coding-agents

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
  • Pdfdeal287 stars

    A python wrapper for the Doc2X API and comes with native texts processing (to improve PDF recall in RAG). | D…

    Trust 74Quality 66document-processing
  • UForm1.2K stars

    Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜…

    Trust 84Quality 78rag-knowledge

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
  • iTextSharp.LGPLv2.Core is an unofficial port of the last LGPL version of the iTextSharp (V4.1.6) to .NET Core

    Trust 78Quality 75document-processing

Slides and decks

PPT and presentation skills

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

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

    Trust 91Quality 100design-creative
  • Portable Codex skill for auditable, rights-aware Chinese book-review short-video workflows.

    Trust 77Quality 69design-creative
  • Codex skill for fiction planning, chapter drafting, scene continuation, and revision.

    Trust 74Quality 66design-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
  • OpenClaw/Codex Skill: Auto video editing for talk/vlog videos — speech recognition, sentence splitting, subti…

    Trust 81Quality 83media
  • Matrix 3D741 stars

    Generate large-scale explorable 3D scenes with high-quality panorama videos from a single image or text promp…

    Trust 78Quality 62media-automation

Images, video, UI

Design and creative skills

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

  • PySceneDetect5.0K stars

    :movie_camera: Python and OpenCV-based scene cut/transition detection program & library.

    Trust 88Quality 99media-automation
  • Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images

    Trust 78Quality 71media-automation
  • Ru Dalle1.6K stars

    Generate images from texts. In Russian

    Trust 77Quality 67media-automation

Analysis and pipelines

Data and analytics skills

Data analysis, analytics, ETL, notebooks, databases, tables, charts, and reporting workflows.

  • 4DGaussians3.8K stars

    [CVPR 2024] 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering

    Trust 79Quality 70robotics-iot
  • Shifterator289 stars

    Interpretable data visualizations for understanding how texts differ at the word level

    Trust 77Quality 70data-analysis
  • ServiceStack5.5K stars

    Thoughtfully architected, obscenely fast, thoroughly enjoyable web services for all

    Trust 85Quality 95data-analysis

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

213

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

188 quality183 maintained

Research

Research and knowledge work

83

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

75 quality69 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

13

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

13 quality13 maintained

Marketing

Marketing and growth automation

10

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

10 quality10 maintained

Design

Design and creative production

64

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

60 quality58 maintained

Data

Data, BI, and analytics

35

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

35 quality34 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

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 421 ranked candidates matching "scene-texts"

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

1

PySceneDetect

VERIFIEDEXCELLENT · 99TRUST · 88SAFE · REVIEWEDDESIGN

:movie_camera: Python and OpenCV-based scene cut/transition detection program & library.

$ npx skills add Breakthrough/PySceneDetect
5.0K stars68 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 Multimodal media

CLI + Codex · 4 targets

pythonvideo
by BreakthroughDetailsQuick view
2

ITextSharp.LGPLv2.Core

STRONG · 75TRUST · 78SAFE · REVIEWEDCODING

iTextSharp.LGPLv2.Core is an unofficial port of the last LGPL version of the iTextSharp (V4.1.6) to .NET Core

$ npx skills add VahidN/iTextSharp.LGPLv2.Core
676 stars54 quality78 trustReviewed with permission notes18d 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: License is unclear
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation

CLI + Codex · 4 targets

c#pdf
by VahidNDetailsQuick view
3

Midscene

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

AI-powered, vision-driven UI automation for every platform.

$ npx skills add web-infra-dev/midscene
14.2K stars72 quality88 trustReviewedOpenAI Agents + Browser agents9d 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

OpenAI Agents + Browser agents · 4 targets

typescriptcomputer-use
by web-infra-devDetailsQuick view
4

Textshot

VERIFIEDPROMISING · 67TRUST · 80SAFE · EXPERIMENTALRESEARCH

Python tool for grabbing text via screenshot

$ npx skills add ianzhao/textshot
1.8K stars49 quality80 trustExperimental2y 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 Document processing

CLI + Codex · 4 targets

pythonocr
by ianzhaoDetailsQuick view
5

PDFLayoutTextStripper

VERIFIEDPROMISING · 66TRUST · 79SAFE · EXPERIMENTALRESEARCH

Converts a pdf file into a text file while keeping the layout of the original pdf. Useful to extract the content from a table in a pdf file for instance. This is a subcl…

$ npx skills add JonathanLink/PDFLayoutTextStripper
1.6K stars49 quality79 trustExperimental3y 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 Document processing

CLI + Codex · 4 targets

javapdf
by JonathanLinkDetailsQuick view
6

XScene UEPlugin

VERIFIEDPROMISING · 69TRUST · 81SAFE · REVIEWEDCODING

A Unreal Engine 5 (UE5) based plugin aiming to provide real-time visulization, management, editing, and scalable hybrid rendering of Guassian Splatting model.

$ npx skills add xverse-engine/XScene-UEPlugin
1.1K stars52 quality81 trustReviewed with permission notes1y 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

c++computer-vision
by xverse-engineDetailsQuick view
7

TextSnatcher

VERIFIEDPROMISING · 66TRUST · 79SAFE · EXPERIMENTALRESEARCH

How to Copy Text from Images ? Answer is TextSnatcher !. Perform OCR operations in seconds on Linux Desktop.

$ npx skills add RajSolai/TextSnatcher
1.4K stars49 quality79 trustExperimental2y 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 Document processing

CLI + Codex · 4 targets

valaocr
by RajSolaiDetailsQuick view
8

MonoScene

STRONG · 70TRUST · 79SAFE · REVIEWEDDESIGN

[CVPR 2022] "MonoScene: Monocular 3D Semantic Scene Completion": 3D Semantic Occupancy Prediction from a single image

$ npx skills add astra-vision/MonoScene
815 stars47 quality79 trustReviewed with permission notes4mo 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 Multimodal media

CLI + Codex · 4 targets

pythoncomputer-vision
by astra-visionDetailsQuick view
9

Scene Fab

STRONG · 73TRUST · 77SAFE · REVIEWEDDESIGN

scene-fab - AI 影视解说创作工具 | 智能拆条 · AI 解说生成 · 一键配音合成

$ npx skills add Agions/scene-fab
306 stars51 quality77 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 Multimodal media

CLI + Codex · 4 targets

pythonvoice
by AgionsDetailsQuick view
10

Ian Xiaohei Scenes

STRONG · 71TRUST · 78SAFE · REVIEWEDDESIGN

Xiaohei 2.0 Codex Skill for Chinese real-object article illustrations and long-scroll story images

$ npx skills add helloianneo/ian-xiaohei-scenes
347 stars48 quality78 trustReviewed with permission notesClaude Code + OpenAI Agents2mo 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 Multimodal media

Claude Code + OpenAI Agents · 4 targets

image-generation
by helloianneoDetailsQuick view
11

Plan2scene

NEEDS REVIEW · 48TRUST · 71SAFE · EXPERIMENTALCODING

Official implementation of the paper Plan2Scene.

$ npx skills add 3dlg-hcvc/plan2scene
607 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 GitHub automation

CLI + Codex · 4 targets

pythoncomputer-vision
by 3dlg-hcvcDetailsQuick view
12

Wayve Scenes

NEEDS REVIEW · 43TRUST · 70SAFE · EXPERIMENTALCODING

Codebase for the WayveScenes101 Dataset

$ npx skills add wayveai/wayve_scenes
194 stars35 quality70 trustExperimental2y 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 Coding agents

CLI + Codex · 4 targets

pythoncomputer-vision
by wayveaiDetailsQuick view
13

Scene Generation

NEEDS REVIEW · 43TRUST · 70SAFE · EXPERIMENTALDESIGN

A PyTorch implementation of the paper: Specifying Object Attributes and Relations in Interactive Scene Generation

$ npx skills add ashual/scene_generation
193 stars35 quality70 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 Design and creative

CLI + Codex · 4 targets

pythonimage-generation
by ashualDetailsQuick view
14

Scene Text Recognition

NEEDS REVIEW · 42TRUST · 69SAFE · EXPERIMENTALCODING

Scene text detection and recognition based on Extremal Region(ER)

$ npx skills add HsiehYiChia/Scene-text-recognition
167 stars34 quality69 trustExperimental6y 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 Coding agents

CLI + Codex · 4 targets

c++computer-vision
by HsiehYiChiaDetailsQuick view
15

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
16

GdUnit4

VERIFIEDEXCELLENT · 93TRUST · 87SAFE · REVIEWEDCODING

Embedded unit testing framework for Godot 4 supporting GDScript and C#. Features test-driven development, embedded test inspector, extensive assertions, mocking, scene t…

$ npx skills add godot-gdunit-labs/gdUnit4
1.1K stars63 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 Testing and QA

CLI + Codex · 4 targets

gdscripttesting
by godot-gdunit-labsDetailsQuick 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