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.

  • Powerplatform Build Tools292 stars

    Power Platform Build Tools automate common build and deployment tasks related to Power Platform. This include…

    Trust 78Quality 79devops
  • ComputeLibrary3.2K stars

    The Compute Library is a set of computer vision and machine learning functions optimised for both Arm CPUs an…

    Trust 86Quality 95robotics-iot
  • ShowUI1.9K stars

    [CVPR 2025] Open-source, End-to-end, Vision-Language-Action model for GUI Agent & Computer Use.

    Trust 86Quality 92automation

Codex, Claude Code, Cursor

Coding agent skills

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

  • Drawio Skill6.0K stars

    Generate draw.io diagrams from natural language — 6 presets, vision self-check + up to 5-round refinement, co…

    Trust 89Quality 100agent-skills
  • Revup390 stars

    Upload once to create multiple, relative PRs. Productivity-focused git tools with patch revision tracking, re…

    Trust 78Quality 74development
  • Video Search And Summarization1.6K stars

    The NVIDIA VSS Blueprint is a suite of reference architectures for building GPU-accelerated vision agents and…

    Trust 84Quality 89data

Documents and knowledge

Research and RAG skills

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

  • Sparrow5.2K stars

    Structured data extraction and instruction calling with ML, LLM and Vision LLM

    Trust 88Quality 100data
  • Thepipe1.5K stars

    Get clean data from tricky documents, powered by vision-language models ⚡

    Trust 83Quality 87document-processing
  • VLM2Vec655 stars

    This repo contains the code for "VLM2Vec: Training Vision-Language Models for Massive Multimodal Embedding Ta…

    Trust 80Quality 76rag-knowledge

Crawlers and extraction

Web scraping skills

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

  • Paperless Gpt2.4K stars

    Use LLMs and LLM Vision (OCR) to handle paperless-ngx - Document Digitalization powered by AI

    Trust 86Quality 96document-processing
  • Vision Agent5.3K stars

    This tool has been deprecated. Use Agentic Document Extraction instead.

    Trust 85Quality 93document-processing
  • Popsift497 stars

    PopSift is an implementation of the SIFT algorithm in CUDA.

    Trust 77Quality 75robotics-iot

Prompts, B-roll, explainers

Video creation skills

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

  • Champ4.3K stars

    [ECCV 2024] Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

    Trust 80Quality 71media-automation
  • InfinityStar767 stars

    [NeurIPS 2025 Oral]Infinity⭐️: Unified Spacetime AutoRegressive Modeling for Visual Generation

    Trust 79Quality 74media-automation
  • Vision Agents7.9K stars

    Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses St…

    Trust 88Quality 100agent-frameworks

Images, video, UI

Design and creative skills

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

  • Mlx Openai Server345 stars

    A high-performance API server that provides OpenAI-compatible endpoints for MLX models. Developed using Pytho…

    Trust 77Quality 80media-automation
  • VAR8.7K stars

    [NeurIPS 2024 Best Paper Award][GPT beats diffusion🔥] [scaling laws in visual generation📈] Official impl. o…

    Trust 86Quality 93media-automation
  • Geti1.2K stars

    Build computer vision models in a fraction of the time and with less data.

    Trust 86Quality 93robotics-iot

Analysis and pipelines

Data and analytics skills

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

  • WebPlotDigitizer3.1K stars

    Computer vision assisted tool to extract numerical data from plot images.

    Trust 86Quality 97robotics-iot
  • CVprojects2.6K stars

    computer vision projects | 计算机视觉相关好玩的AI项目（Python、C++、embedded system）

    Trust 79Quality 81robotics-iot
  • Administrative Divisions Of China21K stars

    中华人民共和国行政区划：省级（省份）、 地级（城市）、 县级（区县）、 乡级（乡镇街道）、 村级（村委会居委会） ，中国省市区镇村二级三级四级五级联动地址数据。

    Trust 86Quality 96data-analysis

Contracts and policy

Legal and compliance skills

Contract review, policy analysis, compliance research, audit support, and legal document workflows.

  • Row Bot1.3K stars

    Row-Bot - Personal AI Sovereignty. A local-first AI assistant with integrated tools, a personal knowledge gra…

    Trust 82Quality 99legal-compliance
  • Playbook1.9K stars

    A lightweight, stable, and performance-focused customized version of Windows that enhances privacy and compat…

    Trust 84Quality 95legal-compliance
  • Grapheneos.Org672 stars

    Servers for our website, HTTP/HTTPS connectivity checks, HTTPS network time, NTP (for Qualcomm XTRA), Broadco…

    Trust 79Quality 83legal-compliance

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

221

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

221 quality211 maintained

Research

Research and knowledge work

80

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

80 quality79 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

81

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

81 quality70 maintained

Data

Data, BI, and analytics

37

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

37 quality35 maintained

Legal

Legal, policy, and compliance

13

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

13 quality13 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

3

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

3 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 453 ranked candidates matching "llama3-2-vision"

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

1

AliceVision

VERIFIEDEXCELLENT · 96TRUST · 84SAFE · REVIEWEDDESIGN

3D Computer Vision Framework

$ npx skills add alicevision/AliceVision
3.5K stars66 quality84 trustReviewed with permission notes15d 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

c++computer-vision
by alicevisionDetailsQuick view
2

Raster Vision

VERIFIEDEXCELLENT · 96TRUST · 88SAFE · REVIEWEDRESEARCH

An open source library and framework for deep learning on satellite and aerial imagery.

$ npx skills add azavea/raster-vision
2.2K stars65 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 Research agents

CLI + Codex · 4 targets

pythoncomputer-vision
by azaveaDetailsQuick view
3

Computer Vision In Action

VERIFIEDPROMISING · 64TRUST · 76SAFE · EXPERIMENTALCODING

A computer vision closed-loop learning platform where code can be run interactively online. 学习闭环《计算机视觉实战演练：算法与应用》中文电子书、源码、读者交流社区（持续更新中 ...） 📘 在线电子书 https://charmve.gith…

$ npx skills add Charmve/computer-vision-in-action
2.9K stars51 quality76 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: License is unclear
Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents

CLI + Codex · 4 targets

jupyter-notebookcomputer-vision
by CharmveDetailsQuick view
4

Cleanvision

VERIFIEDSTRONG · 82TRUST · 84SAFE · REVIEWEDCODING

Automatically find issues in image datasets and practice data-centric computer vision.

$ npx skills add cleanlab/cleanvision
1.2K stars56 quality84 trustReviewed7mo 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: 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

pythoncomputer-vision
by cleanlabDetailsQuick view
5

Computer Vision Course

STRONG · 78TRUST · 80SAFE · REVIEWEDCODING

This repo is the homebase of a community driven course on Computer Vision with Neural Networks. Feel free to join us on the Hugging Face discord: hf.co/join/discord

$ npx skills add huggingface/computer-vision-course
850 stars54 quality80 trustReviewed with permission notes2mo 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation

CLI + Codex · 4 targets

jupyter-notebookcomputer-vision
by huggingfaceDetailsQuick view
6

Autoregressive Models In Vision Survey

PROMISING · 69TRUST · 75SAFE · REVIEWEDDESIGN

[TMLR 2025🔥] A survey for the autoregressive models in vision.

$ npx skills add ChaofanTao/Autoregressive-Models-in-Vision-Survey
796 stars51 quality75 trustReviewed with permission notes3mo since pushNeeds review
QualityUseful candidate, but compare it with alternatives before adopting.
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

computer-vision
by ChaofanTaoDetailsQuick view
7

Supervision

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDDESIGN

We write your reusable computer vision tools. 💜

$ npx skills add roboflow/supervision
44.4K stars76 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 Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by roboflowDetailsQuick view
8

Vision

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

Datasets, Transforms and Models specific to Computer Vision

$ npx skills add pytorch/vision
17.7K stars73 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

pythonmachine-learning
by pytorchDetailsQuick view
9

Administrative Divisions Of China

VERIFIEDEXCELLENT · 96TRUST · 86SAFE · REVIEWEDDATA

中华人民共和国行政区划：省级（省份）、 地级（城市）、 县级（区县）、 乡级（乡镇街道）、 村级（村委会居委会） ，中国省市区镇村二级三级四级五级联动地址数据。

$ npx skills add modood/Administrative-divisions-of-China
20.8K stars66 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 Data analysis

CLI + Codex · 4 targets

javascriptcsv
by modoodDetailsQuick view
10

Machinevision Toolbox Python

STRONG · 71TRUST · 76SAFE · REVIEWEDRESEARCH

Machine vision toolbox for Python

$ npx skills add petercorke/machinevision-toolbox-python
201 stars50 quality76 trustReviewed with permission notes1mo 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 RAG and knowledge

CLI + Codex · 4 targets

pythoncomputer-vision
by petercorkeDetailsQuick view
11

Vision Agents

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

Open Vision Agents by Stream. Build voice and vision agents quickly with any model or video provider. Uses Stream's edge network for ultra-low latency.

$ npx skills add GetStream/Vision-Agents
7.9K stars69 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

pythonai-agents
by GetStreamDetailsQuick view
12

MIVisionX

STRONG · 77TRUST · 78SAFE · REVIEWEDRESEARCH

MIVisionX toolkit is a set of comprehensive computer vision and machine intelligence libraries, utilities, and applications bundled into a single toolkit. AMD MIVisionX…

$ npx skills add ROCm/MIVisionX
213 stars50 quality78 trustReviewed1mo 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 Research agents

CLI + Codex · 4 targets

c++computer-vision
by ROCmDetailsQuick view
13

Computervision Recipes

VERIFIEDSTRONG · 74TRUST · 79SAFE · REVIEWEDDESIGN

Best Practices, code samples, and documentation for Computer Vision.

$ npx skills add microsoft/computervision-recipes
9.9K stars55 quality79 trustReviewed with permission notes2y since pushNeeds review
QualitySolid option that is likely worth shortlisting for production workflows.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

jupyter-notebookmachine-learning
by microsoftDetailsQuick view
14

Daily Paper Computer Vision

VERIFIEDPROMISING · 68TRUST · 76SAFE · EXPERIMENTALDESIGN

记录每天整理的计算机视觉/深度学习/机器学习相关方向的论文

$ npx skills add amusi/daily-paper-computer-vision
6.8K stars54 quality76 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: License is unclear
Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Multimodal media

CLI + Codex · 4 targets

machine-learning
by amusiDetailsQuick view
15

BEVFormer

VERIFIEDSTRONG · 71TRUST · 82SAFE · REVIEWEDCODING

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segme…

$ npx skills add fundamentalvision/BEVFormer
4.5K stars52 quality82 trustReviewed with permission notes2y since pushNeeds review
QualitySolid option that is likely worth shortlisting for production workflows.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

pythoncomputer-vision
by fundamentalvisionDetailsQuick view
16

Photo2cartoon

VERIFIEDSTRONG · 70TRUST · 78SAFE · REVIEWEDCODING

人像卡通化探索项目 (photo-to-cartoon translation project)

$ npx skills add minivision-ai/photo2cartoon
4.0K stars52 quality78 trustReviewed with permission notes4y since pushNeeds review
QualitySolid option that is likely worth shortlisting for production workflows.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

pythoncomputer-vision
by minivision-aiDetailsQuick 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