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.

  • React and Next.js performance guidance for writing, reviewing, and refactoring production UI code.

    Trust 94Quality 100coding-agents
  • Frontend Design163K stars

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

    Trust 91Quality 100design-creative
  • Review UI code for web interface guidelines, UX quality, accessibility, and interaction design best practices.

    Trust 91Quality 100design-creative

Codex, Claude Code, Cursor

Coding agent skills

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

  • Agent Skills62K stars

    Production-grade engineering skills and quality gates for AI coding agents.

    Trust 78Quality 100Coding Agents
  • Official Agent Skills for coding agents, research, workflow orchestration, docs, ops, and skill authoring.

    Trust 81Quality 100Agent Skills
  • Translate Figma designs into production-ready UI code with close visual fidelity and component-level detail.

    Trust 91Quality 100design-creative

Documents and knowledge

Research and RAG skills

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

  • MarkItDown80K stars

    Convert PDFs, Office documents, and web files into clean markdown for agents.

    Trust 81Quality 100Document Processing
  • LlamaIndex42K stars

    Data framework for building RAG and knowledge workflows around agent tasks.

    Trust 81Quality 100RAG
  • Vmprint549 stars

    This layout engine can solve the hardest layout problems imaginable. Its output is DTP grade and deterministi…

    Trust 78Quality 82document-processing

Markets and quant

Finance and trading skills

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

  • Bs P153 stars

    Ultra-low latency AVX-512 Polymarket market-making kernel (Logit Jump-Diffusion + Avellaneda-Stoikov in logit…

    Trust 77Quality 67finance

Crawlers and extraction

Web scraping skills

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

  • Firecrawl34K stars

    Turn websites into clean markdown or structured data for retrieval and agents.

    Trust 82Quality 100Web Scraping
  • Crawl4AI66K stars

    Open-source LLM-friendly web crawler and scraper for agent workflows.

    Trust 82Quality 100Web Scraping
  • Doctron587 stars

    html转pdf , html转图片 , Docker-powered html convert to pdf(html2pdf), html to image(html2image like jpeg,png),wh…

    Trust 71Quality 48document-processing

Slides and decks

PPT and presentation skills

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

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

    Trust 94Quality 100design-creative
  • Canvas Design163K stars

    Create original visual art, posters, PNG assets, and PDF documents through a clear design philosophy.

    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.

  • Write precise Seedance 2.0 prompts for multimodal video, camera movement, editing, music, and product storyte…

    Trust 84Quality 100design-creative
  • It is a simple python tool to extract key-frames from a video file using peak estimation from frame differenc…

    Trust 68Quality 43robotics-iot

Images, video, UI

Design and creative skills

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

  • a GUI application, which uses YOLOs (YOLOv8, YOLO11, YOLOv13) for Object Detection/Tracking, Human Pose Estim…

    Trust 75Quality 64robotics-iot
  • RGBD-3DGS-SLAM is a monocular SLAM system leveraging 3D Gaussian Splatting (3DGS) for accurate point cloud an…

    Trust 69Quality 47robotics-iot
  • YoloDotNet781 stars

    YoloDotNet - A C# .NET 8.0 project for Classification, Object Detection, OBB Detection, Segmentation and Pose…

    Trust 79Quality 70robotics-iot

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

76

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

47 quality33 maintained

Research

Research and knowledge work

19

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

16 quality16 maintained

Presentation

Presentation and deck workflows

0

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

0 quality0 maintained

Finance

Finance and quant workflows

4

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

4 quality4 maintained

Marketing

Marketing and growth automation

0

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

0 quality0 maintained

Design

Design and creative production

25

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

21 quality15 maintained

Data

Data, BI, and analytics

15

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

8 quality5 maintained

Legal

Legal, policy, and compliance

2

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

2 quality2 maintained

Education

Education and tutoring

1

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

1 quality0 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 144 ranked candidates matching "kernel-density-estimation"

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

1

KDEpy

STRONG · 73TRUST · 79SAFE · REVIEWEDDATA

Kernel Density Estimation in Python

$ npx skills add tommyod/KDEpy
647 stars50 quality79 trustReviewed with permission notes3mo 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 Data analysis

CLI + Codex · 4 targets

jupyter-notebookdata-analysis
by tommyodDetailsQuick view
2

Semantic Kernel

VERIFIEDEXCELLENT · 100TRUST · 85SAFE · REVIEWEDCODING

Compose enterprise LLM agents and plugins

$ npx skills add microsoft/semantic-kernel
28.1K 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 Coding agents

CLI + Codex · 4 targets

semantic-kernelc#python
by microsoftDetailsQuick view
3

Realtime Multi Person Pose Estimation

VERIFIEDPROMISING · 67TRUST · 75SAFE · EXPERIMENTALCODING

Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)

$ npx skills add ZheC/Realtime_Multi-Person_Pose_Estimation
5.1K stars53 quality75 trustExperimental6y 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 ZheCDetailsQuick view
4

Isaac Ros Pose Estimation

STRONG · 78TRUST · 78SAFE · REVIEWEDRESEARCH

Deep learned, NVIDIA-accelerated 3D object pose estimation

$ npx skills add NVIDIA-ISAAC-ROS/isaac_ros_pose_estimation
475 stars52 quality78 trustReviewed27d 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 RAG and knowledge

CLI + Codex · 4 targets

c++ros
by NVIDIA-ISAAC-ROSDetailsQuick view
5

Keras Realtime Multi Person Pose Estimation

NEEDS REVIEW · 44TRUST · 68SAFE · BLOCKEDDATA

Keras version of Realtime Multi-Person Pose Estimation project

$ npx skills add michalfaber/keras_Realtime_Multi-Person_Pose_Estimation
783 stars39 quality68 trustBlocked for auto-install7y since pushRisky
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: License is unclear
Safety gateThis skill should not be selected by an agent without explicit human security review.

Scenario Data analysis

CLI + Codex · 4 targets

jupyter-notebookcomputer-vision
by michalfaberDetailsQuick view
6

Terraform Cost Estimation

NEEDS REVIEW · 49TRUST · 73SAFE · EXPERIMENTALCODING

Anonymized, secure, and free Terraform cost estimation based on Terraform plan (0.12+) or Terraform state (any version)

$ npx skills add antonbabenko/terraform-cost-estimation
730 stars39 quality73 trustExperimental3y since pushNeeds review
QualityInspect the repository carefully before adding it to an agent workflow.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 Coding agents

CLI + Codex · 4 targets

jqterraform
by antonbabenkoDetailsQuick view
7

Lightweight Human Pose Estimation 3d Demo.Pytorch

NEEDS REVIEW · 49TRUST · 73SAFE · EXPERIMENTALCODING

Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.

$ npx skills add Daniil-Osokin/lightweight-human-pose-estimation-3d-demo.pytorch
687 stars39 quality73 trustExperimental3y since pushNeeds review
QualityInspect the repository carefully before adding it to an agent workflow.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 Coding agents

CLI + Codex · 4 targets

pythoncomputer-vision
by Daniil-OsokinDetailsQuick view
8

Jupyter C Kernel

NEEDS REVIEW · 48TRUST · 71SAFE · EXPERIMENTALDATA

Minimal Jupyter C kernel

$ npx skills add brendan-rius/jupyter-c-kernel
584 stars38 quality71 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 Data analysis

CLI + Codex · 4 targets

pythonnotebook
by brendan-riusDetailsQuick view
9

Tensorflow Realtime Multi Person Pose Estimation

NEEDS REVIEW · 39TRUST · 67SAFE · BLOCKEDDATA

Multi-Person Pose Estimation project for Tensorflow 2.0 with a small and fast model based on MobilenetV3

$ npx skills add michalfaber/tensorflow_Realtime_Multi-Person_Pose_Estimation
220 stars35 quality67 trustBlocked for auto-install4y since pushRisky
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: License is unclear
Safety gateThis skill should not be selected by an agent without explicit human security review.

Scenario Data analysis

CLI + Codex · 4 targets

jupyter-notebookcomputer-vision
by michalfaberDetailsQuick view
10

Pytorch Realtime Multi Person Pose Estimation

NEEDS REVIEW · 44TRUST · 69SAFE · EXPERIMENTALDATA

Pytorch version of Realtime Multi-Person Pose Estimation project

$ npx skills add last-one/Pytorch_Realtime_Multi-Person_Pose_Estimation
218 stars35 quality69 trustExperimental8y 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 Data analysis

CLI + Codex · 4 targets

jupyter-notebookcomputer-vision
by last-oneDetailsQuick view
11

Binary Human Pose Estimation

NEEDS REVIEW · 38TRUST · 67SAFE · BLOCKEDCODING

This code implements a demo of the Binarized Convolutional Landmark Localizers for Human Pose Estimation and Face Alignment with Limited Resources paper by Adrian Bulat…

$ npx skills add 1adrianb/binary-human-pose-estimation
214 stars35 quality67 trustBlocked for auto-install5y since pushRisky
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: License is unclear
Safety gateThis skill should not be selected by an agent without explicit human security review.

Scenario Coding agents

CLI + Codex · 4 targets

luacomputer-vision
by 1adrianbDetailsQuick view
12

Gaze Estimation

NEEDS REVIEW · 38TRUST · 65SAFE · BLOCKEDCODING

A deep learning based gaze estimation framework implemented with PyTorch

$ npx skills add david-wb/gaze-estimation
200 stars35 quality65 trustBlocked for auto-install6y since pushRisky
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: License is unclear
Safety gateThis skill should not be selected by an agent without explicit human security review.

Scenario GitHub automation

CLI + Codex · 4 targets

jupyter-notebookcomputer-vision
by david-wbDetailsQuick view
13

Kernel Memory

VERIFIEDEXCELLENT · 96TRUST · 86SAFE · REVIEWEDRESEARCH

Research project. A Memory solution for users, teams, and applications.

$ npx skills add microsoft/kernel-memory
2.2K 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 RAG and knowledge

CLI + Codex · 4 targets

c#semantic-search
by microsoftDetailsQuick view
14

CognitiveKernel Pro

PROMISING · 67TRUST · 75SAFE · REVIEWEDRESEARCH

Deep Research Agent CognitiveKernel-Pro from Tencent AI Lab. Paper: https://arxiv.org/pdf/2508.00414

$ npx skills add Tencent/CognitiveKernel-Pro
518 stars50 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 RAG and knowledge

CLI + Codex · 4 targets

pythonresearch-agent
by TencentDetailsQuick view
15

Robotics Object Pose Estimation

NEEDS REVIEW · 46TRUST · 70SAFE · EXPERIMENTALCODING

A complete end-to-end demonstration in which we collect training data in Unity and use that data to train a deep neural network to predict the pose of a cube. This model…

$ npx skills add Unity-Technologies/Robotics-Object-Pose-Estimation
344 stars36 quality70 trustExperimental4y 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

pythonros
by Unity-TechnologiesDetailsQuick view
16

Blur Kernel Space Exploring

NEEDS REVIEW · 42TRUST · 70SAFE · EXPERIMENTALRESEARCH

Exploring Image Deblurring via Blur Kernel Space (CVPR'21)

$ npx skills add VinAIResearch/blur-kernel-space-exploring
163 stars34 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 Research agents

CLI + Codex · 4 targets

pythoncomputer-vision
by VinAIResearchDetailsQuick 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