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.

  • Kubernetes Skill for Claude Code and Codex. LLMs hallucinate a lot with K8s - KubeShark fixes this. It elimin…

    Trust 78Quality 72devops
  • Last-night exam-cram coach as a Claude Agent Skill: turns your slides, notes and past papers into a chaptered…

    Trust 85Quality 91productivity
  • Pagecast179 stars

    Publish HTML, Markdown and static mini apps to shareable Cloudflare Pages URLs from the terminal or coding ag…

    Trust 81Quality 89development

Codex, Claude Code, Cursor

Coding agent skills

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

  • Drive the OpenAI Codex CLI as a background implementer, brief it, review its diff, land the commit yourself.

    Trust 75Quality 68coding-agents
  • Agent Skills81K stars

    Production-grade engineering skills for AI coding agents.

    Trust 86Quality 100agent-skills
  • Skills122 stars

    Agent Skills for the Venice.ai API. One folder per surface area, each with a SKILL.md for agent runtimes (Cur…

    Trust 84Quality 87utility

Documents and knowledge

Research and RAG skills

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

  • Start Llms973 stars

    A complete guide to start and improve your LLM skills in 2026 with little background in the field and stay up…

    Trust 78Quality 67rag-knowledge
  • Pyspur5.8K stars

    A visual playground for agentic workflows: Iterate over your agents 10x faster

    Trust 87Quality 100data
  • Mentedb100 stars

    A cognition aware database engine for AI agent memory. Purpose built in Rust with WAL, HNSW, knowledge graphs…

    Trust 76Quality 65rag-knowledge

Crawlers and extraction

Web scraping skills

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

  • NBLM2PPTX324 stars

    Convert NotebookLM PDFs to PPTX with separated background images and editable text layers using Gemini AI

    Trust 75Quality 62document-processing
  • Text Grab4.8K stars

    Use OCR in Windows quickly and easily with Text Grab. With optional background process and notifications.

    Trust 88Quality 99document-processing
  • Some awesome AI related books and pdfs for learning and downloading, also apply some playground models for le…

    Trust 85Quality 88document-processing

Prompts, B-roll, explainers

Video creation skills

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

  • Wunjo CE: Face Swap, Lip Sync, Control Remove Objects & Text & Background, Restyling, Audio Separator, Clone…

    Trust 86Quality 86media-automation
  • Turn creator performance data into a documented retrospective, grounded hypotheses, and reusable content lear…

    Trust 74Quality 81Video Creation
  • Skills58 stars

    Agent skill library for PixVerse CLI — helps AI agents (Claude Code, Cursor, Codex, etc.) generate videos and…

    Trust 74Quality 70design-creative

Images, video, UI

Design and creative skills

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

  • SiamMask3.5K stars

    [CVPR19/TPAMI23] SiamMask: A Framework for Fast Online Object Tracking and Segmentation

    Trust 82Quality 70robotics-iot
  • Tastemaker75 stars

    A Claude Code skill that grounds AI-generated UI in real reference images and a persistent per-developer tast…

    Trust 77Quality 71design-creative
  • Robosat2.1K stars

    Semantic segmentation on aerial and satellite imagery. Extracts features such as: buildings, parking lots, ro…

    Trust 88Quality 95ml-automation

Analysis and pipelines

Data and analytics skills

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

  • Pg Background251 stars

    Production-grade PostgreSQL extension to execute arbitrary SQL in background worker processes — with async ex…

    Trust 73Quality 67data-analysis
  • Agent skill for migrating Tableau, Looker, and Power BI dashboards to Hex apps: extract specs, rebuild with H…

    Trust 76Quality 68utility
  • WrenAI16K stars

    Give AI agents the context to query business data correctly through the open context layer that gives AI agen…

    Trust 85Quality 100data

SEO and content

Marketing and growth skills

SEO, content research, growth workflows, social listening, campaign analysis, and publishing helpers.

  • Agent-led recent-trends research across social, prediction markets, video, code, and the web.

    Trust 91Quality 100research
  • Unofficial D&D 5e Dungeon Master for Claude Code — persistent campaigns, full 5e mechanics, and an optional c…

    Trust 85Quality 87utility

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

234

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

232 quality223 maintained

Research

Research and knowledge work

81

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

81 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

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

68

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

67 quality59 maintained

Data

Data, BI, and analytics

37

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

37 quality36 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

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 446 ranked candidates matching "ground-segmentation"

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

1

Obs Backgroundremoval

VERIFIEDEXCELLENT · 99TRUST · 88SAFE · REVIEWEDDESIGN

An OBS plugin for removing background in portrait images (video), making it easy to replace the background when recording or streaming.

$ npx skills add royshil/obs-backgroundremoval
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 Multimodal media

CLI + Codex · 4 targets

c++computer-vision
by royshilDetailsQuick view
2

Semantic Segmentation Editor

VERIFIEDPROMISING · 67TRUST · 80SAFE · REVIEWEDDESIGN

Web labeling tool for bitmap images and point clouds

$ npx skills add Hitachi-Automotive-And-Industry-Lab/semantic-segmentation-editor
2.0K stars50 quality80 trustReviewed with permission notes2y 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 Multimodal media

CLI + Codex · 4 targets

javascriptmachine-learning
by Hitachi-Automotive-And-Industry-LabDetailsQuick view
3

Pytorch Segmentation

VERIFIEDPROMISING · 67TRUST · 80SAFE · REVIEWEDCODING

:art: Semantic segmentation models, datasets and losses implemented in PyTorch.

$ npx skills add yassouali/pytorch-segmentation
1.8K stars50 quality80 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

jupyter-notebookcomputer-vision
by yassoualiDetailsQuick view
4

Awesome Grounding

VERIFIEDSTRONG · 78TRUST · 82SAFE · REVIEWEDRESEARCH

awesome grounding: A curated list of research papers in visual grounding

$ npx skills add TheShadow29/awesome-grounding
1.1K stars52 quality82 trustReviewed with permission notes11mo 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 Research agents

CLI + Codex · 4 targets

research
by TheShadow29DetailsQuick view
5

Efficient Segmentation Networks

VERIFIEDPROMISING · 64TRUST · 79SAFE · REVIEWEDCODING

Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CG…

$ npx skills add xiaoyufenfei/Efficient-Segmentation-Networks
1.0K stars48 quality79 trustReviewed with permission notes2y 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

pythoncomputer-vision
by xiaoyufenfeiDetailsQuick view
6

Patchwork

STRONG · 73TRUST · 81SAFE · REVIEWEDRESEARCH

SOTA fast and robust ground segmentation using 3D point cloud (accepted in RA-L'21 w/ IROS'21)

$ npx skills add LimHyungTae/patchwork
584 stars50 quality81 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 RAG and knowledge

CLI + Codex · 4 targets

c++ros
by LimHyungTaeDetailsQuick view
7

Solana Playground

STRONG · 78TRUST · 79SAFE · REVIEWEDCODING

Quickly develop, deploy and test Solana programs from browsers

$ npx skills add solana-playground/solana-playground
943 stars55 quality79 trustReviewedBrowser agents2mo 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 Testing and QA

Browser agents + CLI · 4 targets

rustblockchain
by solana-playgroundDetailsQuick view
8

Gitops Playground

STRONG · 72TRUST · 78SAFE · REVIEWEDCODING

Creates a complete GitOps-based operational stack / IDP on your Kubernetes clusters

$ npx skills add cloudogu/gitops-playground
266 stars51 quality78 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 GitHub automation

CLI + Codex · 4 targets

groovykubernetes
by cloudoguDetailsQuick view
9

Pg Background

PROMISING · 67TRUST · 73SAFE · REVIEWEDDATA

Production-grade PostgreSQL extension to execute arbitrary SQL in background worker processes — with async execution, autonomous transactions, cookie-protected handles,…

$ npx skills add vibhorkum/pg_background
251 stars51 quality73 trustReviewed with permission notes2mo 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 Database and SQL

CLI + Codex · 4 targets

plpgsqletl
by vibhorkumDetailsQuick view
10

Flow Playground

PROMISING · 66TRUST · 75SAFE · REVIEWEDCODING

Flow Playground. Browser-based IDE for writing, compiling, and testing Cadence smart contracts directly in a browser

$ npx skills add onflow/flow-playground
116 stars45 quality75 trustReviewed with permission notesBrowser agents3mo since pushNeeds review
QualityUseful candidate, but compare it with alternatives before adopting.
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 Coding agents

Browser agents + CLI · 4 targets

typescriptdeveloper-tools
by onflowDetailsQuick view
11

Line Segmentation Algorithm To Gcp Vision

PROMISING · 65TRUST · 72SAFE · REVIEWEDRESEARCH

Line segmentation algorithm for Google Vision API.

$ npx skills add sshniro/line-segmentation-algorithm-to-gcp-vision
96 stars45 quality72 trustReviewed with permission notes2mo since pushNeeds review
QualityUseful candidate, but compare it with alternatives before adopting.
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 Document processing

CLI + Codex · 4 targets

kotlininvoice
by sshniroDetailsQuick view
12

Gpt Image Playground

VERIFIEDEXCELLENT · 96TRUST · 84SAFE · REVIEWEDDESIGN

基于 OpenAI gpt-image-2 API 的图片生成与编辑工具

$ npx skills add CookSleep/gpt_image_playground
2.5K stars65 quality84 trustReviewedOpenAI 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 gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

OpenAI Agents + CLI · 4 targets

typescriptimage-generation
by CookSleepDetailsQuick view
13

BackgroundMattingV2

VERIFIEDSTRONG · 73TRUST · 79SAFE · REVIEWEDDESIGN

Real-Time High-Resolution Background Matting

$ npx skills add PeterL1n/BackgroundMattingV2
7.2K stars54 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

pythonmachine-learning
by PeterL1nDetailsQuick view
14

Dalle Playground

VERIFIEDPROMISING · 69TRUST · 80SAFE · REVIEWEDDESIGN

A playground to generate images from any text prompt using Stable Diffusion (past: using DALL-E Mini)

$ npx skills add saharmor/dalle-playground
2.7K stars51 quality80 trustReviewed with permission notesOpenAI Agents2y 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 Multimodal media

OpenAI Agents + CLI · 4 targets

javascriptmachine-learning
by saharmorDetailsQuick view
15

DIS

VERIFIEDPROMISING · 68TRUST · 81SAFE · EXPERIMENTALCODING

This is the repo for our new project Highly Accurate Dichotomous Image Segmentation

$ npx skills add xuebinqin/DIS
2.6K stars51 quality81 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 GitHub automation

CLI + Codex · 4 targets

jupyter-notebookcomputer-vision
by xuebinqinDetailsQuick view
16

Ipynb Playground

VERIFIEDPROMISING · 61TRUST · 75SAFE · EXPERIMENTALCODING

Various ipython notebooks

$ npx skills add julienr/ipynb_playground
1.6K stars49 quality75 trustExperimental9y 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 GitHub automation

CLI + Codex · 4 targets

jupyter-notebookblockchain
by julienrDetailsQuick 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