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.

  • Next4.7K stars

    🦍 A configurable component library for web built on React.

    Trust 86Quality 99design-creative
  • Reloader10K stars

    A Kubernetes controller to watch changes in ConfigMap and Secrets and do rolling upgrades on Pods with their…

    Trust 90Quality 100devops
  • Assistant Ui11K stars

    Typescript/React Library for AI Chat💬🚀

    Trust 88Quality 100support-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
  • To Tickets177K stars

    Turn an approved plan into vertical-slice tickets with explicit dependencies.

    Trust 88Quality 100coding-agents

Documents and knowledge

Research and RAG skills

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

  • DocsGPT18K stars

    Private AI platform for agents, assistants and enterprise search. Built-in Agent Builder, Deep research, Docu…

    Trust 89Quality 100rag-knowledge
  • Graphify91K stars

    AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, and more). Turn any folder of co…

    Trust 87Quality 100rag-knowledge
  • The open source code of this project is used for userscripts (油猴脚本) for desktop browsers, including Font Rend…

    Trust 87Quality 100rag-knowledge

Markets and quant

Finance and trading skills

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

  • Nofx13K stars

    Your AI trading terminal assistant for US stocks, commodities, forex, and crypto.

    Trust 88Quality 100finance
  • Midday15K stars

    Invoicing, Time tracking, File reconciliation, Storage, Financial Overview & your own Assistant made for Free…

    Trust 89Quality 100finance
  • 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
  • Malicious Pdf4.1K stars

    💀 Generate malicious PDF test files for testing phone-home callbacks, SSRF, XSS, NTLM credential theft, and…

    Trust 83Quality 99document-processing
  • DevOps Guide9.3K stars

    DevOps Guide - Development to Production all configurations with basic notes to debug efficiently.

    Trust 88Quality 99devops

Slides and decks

PPT and presentation skills

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

  • Modular SenseNova skills for building AI-powered office assistants and productivity workflows

    Trust 87Quality 99data-analysis
  • 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.

  • OpenMontage42K stars

    World's first open-source, agentic video production system. 12 pipelines, 52 tools, 500+ agent skills. Turn y…

    Trust 92Quality 100agent-skills

Images, video, UI

Design and creative skills

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

  • Rasa21K stars

    💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue mana…

    Trust 90Quality 100ml-automation
  • (Supports DeepSeek R1) An AI-powered research assistant that performs iterative, deep research on any topic b…

    Trust 84Quality 91research
  • 面向长篇小说创作的 AI Native 开源系统,用 Agent、世界观、写法引擎、RAG 和整本生产工作流,帮助新手从一句灵感走到完整小说。AI-native engine for end-to-end novel…

    Trust 84Quality 89rag-knowledge

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

230

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

230 quality229 maintained

Research

Research and knowledge work

76

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

76 quality76 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

50

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

50 quality50 maintained

Data

Data, BI, and analytics

38

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

38 quality38 maintained

Legal

Legal, policy, and compliance

15

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

15 quality15 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 429 ranked candidates matching "home-assistant-config"

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

1

Home Assistant Config

VERIFIEDEXCELLENT · 95TRUST · 86SAFE · REVIEWEDCODING

:house: My Home Assistant configuration, a bit different that others :) Be sure to :star2: this repository for updates!

$ npx skills add frenck/home-assistant-config
2.0K 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 Coding agents

CLI + Codex · 4 targets

iot
by frenckDetailsQuick view
2

Homeassistant Powercalc

VERIFIEDEXCELLENT · 94TRUST · 88SAFE · REVIEWEDCODING

Home Assistant Custom component to calculate estimated power consumption of lights and other appliances

$ npx skills add bramstroker/homeassistant-powercalc
1.5K stars64 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

pythoniot
by bramstrokerDetailsQuick view
3

Homelab

VERIFIEDEXCELLENT · 100TRUST · 86SAFE · REVIEWEDCODING

Fully automated homelab from empty disk to running services with a single command.

$ npx skills add khuedoan/homelab
9.4K stars70 quality86 trustReviewed with permission notes2mo 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario GitHub automation

CLI + Codex · 4 targets

pythonkubernetes
by khuedoanDetailsQuick view
4

Addons

VERIFIEDEXCELLENT · 96TRUST · 82SAFE · REVIEWEDCODING

:heavy_plus_sign: Docker add-ons for Home Assistant

$ npx skills add home-assistant/addons
2.2K stars65 quality82 trustReviewed with permission notes2mo 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 GitHub automation

CLI + Codex · 4 targets

shelliot
by home-assistantDetailsQuick view
5

Natively Cluely AI Assistant

VERIFIEDEXCELLENT · 99TRUST · 86SAFE · REVIEWEDCODING

Natively — Free open-source AI meeting assistant, interview copilot, and note taker. The best alternative to Cluely, Otter, Granola, Final Round AI, Fireflies, and Inter…

$ npx skills add Natively-AI-assistant/natively-cluely-ai-assistant
1.8K stars65 quality86 trustReviewedClaude Code20d 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: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Coding agents

Claude Code + CLI · 4 targets

typescriptdeveloper-tools
by Natively-AI-assistantDetailsQuick view
6

AdGuardHome

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDLEGAL

Network-wide ads & trackers blocking DNS server

$ npx skills add AdguardTeam/AdGuardHome
34.9K stars75 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 Legal and compliance

CLI + Codex · 4 targets

goprivacy
by AdguardTeamDetailsQuick view
7

Assistant Ui

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

Typescript/React Library for AI Chat💬🚀

$ npx skills add assistant-ui/assistant-ui
10.6K stars71 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

typescriptchatbot
by assistant-uiDetailsQuick view
8

NextDNS Config

VERIFIEDEXCELLENT · 97TRUST · 85SAFE · REVIEWEDLEGAL

Setup guide for NextDNS, a DoH proxy with advanced capabilities

$ npx skills add yokoffing/NextDNS-Config
3.0K 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 Legal and compliance

CLI + Codex · 4 targets

privacy
by yokoffingDetailsQuick view
9

Home Ops

VERIFIEDEXCELLENT · 97TRUST · 85SAFE · REVIEWEDCODING

Wife approved HomeOps driven by Kubernetes and GitOps using Flux

$ npx skills add onedr0p/home-ops
2.8K 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

yamlkubernetes
by onedr0pDetailsQuick view
10

Ha Bambulab

VERIFIEDEXCELLENT · 91TRUST · 82SAFE · REVIEWEDCODING

A Home Assistant Integration for Bambu Lab Printers

$ npx skills add greghesp/ha-bambulab
2.2K stars65 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 Coding agents

CLI + Codex · 4 targets

pythoniot
by greghespDetailsQuick view
11

OpenBK7231T App

VERIFIEDEXCELLENT · 91TRUST · 84SAFE · REVIEWEDRESEARCH

Open source firmware (Tasmota/Esphome replacement) for BK7231T, BK7231N, BL2028N, T34, XR809, W800/W801, W600/W601, BL602, LN882H, Realtek chips and more

$ npx skills add openshwprojects/OpenBK7231T_App
2.2K stars65 quality84 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: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents

CLI + Codex · 4 targets

ciot
by openshwprojectsDetailsQuick view
12

OpenCCU

VERIFIEDEXCELLENT · 95TRUST · 86SAFE · REVIEWEDCODING

:house: Buildroot-based, cloud-free smart-home platform for a Homematic IP CCU (CCU3/ELV-Charly). Runs on Raspberry Pi & x86/ARM or as a virtual appliance (Proxmox VE, H…

$ npx skills add OpenCCU/OpenCCU
1.8K stars64 quality86 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 Coding agents

CLI + Codex · 4 targets

javascriptkubernetes
by OpenCCUDetailsQuick view
13

AI Novel Writing Assistant

VERIFIEDEXCELLENT · 89TRUST · 84SAFE · REVIEWEDRESEARCH

面向长篇小说创作的 AI Native 开源系统,用 Agent、世界观、写法引擎、RAG 和整本生产工作流,帮助新手从一句灵感走到完整小说。AI-native engine for end-to-end novel creation — from idea to full chapters, with structured plann…

$ npx skills add ExplosiveCoderflome/AI-Novel-Writing-Assistant
1.6K stars64 quality84 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: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario RAG and knowledge

CLI + Codex · 4 targets

typescriptrag
by ExplosiveCoderflomeDetailsQuick view
14

Cue

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDCODING

The home of the CUE language! Validate and define text-based and dynamic configuration

$ npx skills add cue-lang/cue
6.1K stars68 quality89 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

gokubernetes
by cue-langDetailsQuick view
15

Chatbox

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

Powerful AI Client

$ npx skills add chatboxai/chatbox
40.5K stars75 quality88 trustReviewedClaude Code + OpenAI Agents2mo 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

typescriptchatbot
by chatboxaiDetailsQuick view
16

Khoj

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDRESEARCH

Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule automations, do deep research. Turn any online or local LLM int…

$ npx skills add khoj-ai/khoj
35.3K stars75 quality90 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 RAG and knowledge

Claude Code + OpenAI Agents · 4 targets

pythonrag
by khoj-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