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.

  • Emil Design Engineering13K stars

    This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the in…

    Trust 91Quality 100design-creative
  • Fluid1.9K stars

    Fluid, elastic data abstraction and acceleration for BigData/AI applications in cloud. (Project under CNCF)

    Trust 88Quality 95devops
  • Qualcommax NSS Builder111 stars

    Automated OpenWrt firmware builder with NSS hardware acceleration for Xiaomi AX3600 (IPQ807x) — hardened, opt…

    Trust 72Quality 64github-automation

Codex, Claude Code, Cursor

Coding agent skills

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

  • Econ Writing Skill470 stars

    Agent Skill that transforms AI assistants into expert economics paper writers. Synthesizes 50+ guides by Coch…

    Trust 85Quality 94research
  • Xget8.2K stars

    Ultra-high-performance, secure, all-in-one acceleration engine for developer resources

    Trust 90Quality 100agent-skills
  • Paleo18 stars

    🦴 paleo — token-saving skills for LLM agents: compress output, trim context, cap budget (Claude Code / Codex…

    Trust 71Quality 65utility

Documents and knowledge

Research and RAG skills

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

  • Axiom Voice Agent138 stars

    Run a <400ms latency Voice Agent on just 4GB VRAM. Fully offline, no API keys required. Optimized for GTX 165…

    Trust 76Quality 70rag-knowledge
  • Sie2.1K stars

    Open-source inference server and production cluster for all the models your agent needs.

    Trust 87Quality 95rag-knowledge
  • EmbedAnything1.3K stars

    Highly Performant, Modular, Memory Safe and Production-ready Inference, Ingestion and Indexing built in Rust…

    Trust 87Quality 93data

Markets and quant

Finance and trading skills

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

  • Flowpylib137 stars

    Algo Library for Order Flow Inference and TCA

    Trust 73Quality 55finance
  • Stochastic Rs169 stars

    High-performance quantitative finance in Rust — 120+ stochastic processes, option pricing, calibration, fixed…

    Trust 78Quality 70finance
  • Company Research Agent2.0K stars

    An agentic company research tool powered by LangGraph and Tavily that conducts deep diligence on companies us…

    Trust 88Quality 95agent-frameworks

Crawlers and extraction

Web scraping skills

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

  • OpenMLDB1.7K stars

    OpenMLDB is an open-source machine learning database that provides a feature platform computing consistent fe…

    Trust 87Quality 98ml-automation
  • PaddleOCR2Pytorch1.2K stars

    PaddleOCR inference in PyTorch. Converted from [PaddleOCR](https://github.com/PaddlePaddle/PaddleOCR)

    Trust 87Quality 93document-processing
  • OnnxOCR1.8K stars

    基于PaddleOCR重构，并且脱离PaddlePaddle深度学习训练框架的轻量级OCR，推理速度超快 —— A lightweight OCR system based on PaddleOCR, decouple…

    Trust 86Quality 95document-processing

Slides and decks

PPT and presentation skills

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

  • Architecture Drawer16 stars

    Skill for Claude Code & Codex: describe your system architecture in text → get an editable PowerPoint diagram…

    Trust 74Quality 64presentation

Prompts, B-roll, explainers

Video creation skills

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

  • FastVideo3.7K stars

    A unified inference and post-training framework for accelerated video generation.

    Trust 88Quality 98media-automation
  • SpargeAttn1.0K stars

    [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

    Trust 86Quality 85media-automation
  • LightX2V2.4K stars

    Lightweight Image Video Action Generation Inference Framework

    Trust 85Quality 96media-automation

Images, video, UI

Design and creative skills

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

  • Stable Diffusion.Cpp6.3K stars

    Diffusion model(SD,Flux,Wan,Qwen Image,Z-Image,...) inference in pure C/C++

    Trust 87Quality 100media-automation
  • Vllm Omni5.2K stars

    A framework for efficient model inference with omni-modality models

    Trust 87Quality 100media-automation
  • Minimalistic Comfy Wrapper WebUI129 stars

    MCWW: Additional non-node based UI for ComfyUI focused on inference. Stable UI states; presets; and advanced…

    Trust 78Quality 69media-automation

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

207

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

205 quality199 maintained

Research

Research and knowledge work

77

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

77 quality74 maintained

Presentation

Presentation and deck workflows

2

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

2 quality2 maintained

Finance

Finance and quant workflows

15

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

15 quality14 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

99

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

95 quality83 maintained

Data

Data, BI, and analytics

36

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

36 quality35 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

6

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

6 quality6 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
FinanceStock analysisQuantTrading researchSlidesPPT generationDocsPDF parsingExtractWeb scrapingCreativeDesign workflowSportsFootball analytics

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-16 of 450 ranked candidates matching "inference-acceleration"

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

1

TurboDiffusion

VERIFIEDEXCELLENT · 95TRUST · 84SAFE · REVIEWEDDESIGN

TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

$ npx skills add thu-ml/TurboDiffusion
3.5K stars64 quality84 trustReviewed4mo 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 Design and creative

CLI + Codex · 4 targets

pythonvideo-generation
by thu-mlDetailsQuick view
2

Jetson Inference

VERIFIEDEXCELLENT · 87TRUST · 86SAFE · REVIEWEDDESIGN

Hello AI World guide to deploying deep-learning inference networks and deep vision primitives with TensorRT and NVIDIA Jetson.

$ npx skills add dusty-nv/jetson-inference
8.9K stars58 quality86 trustReviewed10mo 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++machine-learning
by dusty-nvDetailsQuick view
3

Inference

VERIFIEDEXCELLENT · 91TRUST · 80SAFE · REVIEWEDCODING

Turn any computer or edge device into a command center for your computer vision projects.

$ npx skills add roboflow/inference
2.3K stars65 quality80 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: License is unclear
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

CLI + Codex · 4 targets

pythoncomputer-vision
by roboflowDetailsQuick view
4

SpargeAttn

VERIFIEDEXCELLENT · 85TRUST · 86SAFE · REVIEWEDDESIGN

[ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.

$ npx skills add thu-ml/SpargeAttn
1.0K stars56 quality86 trustReviewed5mo 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 Design and creative

CLI + Codex · 4 targets

cudavideo-generation
by thu-mlDetailsQuick view
5

YOLO Patch Based Inference

STRONG · 73TRUST · 77SAFE · REVIEWEDCODING

Python library for YOLO small object detection and instance segmentation

$ npx skills add Koldim2001/YOLO-Patch-Based-Inference
553 stars50 quality77 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 Coding agents

CLI + Codex · 4 targets

pythoncomputer-vision
by Koldim2001DetailsQuick view
6

Text Embeddings Inference

VERIFIEDEXCELLENT · 99TRUST · 86SAFE · REVIEWEDRESEARCH

A blazing fast inference solution for text embeddings models

$ npx skills add huggingface/text-embeddings-inference
4.9K stars68 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

rustembeddings
by huggingfaceDetailsQuick view
7

Server

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDDESIGN

The Triton Inference Server provides an optimized cloud and edge inferencing solution.

$ npx skills add triton-inference-server/server
10.8K stars71 quality90 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

pythonmachine-learning
by triton-inference-serverDetailsQuick view
8

Statistical Inferences

STRONG · 73TRUST · 78SAFE · REVIEWEDEDUCATION

Repository for the textbook 'Improving Your Statistical Inferences' by Daniel Lakens

$ npx skills add Lakens/statistical_inferences
312 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 Education and tutoring

CLI + Codex · 4 targets

texeducation
by LakensDetailsQuick view
9

Willow Inference Server

PROMISING · 68TRUST · 79SAFE · REVIEWEDDESIGN

Open source, local, and self-hosted highly optimized language inference server supporting ASR/STT, TTS, and LLM across WebRTC, REST, and WS

$ npx skills add toverainc/willow-inference-server
504 stars46 quality79 trustReviewed with permission notes6mo 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 Multimodal media

CLI + Codex · 4 targets

pythonspeech
by toveraincDetailsQuick view
10

Hivemq Mqtt Tensorflow Kafka Realtime Iot Machine Learning Training Inference

NEEDS REVIEW · 46TRUST · 71SAFE · EXPERIMENTALCODING

Real Time Big Data / IoT Machine Learning (Model Training and Inference) with HiveMQ (MQTT), TensorFlow IO and Apache Kafka - no additional data store like S3, HDFS or S…

$ npx skills add kaiwaehner/hivemq-mqtt-tensorflow-kafka-realtime-iot-machine-learning-training-inference
419 stars37 quality71 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

jupyter-notebookterraform
by kaiwaehnerDetailsQuick view
11

Whisper.Cpp

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDDESIGN

Port of OpenAI's Whisper model in C/C++

$ npx skills add ggml-org/whisper.cpp
51.0K stars76 quality88 trustReviewedOpenAI 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 Multimodal media

OpenAI Agents + CLI · 4 targets

c++speech
by ggml-orgDetailsQuick view
12

DeepSpeed

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDDESIGN

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

$ npx skills add deepspeedai/DeepSpeed
42.5K stars76 quality90 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

pythonmachine-learning
by deepspeedaiDetailsQuick view
13

BentoML

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDCODING

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

$ npx skills add bentoml/BentoML
8.7K stars69 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 Coding agents

CLI + Codex · 4 targets

pythonllmops
by bentomlDetailsQuick view
14

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 Agents18d 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
15

Dowhy

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDCODING

DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inferen…

$ npx skills add py-why/dowhy
8.2K stars69 quality89 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

pythonmachine-learning
by py-whyDetailsQuick view
16

Causalml

VERIFIEDEXCELLENT · 95TRUST · 84SAFE · REVIEWEDDESIGN

Uplift modeling and causal inference with machine learning algorithms

$ npx skills add uber/causalml
5.9K stars68 quality84 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 Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by uberDetailsQuick 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