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.

  • Frontend Design166K stars

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

    Trust 88Quality 100design-creative
  • Material Ui98K stars

    Material UI: Comprehensive React component library that implements Google's Material Design. Free forever.

    Trust 90Quality 100design-creative
  • Design and implementation guidance for distinctive landing pages, portfolios, product demos, and purposeful r…

    Trust 91Quality 100design-creative

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
  • Open Design83K stars

    🎨 Local-first, open-source Claude Design alternative. 🖥️ Native desktop app. ⚡ 259+ Skills · ✨ 142+ Design…

    Trust 91Quality 100agent-skills
  • Agent Skills81K stars

    Production-grade engineering skills for AI coding agents.

    Trust 86Quality 100agent-skills

Documents and knowledge

Research and RAG skills

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

  • Markitdown156K stars

    Python tool for converting files and office documents to Markdown.

    Trust 87Quality 100document-processing
  • PaddleOCR83K stars

    Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bri…

    Trust 89Quality 100document-processing
  • Docling63K stars

    Get your documents ready for gen AI

    Trust 89Quality 100document-processing

Markets and quant

Finance and trading skills

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

  • TradingAgents88K stars

    TradingAgents: Multi-Agents LLM Financial Trading Framework

    Trust 88Quality 100finance
  • Union74K stars

    The trust-minimized, zero-knowledge bridging protocol, designed for censorship resistance, extremely high sec…

    Trust 91Quality 100web3-analytics
  • OpenBB70K stars

    Financial data platform for analysts, quants and AI agents.

    Trust 85Quality 100finance

Crawlers and extraction

Web scraping skills

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

  • Firecrawl139K stars

    The API to search, scrape, and interact with the web at scale. 🔥

    Trust 87Quality 100agent-frameworks
  • Crawl4AI73K stars

    Web crawling built for AI

    Trust 90Quality 100web-automation
  • Scrapling70K stars

    Adaptive web scraping for agent data collection

    Trust 85Quality 100web-automation

Slides and decks

PPT and presentation skills

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

  • Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact ter…

    Trust 91Quality 100design-creative
  • Canvas Design166K stars

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

    Trust 87Quality 100design-creative

Prompts, B-roll, explainers

Video creation skills

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

  • SpargeAttn1.0K stars

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

    Trust 86Quality 85media-automation
  • SageAttention3.4K stars

    [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAtt…

    Trust 84Quality 87media-automation
  • Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (…

    Trust 81Quality 77media-automation

Images, video, UI

Design and creative skills

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

  • Apply Anthropic official brand colors, typography, and visual standards to appropriate Anthropic-related arti…

    Trust 88Quality 100design-creative
  • DyPE357 stars

    [ICML 2026] Official implementation for "DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffu…

    Trust 78Quality 71media-automation
  • MagicDance777 stars

    [ICML 2024] MagicPose(also known as MagicDance): Realistic Human Poses and Facial Expressions Retargeting wit…

    Trust 70Quality 44media-automation

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

178

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

174 quality170 maintained

Research

Research and knowledge work

65

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

64 quality64 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

58

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

55 quality52 maintained

Data

Data, BI, and analytics

32

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

32 quality31 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

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 364 ranked candidates matching "icml"

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

1

Composer

VERIFIEDEXCELLENT · 97TRUST · 85SAFE · REVIEWEDDESIGN

Supercharge Your Model Training

$ npx skills add mosaicml/composer
5.5K stars65 quality85 trustReviewed3mo 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

CLI + Codex · 4 targets

pythonmachine-learning
by mosaicmlDetailsQuick view
2

MultiDiffusion

VERIFIEDPROMISING · 60TRUST · 76SAFE · EXPERIMENTALDESIGN

Official Pytorch Implementation for "MultiDiffusion: Fusing Diffusion Paths for Controlled Image Generation" presenting "MultiDiffusion" (ICML 2023)

$ npx skills add omerbt/MultiDiffusion
1.1K stars48 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 Design and creative

CLI + Codex · 4 targets

jupyter-notebookimage-generation
by omerbtDetailsQuick view
3

OmniShow

STRONG · 71TRUST · 78SAFE · REVIEWEDDESIGN

[ICML 2026] ByteDance's All-in-One Video Generation Model for Human-Object Interaction Video Generation

$ npx skills add Correr-Zhou/OmniShow
407 stars49 quality78 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 Design and creative

CLI + Codex · 4 targets

pythonvideo-generation
by Correr-ZhouDetailsQuick view
4

DyPE

STRONG · 71TRUST · 78SAFE · REVIEWEDDESIGN

[ICML 2026] Official implementation for "DyPE: Dynamic Position Extrapolation for Ultra High Resolution Diffusion".

$ npx skills add guyyariv/DyPE
357 stars49 quality78 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 Design and creative

CLI + Codex · 4 targets

pythonimage-generation
by guyyarivDetailsQuick view
5

Imbalanced Regression

NEEDS REVIEW · 50TRUST · 71SAFE · EXPERIMENTALCODING

[ICML 2021, Long Talk] Delving into Deep Imbalanced Regression

$ npx skills add YyzHarry/imbalanced-regression
920 stars39 quality71 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

pythoncomputer-vision
by YyzHarryDetailsQuick view
6

SageAttention

VERIFIEDEXCELLENT · 87TRUST · 84SAFE · REVIEWEDDESIGN

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, i…

$ npx skills add thu-ml/SageAttention
3.4K stars59 quality84 trustReviewed7mo 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

cudavideo-generation
by thu-mlDetailsQuick view
7

Code2Video

VERIFIEDEXCELLENT · 95TRUST · 86SAFE · REVIEWEDCODING

[ICML 2026] Video generation via code

$ npx skills add showlab/Code2Video
1.8K stars64 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

pythonmulti-agent
by showlabDetailsQuick view
8

Top AI Conferences Paper With Code

VERIFIEDPROMISING · 64TRUST · 76SAFE · EXPERIMENTALCODING

MLNLP: This repository is a collection of AI top conferences papers (e.g. ACL, EMNLP, NAACL, COLING, AAAI, IJCAI, ICLR, NeurIPS, and ICML) with open resource code

$ npx skills add MLNLP-World/Top-AI-Conferences-Paper-with-Code
2.7K stars51 quality76 trustExperimental4y 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

computer-vision
by MLNLP-WorldDetailsQuick view
9

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
10

LLMCompiler

VERIFIEDPROMISING · 67TRUST · 77SAFE · EXPERIMENTALCODING

[ICML 2024] LLMCompiler: An LLM Compiler for Parallel Function Calling

$ npx skills add SqueezeAILab/LLMCompiler
1.9K stars50 quality77 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

pythonllm
by SqueezeAILabDetailsQuick view
11

MedRAX

VERIFIEDSTRONG · 78TRUST · 82SAFE · REVIEWEDCODING

MedRAX: Medical Reasoning Agent for Chest X-ray - ICML 2025

$ npx skills add bowang-lab/MedRAX
1.2K stars52 quality82 trustReviewed with permission notesLangChain9mo 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

LangChain + CLI · 4 targets

pythonhealth-data
by bowang-labDetailsQuick view
12

Code Act

VERIFIEDPROMISING · 67TRUST · 79SAFE · EXPERIMENTALCODING

Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.

$ npx skills add xingyaoww/code-act
1.7K stars49 quality79 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

pythonllm
by xingyaowwDetailsQuick view
13

Deep Gcns Torch

VERIFIEDPROMISING · 65TRUST · 79SAFE · EXPERIMENTALDATA

Pytorch Repo for DeepGCNs (ICCV'2019 Oral, TPAMI'2021), DeeperGCN (arXiv'2020) and GNN1000(ICML'2021): https://www.deepgcns.org

$ npx skills add lightaime/deep_gcns_torch
1.2K stars48 quality79 trustExperimental4y 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 Data analysis

CLI + Codex · 4 targets

pythoncomputer-vision
by lightaimeDetailsQuick view
14

DiT Extrapolation

STRONG · 77TRUST · 81SAFE · REVIEWEDDESIGN

Official implementation for "RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers" (ICML 2025) , UltraViCo (ICLR 2026) and UltraImage

$ npx skills add thu-ml/DiT-Extrapolation
808 stars54 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 Design and creative

CLI + Codex · 4 targets

pythonvideo-generation
by thu-mlDetailsQuick view
15

Causal Forcing

STRONG · 77TRUST · 80SAFE · REVIEWEDDESIGN

[ICML 2026] Official codebase for "Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation" & Causal For…

$ npx skills add thu-ml/Causal-Forcing
786 stars54 quality80 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 Design and creative

CLI + Codex · 4 targets

pythonvideo-generation
by thu-mlDetailsQuick view
16

Open AgentRL

STRONG · 73TRUST · 77SAFE · EXPERIMENTALCODING

[ICML 2026] RLAnything & DemyAgent: General and scalable agentic RL algorithms across terminal, GUI, SWE, and tool-call settings

$ npx skills add Gen-Verse/Open-AgentRL
585 stars50 quality77 trustExperimental2mo 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 gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario Coding agents

CLI + Codex · 4 targets

pythonllm
by Gen-VerseDetailsQuick 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