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.

  • 可能是最深度的 AI 投研报告 Skill:九章个股深研 + 九章财报深度分析,脚本化 DCF/EPV 与可复算估值

    Trust 83Quality 89utility
  • A complete guide to start and improve in machine learning (ML), artificial intelligence (AI) in 2026 without…

    Trust 86Quality 89ml-automation
  • Guaardvark104 stars

    The self-hosted AI workstation. Autonomous screen agents, 3-tier neural routing, parallel agent swarms, video…

    Trust 78Quality 68media-automation

Codex, Claude Code, Cursor

Coding agent skills

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

  • AI Dev Kit1.7K stars

    Databricks Toolkit for Coding Agents provided by Field Engineering

    Trust 82Quality 90coding-agents
  • Vendor-neutral OpenTelemetry skills for AI coding agents, grounded in upstream sources

    Trust 75Quality 70coding-agents
  • Pr Af106 stars

    AI-Native multi-agent Code Reviewer Built on AgentField

    Trust 73Quality 63coding-agents

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
  • Agentfield2.3K stars

    Build, run and scale AI agents like API and microservices - observable,auditable and identity-aware from day…

    Trust 87Quality 99data
  • When Philosophy meets AI

    Trust 83Quality 79rag-knowledge

Markets and quant

Finance and trading skills

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

  • Roboquant459 stars

    Roboquant is a fast, flexible, user-friendly and completely free algorithmic trading platform

    Trust 80Quality 78finance
  • Bittensor1.5K stars

    Internet-scale Neural Networks

    Trust 85Quality 94web3-analytics
  • Aimet2.6K stars

    AIMET is a library that provides advanced quantization and compression techniques for trained neural network…

    Trust 83Quality 92ml-automation

Crawlers and extraction

Web scraping skills

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

  • Claude Code skill: turn YouTube videos into structured, Obsidian-ready Markdown notes with full metadata, cha…

    Trust 80Quality 89productivity
  • Towhee3.4K stars

    Towhee is a framework that is dedicated to making neural data processing pipelines simple and fast.

    Trust 82Quality 70robotics-iot
  • Crnn2.1K stars

    Convolutional Recurrent Neural Network (CRNN) for image-based sequence recognition.

    Trust 79Quality 68document-processing

Slides and decks

PPT and presentation skills

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

  • Neuralangelo4.6K stars

    Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

    Trust 76Quality 66robotics-iot
  • Kill Ai Slop786 stars

    A field guide to the visual & copy tics of AI-generated products — and an Agent Skill that scans your project…

    Trust 87Quality 95design-creative

Prompts, B-roll, explainers

Video creation skills

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

  • Claude AI skill for cinematic Higgsfield AI prompts — 20 sub-skills covering Cinema Studio 2.5/3.0/3.5, MCSLA…

    Trust 78Quality 76media-automation
  • 10 Claude skills that generate studio-quality AI video prompts for Seedance 2.0 on Higgsfield. Viral hooks, S…

    Trust 78Quality 70media-automation
  • Cnn Explainer9.0K stars

    Learning Convolutional Neural Networks with Interactive Visualization.

    Trust 79Quality 74ml-automation

Images, video, UI

Design and creative skills

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

  • Audio Webui1.2K stars

    A webui for different audio related Neural Networks

    Trust 79Quality 65media-automation
  • Neural Amp Modeler LV2 plugin

    Trust 77Quality 75ml-automation
  • Keras Vis3.0K stars

    Neural network visualization toolkit for keras

    Trust 77Quality 69ml-automation

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

208

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

208 quality191 maintained

Research

Research and knowledge work

83

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

83 quality74 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

10

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

10 quality10 maintained

Design

Design and creative production

94

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

94 quality69 maintained

Data

Data, BI, and analytics

35

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

35 quality34 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

3

Football data, World Cup dashboards, xG, match prediction, scouting, and sports analytics.

3 quality3 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 455 ranked candidates matching "neural-radiance-field"

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

1

Neuralforecast

VERIFIEDEXCELLENT · 99TRUST · 86SAFE · REVIEWEDDESIGN

Scalable and user friendly neural :brain: forecasting algorithms.

$ npx skills add Nixtla/neuralforecast
4.2K stars67 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 Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by NixtlaDetailsQuick view
2

AlphaTree Graphic Deep Neural Network

VERIFIEDEXCELLENT · 89TRUST · 83SAFE · REVIEWEDDESIGN

AI Roadmap:机器学习(Machine Learning)、深度学习(Deep Learning)、对抗神经网络(GAN),图神经网络(GNN),NLP,大数据相关的发展路书(roadmap), 并附海量源码(python,pytorch)带大家消化基本知识点,突破面试,完成从新手到合格工程师的跨越,其中深度学习相关论文附有te…

$ npx skills add weslynn/AlphaTree-graphic-deep-neural-network
3.0K stars63 quality83 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: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

CLI + Codex · 4 targets

machine-learning
by weslynnDetailsQuick view
3

Neuralangelo

VERIFIEDPROMISING · 66TRUST · 76SAFE · EXPERIMENTALCODING

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

$ npx skills add NVlabs/neuralangelo
4.6K stars52 quality76 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: License is unclear
Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario GitHub automation

CLI + Codex · 4 targets

pythoncomputer-vision
by NVlabsDetailsQuick view
4

Neuralcoref

VERIFIEDPROMISING · 69TRUST · 78SAFE · REVIEWEDDESIGN

✨Fast Coreference Resolution in spaCy with Neural Networks

$ npx skills add huggingface/neuralcoref
2.9K stars51 quality78 trustReviewed with permission notes3y 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

cmachine-learning
by huggingfaceDetailsQuick view
5

Neural Photo Editor

VERIFIEDPROMISING · 68TRUST · 77SAFE · REVIEWEDCODING

A simple interface for editing natural photos with generative neural networks.

$ npx skills add ajbrock/Neural-Photo-Editor
2.1K stars50 quality77 trustReviewed with permission notes9y 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 ajbrockDetailsQuick view
6

PyNeuraLogic

STRONG · 73TRUST · 76SAFE · REVIEWEDDESIGN

PyNeuraLogic lets you use Python to create Differentiable Logic Programs

$ npx skills add LukasZahradnik/PyNeuraLogic
309 stars51 quality76 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 Multimodal media

CLI + Codex · 4 targets

pythonmachine-learning
by LukasZahradnikDetailsQuick view
7

GraphNeuralNetworks.Jl

STRONG · 73TRUST · 77SAFE · REVIEWEDDESIGN

Graph Neural Networks in Julia

$ npx skills add JuliaGraphs/GraphNeuralNetworks.jl
302 stars51 quality77 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 Multimodal media

CLI + Codex · 4 targets

juliamachine-learning
by JuliaGraphsDetailsQuick view
8

Halfrost Field

VERIFIEDSTRONG · 77TRUST · 80SAFE · REVIEWEDDESIGN

✍🏻 这里是写博客的地方 —— Halfrost-Field 冰霜之地

$ npx skills add halfrost/Halfrost-Field
13.2K stars57 quality80 trustReviewed with permission notes3y 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

gomachine-learning
by halfrostDetailsQuick view
9

Agentfield

VERIFIEDEXCELLENT · 99TRUST · 87SAFE · REVIEWEDRESEARCH

Build, run and scale AI agents like API and microservices - observable,auditable and identity-aware from day one.

$ npx skills add Agent-Field/agentfield
2.3K stars65 quality87 trustReviewed with permission notes23d 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 RAG and knowledge

CLI + Codex · 4 targets

gorag
by Agent-FieldDetailsQuick view
10

Fieldtheory Cli

VERIFIEDEXCELLENT · 95TRUST · 82SAFE · REVIEWEDRESEARCH

Field Theory CLI for bookmarks, Library, commands, and agent workflows

$ npx skills add afar1/fieldtheory-cli
1.9K 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 Document processing

CLI + Codex · 4 targets

typescriptmarkdown
by afar1DetailsQuick view
11

Neural Prophet

VERIFIEDSTRONG · 71TRUST · 80SAFE · REVIEWEDDESIGN

NeuralProphet: A simple forecasting package

$ npx skills add ourownstory/neural_prophet
4.3K stars52 quality80 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 ourownstoryDetailsQuick view
12

Higgsfield

VERIFIEDSTRONG · 70TRUST · 80SAFE · REVIEWEDDESIGN

Fault-tolerant, highly scalable GPU orchestration, and a machine learning framework designed for training models with billions to trillions of parameters

$ npx skills add higgsfield-ai/higgsfield
3.8K stars52 quality80 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 Design and creative

CLI + Codex · 4 targets

jupyter-notebookmachine-learning
by higgsfield-aiDetailsQuick view
13

NeuralNote

VERIFIEDPROMISING · 69TRUST · 79SAFE · REVIEWEDDESIGN

Audio Plugin for Audio to MIDI transcription using deep learning.

$ npx skills add DamRsn/NeuralNote
2.8K stars51 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 Multimodal media

CLI + Codex · 4 targets

c++machine-learning
by DamRsnDetailsQuick view
14

Neural Amp Modeler Lv2

STRONG · 75TRUST · 77SAFE · REVIEWEDDESIGN

Neural Amp Modeler LV2 plugin

$ npx skills add mikeoliphant/neural-amp-modeler-lv2
472 stars52 quality77 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 Multimodal media

CLI + Codex · 4 targets

c++machine-learning
by mikeoliphantDetailsQuick view
15

Cs Field Guide

STRONG · 74TRUST · 78SAFE · REVIEWEDEDUCATION

A free online interactive resource/textbook for high school students learning about computer science.

$ npx skills add uccser/cs-field-guide
373 stars52 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

javascripteducation
by uccserDetailsQuick view
16

Higgsfield AI Prompt Skill

STRONG · 76TRUST · 78SAFE · REVIEWEDDESIGN

Claude AI skill for cinematic Higgsfield AI prompts — 20 sub-skills covering Cinema Studio 2.5/3.0/3.5, MCSLA formula, Soul ID character consistency, Seedance 2.0 prompt…

$ npx skills add OSideMedia/higgsfield-ai-prompt-skill
147 stars49 quality78 trustReviewedClaude Code2mo 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 Video creation

Claude Code + CLI · 4 targets

pythonvideo-generation
by OSideMediaDetailsQuick 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