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.

  • Agentic, long-horizon visual generation: a fuzzy story → a cross-model-audited image-based movie. Brings ARIS…

    Trust 77Quality 77utility
  • A Claude Code skill that removes signs of AI-generated writing from academic medical papers, making them soun…

    Trust 75Quality 64development
  • Last-night exam-cram coach as a Claude Agent Skill: turns your slides, notes and past papers into a chaptered…

    Trust 85Quality 91productivity

Codex, Claude Code, Cursor

Coding agent skills

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

  • 本仓库包含三个面向学术科研人员的Skills,覆盖从文献阅读、论文写作到科学计算的完整研究工作流。office-academic-skill 负责论文阅读报告与学术 PPT/Word 文档生成;research-wri…

    Trust 81Quality 79development
  • Engineering Figure Banana is a Codex skill for generating publication-style engineering and computer science…

    Trust 78Quality 72development
  • Speaker261 stars

    Speaker is a Codex skill project for academic presentations: read real.pptx, combine text extraction, PPTX st…

    Trust 74Quality 73development

Documents and knowledge

Research and RAG skills

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

  • Quarkdown16K stars

    🪐 Markdown with superpowers: from ideas to papers, presentations, websites, books, and knowledge bases.

    Trust 89Quality 100document-processing
  • Graphify91K stars

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

    Trust 87Quality 100rag-knowledge
  • KG LLM Papers2.2K stars

    [Paper List] Papers integrating knowledge graphs (KGs) and large language models (LLMs)

    Trust 86Quality 89rag-knowledge

Markets and quant

Finance and trading skills

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

  • Blockchain1.2K stars

    Compilation of useful documents and scientific papers about Blockchain & cryptocurrencies.

    Trust 76Quality 60web3-analytics

Crawlers and extraction

Web scraping skills

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

  • Sioyek9.6K stars

    Sioyek is a PDF viewer with a focus on textbooks and research papers

    Trust 86Quality 100document-processing
  • OpenOCR1.4K stars

    OpenOCR: An Open-Source Toolkit for General-OCR Research and Applications, integrates a unified training and…

    Trust 86Quality 97document-processing
  • MathTranslate1.4K stars

    translate scientific papers in latex, especially arxiv papers

    Trust 81Quality 79document-processing

Slides and decks

PPT and presentation skills

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

  • Slides_maker342 stars

    Turn papers, code, and docs into presentation-ready, natively editable PPTX in Codex / Claude Code. Native ch…

    Trust 80Quality 77presentation
  • Aut Sci Write149 stars

    Academic research skills suite for Claude Code — literature search (arXiv+PubMed+WoS), PDF extraction, figure…

    Trust 74Quality 65presentation-generation
  • Colloquium222 stars

    A markdown native slides tool for academics building with agents.

    Trust 78Quality 75education

Prompts, B-roll, explainers

Video creation skills

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

  • Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /intervie…

    Trust 78Quality 82media-automation
  • awesome grounding: A curated list of research papers in visual grounding

    Trust 82Quality 78research

Images, video, UI

Design and creative skills

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

  • Annotations of the interesting ML papers I read

    Trust 76Quality 73ml-automation
  • Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!

    Trust 88Quality 95ml-automation
  • 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformer…

    Trust 87Quality 100ml-automation

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

196

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

196 quality187 maintained

Research

Research and knowledge work

128

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

128 quality110 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

14

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

14 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

62

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

62 quality53 maintained

Data

Data, BI, and analytics

33

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

33 quality32 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

7

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

7 quality7 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 265 ranked candidates matching "academic-papers"

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

1

Qinyan Academic Skills

STRONG · 79TRUST · 80SAFE · REVIEWEDRESEARCH

沁言学术科研论文Skills库 - 177个学术研究Agent Skills的综合集合,涵盖论文检索、科学写作、生物信息、药物发现、临床医学等17个分类

$ npx skills add LeonChaoX/qinyan-academic-skills
656 stars53 quality80 trustReviewedClaude Code18d 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 Research agents

Claude Code + CLI · 4 targets

pythonresearch
by LeonChaoXDetailsQuick view
2

Findpapers

STRONG · 74TRUST · 76SAFE · REVIEWEDRESEARCH

Findpapers: A tool for helping researchers who are looking for related works

$ npx skills add jonatasgrosman/findpapers
366 stars52 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 Research agents

CLI + Codex · 4 targets

pythonresearch
by jonatasgrosmanDetailsQuick view
3

Academic Research Skills

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDRESEARCH

Academic Research Skills for Claude Code: research → write → review → revise → finalize

$ npx skills add Imbad0202/academic-research-skills
38.4K stars75 quality88 trustReviewedClaude Code16d 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 Research agents

Claude Code + CLI · 4 targets

pythonresearch
by Imbad0202DetailsQuick view
4

Academic Research Skills Codex

VERIFIEDEXCELLENT · 93TRUST · 84SAFE · REVIEWEDRESEARCH

Codex-native Academic Research Skills suite for human-in-the-loop academic research workflows

$ npx skills add Imbad0202/academic-research-skills-codex
3.8K stars67 quality84 trustReviewedClaude Code + OpenAI 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: License is unclear
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Research agents

Claude Code + OpenAI Agents · 4 targets

pythonresearch
by Imbad0202DetailsQuick view
5

Chatgpt Prompts For Academic Writing

VERIFIEDPROMISING · 66TRUST · 76SAFE · EXPERIMENTALRESEARCH

This list of writing prompts covers a range of topics and tasks, including brainstorming research ideas, improving language and style, conducting literature reviews, and…

$ npx skills add ahmetbersoz/chatgpt-prompts-for-academic-writing
4.7K stars52 quality76 trustExperimentalOpenAI Agents3y 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 Research agents

OpenAI Agents + CLI · 4 targets

research
by ahmetbersozDetailsQuick view
6

Opendraft

STRONG · 70TRUST · 77SAFE · REVIEWEDRESEARCH

Open-source AI thesis writer with 19 specialized agents. Generate 20k+ word research drafts in 10 minutes. FREE (Gemini). Verified citations from 500M+ papers. Export PD…

$ npx skills add federicodeponte/opendraft
144 stars49 quality77 trustReviewed with permission notesOpenAI Agents1mo 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

OpenAI Agents + CLI · 4 targets

pythonresearch
by federicodeponteDetailsQuick view
7

Paperscraper

STRONG · 75TRUST · 79SAFE · REVIEWEDRESEARCH

Tools to scrape publications & their metadata from pubmed, arxiv, medrxiv, biorxiv and chemrxiv.

$ npx skills add jannisborn/paperscraper
528 stars53 quality79 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

pythonresearch
by jannisbornDetailsQuick view
8

Academic File Converter

STRONG · 74TRUST · 74SAFE · EXPERIMENTALRESEARCH

📚 Import Bibtex publications and Jupyter Notebook blog posts into your Markdown website or book. 将Bibtex转换为Markdown网站

$ npx skills add HugoBlox/academic-file-converter
418 stars52 quality74 trustExperimental1mo 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 Document processing

CLI + Codex · 4 targets

pythonmarkdown
by HugoBloxDetailsQuick view
9

Codex Academic Skills

PROMISING · 69TRUST · 78SAFE · REVIEWEDRESEARCH

A curated list of research-oriented skills usable in OpenAI Codex, covering writing, literature review, evaluation, and research workflows.

$ npx skills add Epsilon617/Codex-Academic-Skills
118 stars48 quality78 trustReviewed with permission notesClaude Code + OpenAI Agents2mo 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 Research agents

Claude Code + OpenAI Agents · 4 targets

pythonresearch
by Epsilon617DetailsQuick view
10

KG LLM Papers

VERIFIEDEXCELLENT · 89TRUST · 86SAFE · REVIEWEDRESEARCH

[Paper List] Papers integrating knowledge graphs (KGs) and large language models (LLMs)

$ npx skills add zjukg/KG-LLM-Papers
2.2K stars58 quality86 trustReviewedOpenAI Agents5mo 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

OpenAI Agents + CLI · 4 targets

knowledge-graph
by zjukgDetailsQuick view
11

Arxiv Vanity

VERIFIEDPROMISING · 66TRUST · 79SAFE · EXPERIMENTALRESEARCH

Renders papers from arXiv as responsive web pages so you don't have to squint at a PDF.

$ npx skills add arxiv-vanity/arxiv-vanity
1.6K stars49 quality79 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: Repository looks stale
Safety gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario RAG and knowledge

CLI + Codex · 4 targets

pythonresearch
by arxiv-vanityDetailsQuick view
12

Must Read Papers For Ml

VERIFIEDPROMISING · 66TRUST · 79SAFE · REVIEWEDDATA

Collection of must read papers for Data Science, or Machine Learning / Deep Learning Engineer

$ npx skills add hurshd0/must-read-papers-for-ml
1.4K stars49 quality79 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 Data analysis

CLI + Codex · 4 targets

data-analysis
by hurshd0DetailsQuick view
13

Open Webui Tools

STRONG · 83TRUST · 81SAFE · REVIEWEDRESEARCH

Open‑WebUI Tools is a modular toolkit designed to extend and enrich your Open WebUI instance, turning it into a powerful AI workstation. With a suite of over 15 speciali…

$ npx skills add Haervwe/open-webui-tools
751 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 Research agents

CLI + Codex · 4 targets

pythonresearch
by HaervweDetailsQuick view
14

Research Claw

STRONG · 73TRUST · 78SAFE · REVIEWEDRESEARCH

A self-hosted AI assistant for academic research — manages your papers, searches literature, tracks deadlines, and answers you on the channels you already use.

$ npx skills add nanoAgentTeam/research-claw
292 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 Research agents

CLI + Codex · 4 targets

pythonresearch
by nanoAgentTeamDetailsQuick view
15

Papers

STRONG · 70TRUST · 74SAFE · EXPERIMENTALRESEARCH

Command-line tool to manage bibliography (pdfs + bibtex)

$ npx skills add perrette/papers
156 stars49 quality74 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 Document processing

CLI + Codex · 4 targets

pythonpdf
by perretteDetailsQuick view
16

Paperseek

PROMISING · 69TRUST · 78SAFE · REVIEWEDRESEARCH

LLM based Literature Search Agent. 一个面向研究者的文献发现工具,支持用自然语言发起检索、自动迭代查询、扩展候选论文、排序结果并导出可复核的文献列表。

$ npx skills add MingfengHong/paperseek
125 stars48 quality78 trustReviewed with permission notes1mo 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 Research agents

CLI + Codex · 4 targets

pythonresearch
by MingfengHongDetailsQuick 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