Star0

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
80
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.

Codex, Claude Code, Cursor

Coding agent skills

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

  • Planning With Files25K stars

    Persistent file-based planning for AI coding agents and long-running agentic tasks. Crash-proof markdown plan…

    Trust 91Quality 100agent-skills
  • David Ondrej Skills968 stars

    Official Agent Skills for coding agents, research, workflow orchestration, docs, ops, and skill authoring.

    Trust 81Quality 100Agent Skills
  • Open Design76K stars

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

    Trust 94Quality 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 90Quality 100document-processing
  • Quarkdown16K stars

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

    Trust 93Quality 100document-processing
  • Logseq44K stars

    A privacy-first, open-source platform for knowledge management and collaboration. Download link: http://githu…

    Trust 92Quality 100rag-knowledge

Markets and quant

Finance and trading skills

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

  • Serenity Skill12K stars

    Stock analysis skill for market research and financial reasoning workflows.

    Trust 78Quality 100Finance
  • OpenBB46K stars

    Open-source investment research platform for financial analysis agents.

    Trust 78Quality 100Finance
  • Daily Stock Analysis52K stars

    LLM驱动的 A/H/美股智能分析：多数据源行情 + 实时新闻 + LLM决策仪表盘 + 多渠道推送，零成本定时运行，纯白嫖. LLM-powered stock analysis system for A/H/US…

    Trust 94Quality 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 91Quality 100agent-frameworks
  • Maxun16K stars

    🔥 The open-source no-code platform for web scraping, crawling, search and AI data extraction • Turn websites…

    Trust 93Quality 100web-automation
  • Scrapegraph AI27K stars

    Python scraper based on AI

    Trust 90Quality 100web-automation

Slides and decks

PPT and presentation skills

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

  • Ppt Master37K stars

    AI generates a real, editable PowerPoint from any document — native shapes & animations, speaker notes voiced…

    Trust 93Quality 100agent-frameworks
  • Guizang Ppt Skill17K stars

    AI-agent Skill for generating polished HTML slide decks: editorial magazine and Swiss layouts, image prompts,…

    Trust 92Quality 100agent-skills
  • Slidev47K stars

    Presentation Slides for Developers

    Trust 90Quality 100document-processing

Images, video, UI

Design and creative skills

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

  • Seedance 2.0 Skill OS796 stars

    Direct the model. Do not micro-manage the frame.

    Trust 80Quality 100Creative
  • Diffusers34K stars

    🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

    Trust 94Quality 100media-automation
  • Pixelle Video23K stars

    🚀 AI 全自动短视频引擎 | AI Fully Automated Short Video Engine

    Trust 92Quality 100media-automation

Analysis and pipelines

Data and analytics skills

Data analysis, analytics, ETL, notebooks, databases, tables, charts, and reporting workflows.

  • Dataease24K stars

    🔥 人人可用的开源 BI 工具，数据可视化神器。An open-source BI tool alternative to Tableau.

    Trust 92Quality 100data-analysis
  • Chartdb22K stars

    Database diagrams editor that allows you to visualize and design your DB with a single query.

    Trust 92Quality 100data-analysis
  • Airflow46K stars

    Apache Airflow - A platform to programmatically author, schedule, and monitor workflows

    Trust 94Quality 100data-analysis

SEO and content

Marketing and growth skills

SEO, content research, growth workflows, social listening, campaign analysis, and publishing helpers.

  • Aaron Marketing Skills2.3K stars

    120 marketing skills for SEO/GEO, influencer, paid ads, email, launch, organic social, and brand narrative ag…

    Trust 81Quality 100Marketing
  • Umami37K stars

    Umami is a modern, privacy-focused analytics platform. An open-source alternative to Google Analytics, Mixpan…

    Trust 94Quality 100growth-marketing
  • Analytics27K stars

    Open source, privacy-first web analytics. Lightweight, cookie-free Google Analytics alternative. Self-hosted…

    Trust 93Quality 100growth-marketing

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

458

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

457 quality455 maintained

Research

Research and knowledge work

110

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

110 quality110 maintained

Presentation

Presentation and deck workflows

8

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

8 quality8 maintained

Finance

Finance and quant workflows

27

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

27 quality27 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

24

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

24 quality24 maintained

Data

Data, BI, and analytics

77

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

77 quality77 maintained

Legal

Legal, policy, and compliance

25

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

25 quality25 maintained

Education

Education and tutoring

1

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

1 quality1 maintained

World Cup

Football and World Cup analytics

1

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

1 quality1 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 727 ranked candidates matching "fine-tuning"

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

1

Llama Cookbook

VERIFIEDEXCELLENT · 100TRUST · 92SAFE · VERIFIEDCODING

Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started with Inference, Fine-Tuning, RAG. We also show you how to solve end to e…

$ npx skills add meta-llama/llama-cookbook
18.4K stars73 quality92 trustVerifiedClaude Code + LangChain2mo 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/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Coding agents

Claude Code + LangChain · 4 targets

jupyter-notebookmachine-learning
by meta-llamaDetailsQuick view
2

Easy Dataset

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDCODING

A powerful tool for creating datasets for LLM fine-tuning 、RAG and Eval

$ npx skills add ConardLi/easy-dataset
14.5K stars69 quality88 trustReviewedClaude Code2mo 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

javascriptrag
by ConardLiDetailsQuick view
3

H2o Llmstudio

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · VERIFIEDCODING

H2O LLM Studio - a framework and no-code GUI for fine-tuning LLMs. Documentation: https://docs.h2o.ai/h2o-llmstudio/

$ npx skills add h2oai/h2o-llmstudio
5.0K stars68 quality90 trustVerifiedClaude 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/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

pythonchatbot
by h2oaiDetailsQuick view
4

SimpleTuner

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · VERIFIEDDESIGN

A general fine-tuning kit geared toward image/video/audio diffusion models.

$ npx skills add bghira/SimpleTuner
2.9K stars66 quality89 trustVerifiedClaude Code17d 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/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Multimodal media

Claude Code + CLI · 4 targets

pythonmachine-learning
by bghiraDetailsQuick view
5

Trainer

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · VERIFIEDCODING

Distributed AI Model Training and LLM Fine-Tuning on Kubernetes

$ npx skills add kubeflow/trainer
2.1K stars65 quality89 trustVerifiedClaude Code21d 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/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Coding agents

Claude Code + CLI · 4 targets

gokubernetes
by kubeflowDetailsQuick view
6

Second Brain AI Assistant Course

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · VERIFIEDCODING

Learn to build your Second Brain AI assistant with LLMs, agents, RAG, fine-tuning, LLMOps and AI systems techniques.

$ npx skills add decodingai-magazine/second-brain-ai-assistant-course
2.8K stars63 quality88 trustVerifiedClaude Code + OpenAI Agents3mo 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/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

jupyter-notebookllmops
by decodingai-magazineDetailsQuick view
7

Mlx Tune

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · VERIFIEDDESIGN

Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.

$ npx skills add ARahim3/mlx-tune
1.3K stars64 quality89 trustVerifiedClaude Code14d 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/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Multimodal media

Claude Code + CLI · 4 targets

pythonspeech
by ARahim3DetailsQuick view
8

DB GPT Hub

VERIFIEDSTRONG · 77TRUST · 82SAFE · EXPERIMENTALCODING

A repository that contains models, datasets, and fine-tuning techniques for DB-GPT, with the purpose of enhancing model performance in Text-to-SQL

$ npx skills add eosphoros-ai/DB-GPT-Hub
2.0K stars54 quality82 trustExperimentalClaude Code + OpenAI Agents1y 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 gateSparse or mixed signals. Useful for discovery, but not for autonomous installation.

Scenario GitHub automation

Claude Code + OpenAI Agents · 4 targets

pythonsql
by eosphoros-aiDetailsQuick view
9

RAG FiT

EXCELLENT · 86TRUST · 82SAFE · REVIEWEDRESEARCH

Framework for enhancing LLMs for RAG tasks using fine-tuning.

$ npx skills add IntelLabs/RAG-FiT
770 stars54 quality82 trustReviewedClaude Code29d 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: Quality score needs review
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario RAG and knowledge

Claude Code + CLI · 4 targets

pythonsemantic-search
by IntelLabsDetailsQuick view
10

Pmetal

STRONG · 74TRUST · 77SAFE · REVIEWEDFINANCE

PMetal: high-performance Apple Silicon framework for local LLM inference, LoRA/QLoRA fine-tuning, serving, quantization, and MLX/Metal acceleration.

$ npx skills add Epistates/pmetal
297 stars51 quality77 trustReviewed with permission notesClaude Code1mo 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: License is unclear
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Finance and quant

Claude Code + CLI · 4 targets

rustmachine-learning
by EpistatesDetailsQuick view
11

ReinFlow

STRONG · 76TRUST · 80SAFE · REVIEWEDCODING

[NeurIPS 2025] Flow x RL. "ReinFlow: Fine-tuning Flow Policy with Online Reinforcement Learning". Support VLAs e.g., Pi0, Pi0.5, GR00TN1.5. Fully open-sourced.

$ npx skills add ReinFlow/ReinFlow
337 stars48 quality80 trustReviewed with permission notesClaude 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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Coding agents

Claude Code + CLI · 4 targets

pythonrobotics
by ReinFlowDetailsQuick view
12

Rapidfireai

STRONG · 79TRUST · 80SAFE · REVIEWEDRESEARCH

RapidFire AI: Rapid AI Customization from RAG to Fine-Tuning

$ npx skills add RapidFireAI/rapidfireai
165 stars49 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 RAG and knowledge

Claude Code + CLI · 4 targets

javascriptrag
by RapidFireAIDetailsQuick view
13

Unsloth

VERIFIEDEXCELLENT · 100TRUST · 94SAFE · VERIFIEDCODING

Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.

$ npx skills add unslothai/unsloth
67.0K stars77 quality94 trustVerifiedClaude Code + OpenAI Agents17d 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/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

pythonvoice
by unslothaiDetailsQuick view
14

Llama Index

VERIFIEDEXCELLENT · 100TRUST · 92SAFE · VERIFIEDDATA

LlamaIndex is the leading document agent and OCR platform

$ npx skills add run-llama/llama_index
50.2K stars76 quality92 trustVerifiedClaude Code + LlamaIndex20d 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/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario RAG and knowledge

Claude Code + LlamaIndex · 4 targets

pythonrag
by run-llamaDetailsQuick view
15

OpenLLM

VERIFIEDEXCELLENT · 100TRUST · 91SAFE · VERIFIEDCODING

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

$ npx skills add bentoml/OpenLLM
12.4K stars72 quality91 trustVerifiedClaude Code + OpenAI Agents15d 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/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Coding agents

Claude Code + OpenAI Agents · 4 targets

pythonllmops
by bentomlDetailsQuick view
16

Rf Detr

VERIFIEDEXCELLENT · 100TRUST · 92SAFE · VERIFIEDDESIGN

RF-DETR is a real-time object detection and segmentation model architecture developed by Roboflow, SOTA on COCO, designed for fine-tuning. [ICLR 2026]

$ npx skills add roboflow/rf-detr
7.8K stars69 quality92 trustVerifiedClaude Code21d 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/…
Safety gateStrong metadata, audit, install, and review signals. Suitable for agent shortlists after normal workspace review.

Scenario Multimodal media

Claude Code + CLI · 4 targets

pythonmachine-learning
by roboflowDetailsQuick 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