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.

  • Reviews animation and motion code against a high craft bar derived from Emil Kowalski's design engineering ph…

    Trust 91Quality 100design-creative
  • FLUX, Stable Diffusion, SDXL, SD3, LoRA, Fine Tuning, DreamBooth, Training, Automatic1111, Forge WebUI, Swarm…

    Trust 88Quality 100education
  • fast-stable-diffusion + DreamBooth

    Trust 84Quality 86data-analysis

Codex, Claude Code, Cursor

Coding agent skills

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

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

    Trust 91Quality 100design-creative
  • Skills377 stars

    Agent Skills for VueUse

    Trust 81Quality 92coding-agents
  • Openclip519 stars

    OpenClip - AI-powered highlight extraction for long videos (AI 驱动的长视频精彩时刻提取工具)

    Trust 79Quality 72agent-skills

Documents and knowledge

Research and RAG skills

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

  • Queryable3.0K stars

    Run OpenAI's CLIP and Apple's MobileCLIP model on iOS to search photos.

    Trust 84Quality 90rag-knowledge
  • UForm1.2K stars

    Pocket-Sized Multimodal AI for content understanding and generation across multilingual texts, images, and 🔜…

    Trust 84Quality 78rag-knowledge
  • Md Editor V32.5K stars

    Markdown editor for vue3, developed in jsx and typescript, dark theme、beautify content by prettier、render art…

    Trust 87Quality 96document-processing

Markets and quant

Finance and trading skills

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

  • Exchange Core2.6K stars

    Ultra-fast matching engine written in Java based on LMAX Disruptor, Eclipse Collections, Real Logic Agrona, O…

    Trust 78Quality 68finance

Crawlers and extraction

Web scraping skills

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

  • AI Crawler Py3.1K stars

    Crawl a website starting from a URL, find relevant pages, and extract data – all guided by your natural langu…

    Trust 80Quality 85agent-frameworks
  • LLMFeeder423 stars

    Brower extension to convert web pages to clean Markdown and copy to clipboard so you can feed it to your favo…

    Trust 77Quality 74coding-agents
  • Capcap552 stars

    ⌘⌘ - A lightweight, native macOS screenshot tool that lives in your menu bar. Double-tap ⌘ Command to capture…

    Trust 79Quality 76document-processing

Slides and decks

PPT and presentation skills

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

  • Deck1.3K stars

    Deck is a modern, native, privacy-first clipboard manager for macOS.

    Trust 82Quality 85productivity-automation

Prompts, B-roll, explainers

Video creation skills

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

  • OpenClaw/Codex Skill: Auto video editing for talk/vlog videos — speech recognition, sentence splitting, subti…

    Trust 81Quality 83media
  • Sana8.3K stars

    SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

    Trust 89Quality 100media-automation
  • TurboDiffusion3.5K stars

    TurboDiffusion: 100–200× Acceleration for Video Diffusion Models

    Trust 84Quality 95media-automation

Images, video, UI

Design and creative skills

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

  • Visual Skills118 stars

    AI film director skills for Claude agents: cinematic dramaturgy (Murch, blocking, montage) + exact prompt syn…

    Trust 84Quality 88design-creative
  • Diffusers34K stars

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

    Trust 90Quality 100media-automation
  • Inpaint Anything extension performs stable diffusion inpainting on a browser UI using masks from Segment Anyt…

    Trust 80Quality 65media-automation

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

204

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

203 quality194 maintained

Research

Research and knowledge work

79

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

79 quality76 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

14

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

14 quality13 maintained

Marketing

Marketing and growth automation

11

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

11 quality11 maintained

Design

Design and creative production

101

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

101 quality76 maintained

Data

Data, BI, and analytics

35

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

35 quality33 maintained

Legal

Legal, policy, and compliance

11

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

11 quality11 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

Decision filters

Choose by scenario, quality, and trust signals.

Showing 1-16 of 453 ranked candidates matching "clip-guided-diffusion"

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

1

Vox Director

VERIFIEDEXCELLENT · 100TRUST · 81SAFE · REVIEWEDDESIGN

Turn one topic into a narrated Vox-style paper-collage explainer or ad video, from script through captions.

$ npx skills add Alisa0808/vox-director --skill vox-director
326 stars88 quality81 trustReviewedClaude Code + OpenAI Agents18d since pushSafe to try1.0K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Uses external video and media providers; review provider cost, account, and con…
TrustGood trust signals with a few areas worth checking before rollout.Review: Uses external video and media providers; review provider cost, account, and con…
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Video creation

Claude Code + OpenAI Agents · 4 targets

claude-codecodexcursorffmpeg
by Alisa0808DetailsQuick view
2

Seedance 2.0 Prompt Writing

VERIFIEDEXCELLENT · 100TRUST · 84SAFE · REVIEWEDDESIGN

Write precise Seedance 2.0 prompts for multimodal video, camera movement, editing, music, and product storytelling.

$ npx skills add dexhunter/seedance2-skill --skill seedance-prompt-en
2.9K stars91 quality84 trustReviewedClaude Code + OpenAI Agents6mo since pushSafe to try3.5K installs
QualityHigh-confidence pick with strong adoption and healthy maintenance signals.Check: Model capabilities, asset limits, and platform rules can change; verify them be…
TrustGood trust signals with a few areas worth checking before rollout.Review: Model capabilities, asset limits, and platform rules can change; verify them be…
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Video creation

Claude Code + OpenAI Agents · 4 targets

claude-codecodexcursorseedance-2.0
by dexhunterDetailsQuick view
3

Stable Diffusion Webui

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDDESIGN

Stable Diffusion web UI

$ npx skills add AUTOMATIC1111/stable-diffusion-webui
163.7K stars71 quality87 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 Multimodal media

CLI + Codex · 4 targets

pythonimage-generation
by AUTOMATIC1111DetailsQuick view
4

Stable Diffusion.Cpp

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDDESIGN

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

$ npx skills add leejet/stable-diffusion.cpp
6.3K stars68 quality87 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 Design and creative

CLI + Codex · 4 targets

c++image-generation
by leejetDetailsQuick view
5

Clipboard

VERIFIEDEXCELLENT · 97TRUST · 83SAFE · REVIEWEDCODING

😎🏖️🐬 Your new, 𝙧𝙞𝙙𝙤𝙣𝙠𝙪𝙡𝙞𝙘𝙞𝙤𝙪𝙨𝙡𝙮 smart clipboard manager

$ npx skills add Slackadays/Clipboard
5.8K stars65 quality83 trustReviewed with permission notes3mo 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 Coding agents

CLI + Codex · 4 targets

c++productivity
by SlackadaysDetailsQuick view
6

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
7

Clip Retrieval

VERIFIEDEXCELLENT · 94TRUST · 84SAFE · REVIEWEDRESEARCH

Easily compute clip embeddings and build a clip retrieval system with them

$ npx skills add rom1504/clip-retrieval
2.8K stars63 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 RAG and knowledge

CLI + Codex · 4 targets

jupyter-notebooksemantic-search
by rom1504DetailsQuick view
8

Custom Diffusion

VERIFIEDEXCELLENT · 90TRUST · 84SAFE · REVIEWEDRESEARCH

Custom Diffusion: Multi-Concept Customization of Text-to-Image Diffusion (CVPR 2023)

$ npx skills add adobe-research/custom-diffusion
2.0K stars65 quality84 trustReviewed2mo 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

CLI + Codex · 4 targets

pythoncomputer-vision
by adobe-researchDetailsQuick view
9

Stable Diffusion Videos

VERIFIEDSTRONG · 84TRUST · 84SAFE · REVIEWEDDESIGN

Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts

$ npx skills add nateraw/stable-diffusion-videos
4.7K stars56 quality84 trustReviewed8mo 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: 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 naterawDetailsQuick view
10

ClipCascade

VERIFIEDEXCELLENT · 92TRUST · 85SAFE · REVIEWEDDESIGN

ClipCascade is a lightweight utility that automatically syncs the clipboard across devices, no key press required.

$ npx skills add Sathvik-Rao/ClipCascade
1.8K stars61 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 Design and creative

CLI + Codex · 4 targets

pythonproductivity
by Sathvik-RaoDetailsQuick view
11

Multidiffusion Upscaler For Automatic1111

VERIFIEDPROMISING · 66TRUST · 78SAFE · REVIEWEDDESIGN

Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0

$ npx skills add pkuliyi2015/multidiffusion-upscaler-for-automatic1111
5.0K stars53 quality78 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: License is unclear
Safety gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Multimodal media

CLI + Codex · 4 targets

pythonimage-generation
by pkuliyi2015DetailsQuick view
12

Dreambooth Stable Diffusion

VERIFIEDPROMISING · 69TRUST · 80SAFE · REVIEWEDDESIGN

Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) by way of Textual Inversion (https://arxiv.org/abs/2208.01618) for Stable Diffusion (https://arxiv.org/ab…

$ npx skills add JoePenna/Dreambooth-Stable-Diffusion
3.2K stars51 quality80 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

jupyter-notebookmachine-learning
by JoePennaDetailsQuick view
13

Diffusiondb

VERIFIEDPROMISING · 66TRUST · 77SAFE · EXPERIMENTALCODING

A large-scale text-to-image prompt gallery dataset based on Stable Diffusion

$ npx skills add poloclub/diffusiondb
1.4K stars49 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

pythoncomputer-vision
by poloclubDetailsQuick view
14

Stable Diffusion Prompt Reader

VERIFIEDPROMISING · 66TRUST · 79SAFE · REVIEWEDDESIGN

A simple standalone viewer for reading prompts from Stable Diffusion generated image outside the webui.

$ npx skills add receyuki/stable-diffusion-prompt-reader
1.3K stars49 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

pythonimage-generation
by receyukiDetailsQuick view
15

CLIP

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDDESIGN

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

$ npx skills add openai/CLIP
33.8K stars72 quality89 trustReviewed4mo 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

jupyter-notebookmachine-learning
by openaiDetailsQuick view
16

Stable Diffusion Webui Colab

VERIFIEDEXCELLENT · 91TRUST · 85SAFE · REVIEWEDDESIGN

stable diffusion webui colab

$ npx skills add camenduru/stable-diffusion-webui-colab
15.9K stars62 quality85 trustReviewed8mo 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

jupyter-notebookimage-generation
by camenduruDetailsQuick 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