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.

  • Ethereum.org is a primary online resource for the Ethereum community.

    Trust 87Quality 100web3-analytics
  • Readme.So4.6K stars

    An online drag-and-drop editor to easily build READMEs

    Trust 85Quality 92document-processing
  • It Tools39K stars

    Collection of handy online tools for developers, with great UX.

    Trust 88Quality 100coding-agents

Codex, Claude Code, Cursor

Coding agent skills

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

  • Skills122 stars

    Agent Skills for the Venice.ai API. One folder per surface area, each with a SKILL.md for agent runtimes (Cur…

    Trust 84Quality 87utility
  • 🤖 精选的 AI Agent Skills 列表,适用于 Cursor、Claude Code、GitHub Copilot 等 AI 编程工具

    Trust 84Quality 94coding-agents
  • Video Shotcraft1.8K stars

    AI video skill for Claude Code & Codex — cinematic product videos with Remotion: 106 shot recipe cards, 161 m…

    Trust 84Quality 87utility

Documents and knowledge

Research and RAG skills

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

  • Markpdfdown1.8K stars

    A high-quality PDF to Markdown tool based on large language model visual recognition. 一款基于大模型视觉识别的高质量PDF转Mark…

    Trust 83Quality 84document-processing
  • Khoj35K stars

    Your AI second brain. Self-hostable. Get answers from the web or your docs. Build custom agents, schedule aut…

    Trust 90Quality 100data
  • MrDoc3.2K stars

    mrdoc,online document system developed based on python. It is suitable for individuals and small teams to man…

    Trust 87Quality 97document-processing

Markets and quant

Finance and trading skills

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

  • Quant Trading10K stars

    Python quantitative trading strategies including VIX Calculator, Pattern Recognition, Commodity Trading Advis…

    Trust 82Quality 82finance
  • Qbot18K stars

    [🔥updating ...] AI 自动量化交易机器人(完全本地部署) AI-powered Quantitative Investment Research Platform. 📃 online docs: h…

    Trust 89Quality 100finance
  • Akaunting10.0K stars

    Online Accounting Software

    Trust 85Quality 100finance

Crawlers and extraction

Web scraping skills

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

  • Pot Desktop19K stars

    🌈一个跨平台的划词翻译和OCR软件 | A cross-platform software for text translation and recognition.

    Trust 90Quality 100document-processing
  • Doctr6.1K stars

    docTR (Document Text Recognition) - a seamless, high-performing & accessible library for OCR-related tasks po…

    Trust 88Quality 100document-processing
  • KkFileView14K stars

    Universal File Online Preview Project based on Spring-Boot

    Trust 84Quality 100document-processing

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
  • FunClip5.8K stars

    Open-source, accurate and easy-to-use video speech recognition & clipping tool. LLM-based AI clipping integra…

    Trust 89Quality 100media-automation
  • VoxCPM31K stars

    VoxCPM2: Tokenizer-Free TTS for Multilingual Speech Generation, Creative Voice Design, and True-to-Life Cloni…

    Trust 90Quality 100media-automation

Images, video, UI

Design and creative skills

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

  • Kokoro FastAPI5.1K stars

    Dockerized FastAPI wrapper for Kokoro-82M text-to-speech model w/multiplatform CPU, AMD, NVIDIA GPU PyTorch s…

    Trust 87Quality 99media-automation
  • Mlx Audio7.4K stars

    A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framewor…

    Trust 89Quality 100media-automation
  • A comprehensive ComfyUI integration for Microsoft's VibeVoice text-to-speech model, enabling high-quality sin…

    Trust 86Quality 87media-automation

Analysis and pipelines

Data and analytics skills

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

  • Drawdb37K stars

    Free, simple, and intuitive online database diagram editor and SQL generator.

    Trust 87Quality 100data-analysis
  • TTS10K stars

    :robot: :speech_balloon: Deep learning for Text to Speech (Discussion forum: https://discourse.mozilla.org/c/…

    Trust 82Quality 76media-automation
  • Totum Mit984 stars

    Small-code database for non-programmers. Universal UI, simple-code logic, automatic actions, access rules, lo…

    Trust 77Quality 78productivity-automation

Supply tracks

Build the registry by domain, not just by count.

Coding

Coding and developer agents

185

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

185 quality184 maintained

Research

Research and knowledge work

81

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

81 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

16

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

16 quality15 maintained

Marketing

Marketing and growth automation

18

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

18 quality18 maintained

Design

Design and creative production

105

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

105 quality98 maintained

Data

Data, BI, and analytics

31

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

31 quality31 maintained

Legal

Legal, policy, and compliance

14

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

14 quality14 maintained

Education

Education and tutoring

8

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

8 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 449 ranked candidates matching "online-speech-recognition"

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

1

Speech Recognition

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDDESIGN

Speech recognition module for Python, supporting several engines and APIs, online and offline.

$ npx skills add Uberi/speech_recognition
9.0K stars69 quality89 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

pythonspeech
by UberiDetailsQuick view
2

ASRT SpeechRecognition

VERIFIEDEXCELLENT · 99TRUST · 86SAFE · REVIEWEDDESIGN

A Deep-Learning-Based Chinese Speech Recognition System 基于深度学习的中文语音识别系统

$ npx skills add nl8590687/ASRT_SpeechRecognition
8.4K stars66 quality86 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

pythonspeech
by nl8590687DetailsQuick view
3

PaddleSpeech

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDDESIGN

Easy-to-use Speech Toolkit including Self-Supervised Learning model, SOTA/Streaming ASR with punctuation, Streaming TTS with text frontend, Speaker Verification System,…

$ npx skills add PaddlePaddle/PaddleSpeech
12.6K stars72 quality90 trustReviewed1mo 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

pythonspeech
by PaddlePaddleDetailsQuick view
4

Speechbrain

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDDESIGN

A PyTorch-based Speech Toolkit

$ npx skills add speechbrain/speechbrain
11.6K stars72 quality88 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

pythonspeech
by speechbrainDetailsQuick view
5

Lhotse

VERIFIEDEXCELLENT · 93TRUST · 86SAFE · REVIEWEDDESIGN

Tools for handling multimodal data in machine learning projects.

$ npx skills add lhotse-speech/lhotse
1.1K stars63 quality86 trustReviewed1mo 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

pythonspeech
by lhotse-speechDetailsQuick view
6

Face Recognition

VERIFIEDSTRONG · 82TRUST · 79SAFE · EXPERIMENTALCODING

The world's simplest facial recognition api for Python and the command line

$ npx skills add ageitgey/face_recognition
56.5K stars61 quality79 trustExperimental2y 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

CLI + Codex · 4 targets

pythonmachine-learning
by ageitgeyDetailsQuick view
7

Whisper.Cpp

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDDESIGN

Port of OpenAI's Whisper model in C/C++

$ npx skills add ggml-org/whisper.cpp
51.0K stars76 quality88 trustReviewedOpenAI 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/…Review: Documentation summary is thin
Safety gateGood audit and safety signals with no high-risk permission hints in public metadata.

Scenario Multimodal media

OpenAI Agents + CLI · 4 targets

c++speech
by ggml-orgDetailsQuick view
8

WhisperX

VERIFIEDEXCELLENT · 100TRUST · 90SAFE · REVIEWEDDESIGN

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)

$ npx skills add m-bain/whisperX
22.6K stars74 quality90 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

pythonspeech
by m-bainDetailsQuick view
9

Speech To Speech

VERIFIEDEXCELLENT · 99TRUST · 86SAFE · REVIEWEDDESIGN

Build local voice agents with open-source models

$ npx skills add huggingface/speech-to-speech
4.9K stars68 quality86 trustReviewed1mo 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 huggingfaceDetailsQuick view
10

Vosk API

VERIFIEDEXCELLENT · 100TRUST · 88SAFE · REVIEWEDDESIGN

Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node

$ npx skills add alphacep/vosk-api
14.9K stars72 quality88 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

jupyter-notebookspeech
by alphacepDetailsQuick view
11

Espnet

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDDESIGN

End-to-End Speech Processing Toolkit

$ npx skills add espnet/espnet
9.9K stars70 quality87 trustReviewed1mo 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

pythonspeech
by espnetDetailsQuick view
12

SenseVoice

VERIFIEDEXCELLENT · 97TRUST · 85SAFE · REVIEWEDDESIGN

Multilingual speech understanding: ASR + emotion recognition + audio event detection. 50+ languages, 15x faster than Whisper, non-autoregressive.

$ npx skills add FunAudioLLM/SenseVoice
8.6K stars69 quality85 trustReviewed1mo 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

cspeech
by FunAudioLLMDetailsQuick view
13

Mlx Audio

VERIFIEDEXCELLENT · 100TRUST · 89SAFE · REVIEWEDDESIGN

A text-to-speech (TTS), speech-to-text (STT) and speech-to-speech (STS) library built on Apple's MLX framework, providing efficient speech analysis on Apple Silicon.

$ npx skills add Blaizzy/mlx-audio
7.4K stars69 quality89 trustReviewed1mo 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

pythonspeech
by BlaizzyDetailsQuick view
14

Annyang

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDDESIGN

💬 Speech recognition for your site

$ npx skills add TalAter/annyang
6.8K stars69 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 Multimodal media

CLI + Codex · 4 targets

typescriptspeech
by TalAterDetailsQuick view
15

Argmax Oss Swift

VERIFIEDEXCELLENT · 100TRUST · 87SAFE · REVIEWEDDESIGN

On-device Speech AI for Apple Silicon

$ npx skills add argmaxinc/argmax-oss-swift
6.2K 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 Multimodal media

CLI + Codex · 4 targets

swiftspeech
by argmaxincDetailsQuick view
16

Pocketsphinx

VERIFIEDEXCELLENT · 94TRUST · 82SAFE · REVIEWEDDESIGN

A small speech recognizer

$ npx skills add cmusphinx/pocketsphinx
4.3K stars67 quality82 trustReviewed with permission notes1mo since pushNeeds review
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 gateUsable candidate, but the agent should surface permission and audit notes before installation.

Scenario Multimodal media

CLI + Codex · 4 targets

cspeech
by cmusphinxDetailsQuick 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