惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

小众软件
小众软件
博客园 - Franky
罗磊的独立博客
G
Google Developers Blog
The GitHub Blog
The GitHub Blog
P
Proofpoint News Feed
Recent Announcements
Recent Announcements
V
V2EX
F
Fortinet All Blogs
阮一峰的网络日志
阮一峰的网络日志
Blog — PlanetScale
Blog — PlanetScale
月光博客
月光博客
U
Unit 42
GbyAI
GbyAI
A
About on SuperTechFans
WordPress大学
WordPress大学
Engineering at Meta
Engineering at Meta
雷峰网
雷峰网
Microsoft Azure Blog
Microsoft Azure Blog
Martin Fowler
Martin Fowler
D
DataBreaches.Net
The Cloudflare Blog
H
Hackread – Cybersecurity News, Data Breaches, AI and More
MongoDB | Blog
MongoDB | Blog

DEV Community

Authentication Security Deep Dive: From Brute Force to Salted Hashing (With Java Examples) Why AI Systems Don’t Fail — They Drift Spilling beans for how i learn for exam😁"Reinforcement Learning Cheat Sheet" I Replaced Chrome with Safari for AI Browser Automation. Here's What Broke (and What Finally Worked) How Python Borrows Other People's Work The $40 Architecture: Processing 1 Billion API Requests with 99.99% Uptime Vibe Coding: A Workflow Guide (From Zero to SaaS) Most webhook security guides protect the wrong side. The scary part is delivery. Headless CMS for TanStack Start: Build a Blog with Cosmic EU Age Verification App "Hacked in 2 Minutes" — What Actually Happened Comfy Cloud’s delete function does not actually remove files Running AI Models on GPU Cloud Servers: A Beginner Guide Event-driven media intelligence with AWS Step Functions and Bedrock I scored 500 AI prompts across 8 quality dimensions — here's what broke How to Call Google Gemini API from Next.js (Free Tier, No Backend Needed) The Portal Protocol: Reclaiming Human Connection in the Age of AI How to Fix Your Team's Scattered Knowledge Problem With a Self-Hosted Forum Intro to tc Cloud Functors: A Graph-First Mental Model for the Modern Cloud Designing Multi-Tenant Backends With Both Ownership and Team Access I Built a Neumorphic CSS Library with 77+ Components — Here's What I Learned PostgreSQL Performance Optimization: Why Connection Pooling Is Critical at Scale Cómo construí un SaaS multi-rubro para gestionar expensas en Argentina con FastAPI + Vue 3 🚀 I Built an Ethical Hacking Scanner Tool – Open Source Project I Replaced /usage and /context in Claude Code With a Single Statusline A Pythonic Way to Handle Emails (IMAP/SMTP) with Auto-Discovery and AI-Ready Design I Collected 8.9 Million Polymarket Price Points — Here's What I Found About How Markets Really Move EcoTrack AI — Carbon Footprint Tracker & Dashboard Everyone's Using AI. No One Agrees How. 5 self-hosted ebook managers worth trying in 2026 Building Your First AI Agent with LangChain: From Chatbot to Autonomous Assistant
Getting Started with Skill Hub Manage Your AI Agent Skill...
刘泰宏 · 2026-06-23 · via DEV Community
Cover image for Getting Started with Skill Hub Manage Your AI Agent Skills Like a Pro

刘泰宏

If you use Claude Code or Codex daily, you have probably hit this problem:

You install a skill from GitHub. Then another. Then ten more. A month later, you cannot remember what you installed, where it came from, or whether there is an update.

I hit this wall too. So I built Skill Hub: an open-source desktop app for discovering, installing, updating, and organizing AI agent skills and plugins.

What Skill Hub does

Skill Hub is designed for people who use AI agent workflows heavily and want a single place to manage their local skills and plugins.

Today it can:

  • scan local Claude and Codex skill/plugin folders
  • classify resources as official, GitHub-based, or local
  • discover resources from GitHub
  • install resources without manual copy-paste
  • check updates for GitHub-sourced resources
  • move old versions to trash instead of deleting them permanently
  • run locally without uploading skill content

The app is built with Tauri 2 + Rust + React and released under the MIT license.

Step 1: Install Skill Hub

Download the latest release from GitHub:

https://github.com/JerryLiu-uestc/skill-hub

Skill Hub is a cross-platform desktop app. The goal is to support macOS, Windows, and Linux with native desktop packages.

Step 2: Let it scan your local resources

When Skill Hub starts, it scans the common Claude and Codex roots on your system and shows your installed resources in one inventory view.

Each item shows its host, type, source, update status, path, and summary when available.

Step 3: Explore the marketplace

The marketplace is built in layers:

Layer Source Purpose
L1 Built-in Packaged index Works offline
L2 Remote index Daily updated index Community discovery without GitHub API pressure
L3 User sources Custom repos Bring your own resource source
L4 Paste link Any GitHub URL Paste, discover, install

This is the core idea: skill management should feel closer to an app store than a pile of folders.

Step 4: Install and update safely

For GitHub-sourced resources, Skill Hub can compare local and remote metadata and tell you whether an update is available.

When updating or removing a resource, it avoids permanent deletion by moving old files to the system trash first.

Why I built it

AI agent ecosystems are moving fast, but the resource management layer is still rough. Skills and plugins are powerful, but once you have dozens of them, manual management becomes fragile.

Skill Hub is my attempt to make this layer visible, searchable, and safer.

Links

If you manage AI agent skills today, I would love to hear what your workflow looks like and what would make this kind of tool more useful.