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

WordPress大学
WordPress大学
酷 壳 – CoolShell
酷 壳 – CoolShell
OSCHINA 社区最新新闻
OSCHINA 社区最新新闻
腾讯CDC
freeCodeCamp Programming Tutorials: Python, JavaScript, Git & More
Jina AI
Jina AI
N
Netflix TechBlog - Medium
有赞技术团队
有赞技术团队
博客园 - 【当耐特】
MongoDB | Blog
MongoDB | Blog
P
Proofpoint News Feed
L
LangChain Blog
aimingoo的专栏
aimingoo的专栏
GbyAI
GbyAI
B
Blog
F
Fortinet All Blogs
T
Tailwind CSS Blog
Cyber Security Advisories - MS-ISAC
Cyber Security Advisories - MS-ISAC
G
Google Developers Blog
A
About on SuperTechFans
C
Check Point Blog
Microsoft Security Blog
Microsoft Security Blog
MyScale Blog
MyScale Blog
B
Blog RSS Feed

Hacker News: Show HN

PurrrrrFocus: Pomodoro Timer App - App Store Workflow Engine — Multi-Step Orchestration for Bun RapidPhoto: Pro Photo Editor App - App Store GitHub - DheerG/swarms: Achieve extraordinary results with claude code across a variety of tasks SPICE simulation → oscilloscope → verification with Claude Code — Lucas Gerads Show HN: VCoding – A 5 MB native Windows IDE with no dynamic dependencies Show HN: LLMs don't hallucinate because they're bad at math, it's the format GitHub - Agent-FM/agentfm-core: AgentFM is a peer-to-peer network that turns everyday computers into a decentralized AI supercomputer. AgentFM lets you run massive AI workloads directly across a global mesh of idle CPUs and GPUs. Show HN: Tracking Top US Science Olympiad Alumni over Last 25 Years GitHub - Potarix/agent-hub: One place to talk to all your agents Show HN: Runtime security for AI agents(injection,tool abuse, data exfiltration) GitHub - dubeyKartikay/lazyspotify: Terminal Spotify client for macOS and Linux GitHub - the-banana-tool/king-louie: Easy to use GUI Personal AI Assistant. Win/Linux/Mac. Show HN I made my vacation rental bookable by AI agents–no Airbnb, 0% commission GitHub - basteez/jsf-autoreload: maven plugin to enable hot reload on jsf projects uvm32/hosts/host-gdbstub at main · ringtailsoftware/uvm32 GitHub - labsai/EDDI: Config-driven engine that turns JSON into production-grade AI agents. Multi-agent orchestration, 12+ LLM providers, MCP/A2A protocols, RAG, persistent memory, and enterprise compliance (EU AI Act, GDPR, HIPAA). Built on Quarkus. GitHub - glitchnsec/fortyone-oss: AI Executive Assistant Platform Quickstart | Alien GitHub - muxshed/shed: One stream in, or many. Every destination, simultaneously. No cloud middleman, no per-channel fees, no limits. GitHub - ocrbase-hq/ocrbase: 📄 PDF/IMG ->.MD/JSON Document OCR API for PaddleOCR and GLMOCR. Self-hostable. GitHub - impactjo/home-memory: MCP server that lets your AI assistant remember everything about your home. GitHub - Sets88/dbcls: DbCls is a powerful terminal database client that supports various databases GitHub - neptun2000/heor-agent-mcp GitHub - SeanFDZ/macmind: Single-layer transformer in HyperTalk for the classic Macintosh RollQuation: Math Puzzles - Apps on Google Play GitHub - dropbox/witchcraft Show HN: Agent-cache – Multi-tier LLM/tool/session caching for Valkey and Redis GitHub - opentalon/opentalon: OpenTalon is an open-source platform built from the ground up in Go as a robust alternative to OpenClaw LinkedIn™ 职位抓取工具 - Chrome 应用商店
GitHub - AltrinaAI/skill-studio: Lightweight app for mini...
harveyhu · 2026-06-19 · via Hacker News: Show HN

The best human interface for Agent Skills. Available on macOS, Linux, and Windows.

Skill Studio — recent skills, skill mining, and the discovered skills library

We love agent skills. As agents get more powerful, it's easy to feel like losing control over the direction of your project or organization. We think agent skills is the right place to specify your taste, expertise, and customize your way of doing things on an organization level.

There just isn't a good human interface for editing agent skills. Any place that requires human creativity needs a good human interface: clean, intuitive, version controlled. So we built one and open-sourced it.

Built with Tauri, Skill Studio runs on macOS, Linux, and Windows, and connects to any remote dev setup you have natively VS Code style (see design.md).

Features

  • Discover and manage every skill on your machine, across Claude Code, Codex, Cursor, Gemini CLI, OpenClaw, the shared ~/.agents/skills standard, and project repos.
  • Skill Mining — use your local agent to analyze past agent conversations to create / update skills.
  • Edit rendered markdown directly — view and edit SKILL.md and other Markdown files directly on the rendered document. Double click to edit the raw markdown syntax.
  • Automatic versioning — automatically track changes across all your skills and sync to any remote you specify
  • Secrets manager — machine-local store. Automatically detect secrets used and notice on export for "batteries included" sharing of the skills.
  • Terminals & remote hosts — managed agent sessions that survive UI disconnect, so you can close your laptop and pick the run back up later. Point Studio at any SSH host and run agents there. Supports Claude Code, Codex, or a shell.

Install

Grab the latest build for your platform:

Platform
macOS — Apple silicon & Intel Download
Windows Download
Linux — Debian/Ubuntu Download

First launch

The builds aren't OS-notarized yet, so macOS and Windows warn the first time you open the app:

  • macOS — the app is blocked as unverified. Open System Settings → Privacy & Security, scroll to the message about Skill Studio, and click Open Anyway.
  • Windows — SmartScreen shows "Windows protected your PC". Click More info → Run anyway.
  • Linux — install the package with sudo apt install ./Skill-Studio-Linux-x86_64.deb.

Build from source

Install Rust, Node.js/npm, and the Tauri prerequisites for your OS, then:

git clone https://github.com/AltrinaAI/skill-studio.git
cd skill-studio
npm install
npm run tauri -- build

The built app bundle is written under client/desktop/target/release/bundle/.

Development

npm install
npm run dev          # native desktop
Mode Command Open
Native desktop npm run dev the app window
Browser, local backend cargo run -p skill-server + npm run dev:vite localhost:1420

Roadmap

The thesis: the future is one where humans collaborate with AI agents, not one where they are replaced by them. Skills are the medium for human expert knowledge, so they need a first-class human UX. Next:

  1. Team collaboration & secret management — share skills and the secrets they need across a team, account-backed.
  2. Multi-modal skills / SOP documents in a format readable by both humans and agents, for computer use agents.