Futures
Access hundreds of perpetual contracts
TradFi
Gold
One platform for global traditional assets
Options
Hot
Trade European-style vanilla options
Unified Account
Maximize your capital efficiency
Demo Trading
Introduction to Futures Trading
Learn the basics of futures trading
Futures Events
Join events to earn rewards
Demo Trading
Use virtual funds to practice risk-free trading
Launch
CandyDrop
Collect candies to earn airdrops
Launchpool
Quick staking, earn potential new tokens
HODLer Airdrop
Hold GT and get massive airdrops for free
Launchpad
Be early to the next big token project
Alpha Points
Trade on-chain assets and earn airdrops
Futures Points
Earn futures points and claim airdrop rewards
More
swyx Shares His Mac Setup as an Open-Source Claude Skill
Headline
swyx Releases His Mac Setup as an Open-Source Claude Skill
Summary
Shawn “swyx” Wang, founder of the Latent Space podcast, published his 2026 Mac setup as a reusable skill on GitHub. The skill works with Anthropic’s Claude Cowork desktop app, which can run these automations to configure developer environments—installing CLI tools, setting up VS Code extensions, and configuring productivity apps through bash scripts and dotfiles. swyx has published Mac setup guides for years; this version makes the process executable by an AI agent running in a sandboxed VM.
Analysis
The skill is a markdown file bundling instructions, workflows, and code dependencies. By packaging his setup this way, swyx shows how developers can extend Claude Cowork beyond chat into local task execution. Claude Cowork (which evolved from Claude Code) runs these skills in sandboxed VMs, handling file operations and multi-app tasks without constant user input. Anthropic has built out integrations with Notion, Figma, and other tools through its Skills Directory.
swyx coined the “AI Engineer” term and hosts a podcast covering developer-AI tooling. His background includes roles at AWS and Netflix. Publishing this skill fits a pattern he’s discussed on the podcast: making AI automations portable and hackable rather than locked into proprietary platforms. Other developers can fork his setup, modify it, and share their own versions.
Impact Assessment
This is a niche contribution, but it demonstrates a pattern that could spread. Open-source AI skills let developers share automations the way they share dotfiles today. The immediate audience is small—people using Claude Cowork who want to automate their Mac setup—but the approach could influence how agent platforms handle user-contributed workflows.