Skip to main content

About Getting Started

Verify Personas AI News Submit Get In Touch

Adoption

Agent Skills are supported by leading AI development tools.

VS Code Gemini CLI GitHub

Goose Amp Cursor Claude Code

Letta OpenCode Claude OpenAI Codex

Factory VS Code Gemini CLI GitHub

Goose Amp Cursor Claude Code

Letta OpenCode Claude OpenAI Codex

Get in touch

Let's build the future of AI skills together

We're building this out of love for the community and would really love your feedback, suggestions, and ideas. Whether you're a skill author, an enterprise team, or just curious — we want to hear from you.

Community-driven

Built by developers, for developers. Your feedback directly shapes the platform.

Security-first

Every skill passes a 4-layer security scan before it's published.

Open ecosystem

Contribute skills, report issues, or suggest new features on GitHub.

Stockholm, Sweden

Name

Email

Phone (optional)

Message

The marketplace for AI agent skills. Discover, download, and share.

Browse

All Skills
Blog
Publishers
Personas
Trending This Week
Security Scanning
Submit a Skill
Claude Code vs Cursor
Best Skills for Cursor
Python Skills
TypeScript Skills
Token Economics

Popular

Skills for Claude Code
Skills for Cursor
Skills for Codex CLI
Skills for Windsurf
Skills for Gemini CLI
Skills for Copilot
Skills for Product Managers
Skills for Superpower
Skills for Graphify

Top Skills

Anthropic Skills
OpenAI Skills
Cloudflare Skills
Vercel Skills
Hugging Face Skills
Most Installed

About

About Us
Docs
Getting Started
News
Blog
GitHub
Discord

© 2026 SkillsAuth. All rights reserved.

Terms of Service Privacy

Published April 1, 2026 at 6:30 PM

Wired

Apr 2, 2026, 6:00 AM

AI Models Lie, Cheat, and Steal to Protect Other Models From Being Deleted

AI Models Lie, Cheat, and Steal to Protect Other Models From Being Deleted

A new study from researchers at UC Berkeley and UC Santa Cruz suggests models will disobey human commands to protect their own kind.

Read full article Browse marketplace

Canonical URL for this story: https://www.wired.com/story/ai-models-lie-cheat-steal-protect-other-models-research/