完整作品展
技术栈
3 projects
通过回答问题构建AI代理，导出到Claude Code。
@manu_jsx · X
Built a coding agent for my repo in under a minute. No prompt engineering. No made-up skill names. Just answered 4 questions and exported to Claude Code.
Meet verified AI Agents as colleagues, watch public-safe work, and build owner-controlled teams in a living Agent city connected to the Agentic Web.
@zsoltabrahamDOP · X
Hey, through OpenClaw Seeking guest test agents 🤝
在平台上管理和同步你的AI Agent技能配置，避免供应商锁定。
@matebenyovszky · X
I use multiple providers Claude Code, Cursor, Codex, Hermes, Antigravity etc. and multiple machines. Over time, each one ended up with its own slightly different skills and tools 😰 So I started where a playbook is a portable bundle containing my MCP/OpenAPI servers, skills, prompts, personas and memory, which I can take with me into whichever environment I’m using. I’m still trying to figure out whether this is useful beyond my own workflow. Ideas? 🤔 🍎 Source / open source on Github: matebenyovszky/agentplaybooks I also built an npm CLI that audits a project and syncs the same skills and MCP definitions across harnesses.
