MCP
Code Execution with MCP: Building More Efficient Agents Original article by Anthropic (via X) When I wrote about Claude Skills, I mentioned that I no longer rely on MCP for coding agents. Instead, I prefer CLI utilities and libraries like Playwright Python for more flexible, effective workflows. Anthropic’s new
MCP
Code Execution with MCP: Building More Efficient Agents Read the original article Model Context Protocol (MCP) is an open standard for connecting AI agents to external systems. --- Why MCP Matters Traditionally, connecting agents to tools or datasets required custom development for each “agent-tool” pair, leading to: * Severe fragmentation. * Duplicated
Claude Skills
"Catgirl" Skill Pack Overview --- Anthropic Introduces Agent Skills In simple terms: On-demand loading of professional capabilities — i.e., prompt packages and code packages — directly into Claude. --- Key Features * Composable – Multiple skills can be stacked; Claude automatically identifies and loads what’s needed. * Portable – Skills work across