This is coming late as skills have largely replaced MCP. Now your site can just host a SKILL.md to tell agents how to use the site.

▲

jasonjmcghee an hour ago | parent | next [-]

It's not meant to describe how to use the site, it should / can replace the need for playwright and DOM inspection / manipulation entirely.

Think of it like an "IDE actions". Done right, there's no need to ever use the GUI.

As opposed to just being documentation for how to use the IDE with desktop automation software.

▲

hnlmorg 5 hours ago | parent | prev | next [-]

The purpose of this appears to be for sites that cannot be controlled via prompt instructions alone.

I do like agent skills, but I’m really not convinced by the hype that they make MCP redundant.

	▲	dionian 2 hours ago \| parent [-]
		seems like skill is a better interface, but state still needs to be externally managed, even if not using mcp as the protocol

▲

fdefitte 3 hours ago | parent | prev | next [-]

Skills are great for static stuff but they kinda fall apart when the agent needs to interact with live state. WebMCP actually fills a real gap there imo.

	▲	charcircuit 3 hours ago \| parent [-]
		What prevents them with working with live state. Coding agents deal with the live state of source code evolving fine. So why can't they watch a web page or whatever update over time? This seems to be a micro optimization that requires explicit work from the site developer to make work. Long term I just don't see this taking off versus agents just using sites directly. A more long term viable feature would be a way to allow agents to scroll the page or hover over menus without the user's own view being affected.

▲

ATechGuy 5 hours ago | parent | prev [-]

Interesting. I'd appreciate an example. Thanks!

▲

ednc 5 hours ago | parent [-]

check out https://moltbook.com/skill.md

	▲	Spivak 5 hours ago \| parent \| next [-]
		I really like how the shell and regular API calls has basically wholesale replaced tools. Real life example of worse-is-better working in the real world. Just give your AI agent a little linux VM to play around that it already knows how to use rather than some specialized protocol that has to predict everything an agent might want to do.
	▲	esafak an hour ago \| parent \| prev [-]
		no workie