it seems like these different agents and tools have some differences in how they are holding their mcp, connector or plugin data. what that means is that if you build a self learning/self healing skill with one, and then you use the other agent or tool and continue working, they wont see the correct mcp, connector or plugins available, and will mess everything up! i am certain nate has an obvious solution for this. @Nate Herk i would love to see a video on this. - you are always using vs-code, but claudes connectors and plugins from the desktop app are largely not innately working with vs code or terminal. theres obviously a required workaround for this

has anyone built a skill or hook to automatically reference the latest ai innovators, before doing solving any build plans. i.e. ive seen nate say to claude several times: think of any mcp's or skills that might be useful to use here. however claude is a bit stupid. its training isn't up to date. i need to actively point it to where to look. but obviously its not going to read everything -> assess how everything slots together -> make all these different ideas compete for the best one in that process and even if it did, it would pollute the context like crazy. even using subagents to do alot of that for you would take time. i see two options. and im not in the loop enough to know if people are alraedy doing this or not: 1. make a basic skill that tells it specifically which things or spots to reference - Then create an automation which feeds it - I.E occasionally looking at all the ideas, comparing them and updating a db that feeds the source for the initial skill (could also be used for all domains of knowledge work to great effect) - and more importanly: - - could be built and run by one person, and just accessed by many without any need for everyone to constantly do this "2." create a skill that delegates a bunch of sub-agents to do this every time obviously checking the lates ai innovators methods and successful work/agent brains documentation(if they exist) would just improve your agents abilities to get everything and anything done - assuming you dont stuff everything in context and pollute it

I installed Hermes recently and I’m still trying to understand where it really stands compared to tools like Claude Code and other AI agents. For people actively using Hermes: what are your real use cases? What makes it powerful for you on a daily basis? I feel like I might be missing the bigger picture behind it.

Let's get to know each other! Comment below sharing where you are in the world, a career goal you have, and something you like to do for fun. 😊

1) 🚫 No Business Promotions → NO “DM me for…” or "Comment 'Automation'" posts. 2) 🔗 No Linking Your Own Community/YouTube Videos 3) 🏷️ Title Specifically 4) 🔍 Search for Help First (searchbar) 5) 🙌 Stay Respectful 6) ❌ Enforced Clean‑Up Posts that break these rules will be removed without warning. If you ever have questions, feel free to ask. Let’s make this the best AI Automation community out there by sharing, collaborating, and learning together. 🚀