Muratcan Koylan
12.9K
posts
@muratcan
Toronto, Canada 🇨🇦
Joined December 2022
Pinned
I’m excited to share a new repo: Agent Skills for Context Engineering Instead of just offering a library of black-box tools, it acts as a "Meta-Agent" knowledge base. It provides a standard set of skills, written in markdown and code, that you can feed to an agent so it
It’s actually a good question; the difference is subtle but structural. I usually frame it like this: AGENTS[.]md acts as the declarative context. You write this for every repo (and nested directories) to define the project structure, persona, and coding rules. Skills are the
Finally acquired a 3D printer I need to know how people are actually using agents to design CAD and hardware. Also drop any good papers, blogs, or embodied AI projects I should be looking pls.
00:00
Don’t make the model solve the entire complex problem. Make the harness turn the complex problem into a collection of simple problems. 1. Start with the dumbest system that can work. 2. Build a good eval. 3. Add complexity only where the eval shows that you need it. I love
100%. To me, mastering prompt & context engineering is less about becoming an expert in an engineering domain and more about knowing how to activate the right neural nets of the model for an unfamiliar problem. It is extremely undervalued how important (and challenging) it is to
if you can master the meta-skill of figuring out what problems in arbitrary domains are computationally tractable, you will have the opportunity, for at least a year two, and maybe longer, to be a kind of meta-genius. you will not know the answer to anything, or even how to find
Thank you for supporting open source
@samaI’m excited to share a new repo: Agent Skills for Context Engineering Instead of just offering a library of black-box tools, it acts as a "Meta-Agent" knowledge base. It provides a standard set of skills, written in markdown and code, that you can feed to an agent so it
