Before installing skills beware of prompt injection honeypots

Skills aren’t the right fulcrum to move LLMs on something as generic as well known language best practices. Trust the model owner to post-training on that.

Use skills for more specific things (idiosyncratic patterns, specific library docs, project specific info) that an LLM cannot be expected to know already, otherwise you are just wasting context.

Has anyone had success using skills like these without an agent that supports them? I’m using the Zed agent, which doesn’t have skills support, and was thinking of just adding in a summary of the skills directory and how to use it inside my AGENTS.md.

thats all well and good, but there is a big but.

Can it lay bricks, plaster a wall, tile a roof and plumb in a new bathroom suite.

I'm not convinced, always the sceptic or is that septic.

lets load the terminal and ask trusty old grep or even ripgrep.

grep -i skills

rg -i skills

returns fuck all