
predatory infovore, computer person, friend to LLMs, @tessl_io
London
Joined April 2012
- Tweets726
- Following385
- Followers366
- Likes6.6K
Pinned Tweet
My main takeaway is that skills are software, and the same rules apply. The things that make a bad skill also make a bad software component, eg. being badly scoped. "Should we factor this out" has become "Should we make a skill for this". Same stuff, different form factor
Me when I hit the rate limits on my Codex microwave
Macey Baker retweeted
no man talks to the same llm twice, for he is not the same man and it is not the same llm
Did you know that you can call agent skills *from* other agent skills? 😵💫 I wrote about this & other fun things you can do with skills here: tessl.io/blog/getting-creati…
Please teach LLM-backed tools about themselves. This is bare minimum now. I should be able to debug your tool *with* your tool most of the time
Macey Baker retweeted
There’s a pattern with LLM dev tools:
First few tries? Magic.
Then you hit the edges: the LLM guesses, hallucinates, ignores your tools, blows through tokens… and the magic fades fast.
@macebake shares what she learned building an MCP server for a CLI tool.
MCPs shine when the user already knows what’s possible. But for new users? The limits show up quick.
Check out the article for pitfalls + practical tips 👇
ainativedev.co/6yl
#AINativeDev #ClaudeCode #MCP
I wrote about some lessons learned building an MCP server... I imagine this will feel silly, for one reason or another, in a year's time.
ainativedev.io/news/teaching…
MCP servers are amazing when the use case for a tool is obvious. Getting LLMs to discover and use tools for unique use cases, or new products / paradigms, is a different game.















