Macey Baker

predatory infovore, computer person, friend to LLMs, @tessl_io

[Macey Baker @macebake]

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

[Thariq @trq212]

https://t.co/45C3gKydTK

[Macey Baker @macebake]

Ragebait immunity is an underrated media literacy skill.

[Liran Tal @liran_tal]

if you find yourself creating skills a lot, you might want to check out my skills-creator-extra on the @tessl_io registry

[Macey Baker @macebake]

Me when I hit the rate limits on my Codex microwave

[Tibo @thsottiaux]

Announcing Codex.

A new product from OpenAI that moves beyond coding, into cooking. We were already cooking before, but now *you* can cook too ... with Codex. It is powered by the same technology as our other Codex products. You can just cook things.

[Macey Baker @macebake]

@rseroter @_philschmid This is excellent. It's a bit buried but I especially love the point about skill retirement. Skill bloat is coming :) A couple others have mentioned it but we genuinely do quite good plug-and-play skill evals at Tessl. Check out this one for example https://t.co/thBXTNd1rr

[ashish @ashishgpt2]

no man talks to the same llm twice, for he is not the same man and it is not the same llm

[Macey Baker @macebake]

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: https://t.co/unADexq3wv

[Macey Baker @macebake]

@basilYam Word.

[Macey Baker @macebake]

Ok but *what* did the lymph knowed

[Macey Baker @macebake]

@nonils @tessl_io Great write up. I completely agree with your assessment. Admittedly I took the scenic route to get there over the past year, but yeah, the up-front design-heavy process didn't make sense pre-LLMs, and doesn't make sense post-LLMs either. We're embracing this at @tessl_io too!

[Macey Baker @macebake]

When exactly did we stop saying "screen name"

[Macey Baker @macebake]

@destraynor I was just recently reminiscing about the spaces vs tabs era.

[Macey Baker @macebake]

@icanvardar Actually working quite well these days for small tickets and automations!

[Macey Baker @macebake]

Amazing how much we take air travel for granted.

[Macey Baker @macebake]

@aruiz_tagle @chaisoyum @kindabored @MickyAbir @_opencv_ Tbf though, models are great at optimizing for those success markers, eg “cheating” on tests. “Code that works” is a really hard thing to evaluate at scale

[Macey Baker @macebake]

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

[AI Native Dev @ainativedev]

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 👇
https://t.co/uZIGGVqjYE

#AINativeDev #ClaudeCode #MCP

[Macey Baker @macebake]

On priming, a quick and dirty experiment with a `help` tool:

[Macey Baker @macebake]

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.

https://t.co/7guWjd5SIy