How to update your language to get better results from AI

Hi friend!
​
Both of these statements are true:

AI tools democratize professional work.
But seniority still matters.

A beginner can now create things that looked impossible a few years ago. They can design an interface, generate a professional slide deck, write functional code, or edit a video.

Give the same tools to a senior engineer, designer, analyst, or strategist, and the output will still be much better. Not because they can click different buttons. Not because they have access to a secret model. But because they know what good looks like, and they have the language to describe it.

A lot of professional skill is vocabulary.

In design, “make this bigger” is vague. “Increase the padding, tighten the hierarchy, and reduce visual noise” gives the model a much clearer target.

In creating slides, “create a chart” is vague. “Use a dumbbell chart to show the before/after delta across categories” gets you much closer.

The same is true in code. The same is true in design. The same is true in almost any form of knowledge work.

Language matters because language carries judgment. It encodes distinctions. It gives shape to vague taste.

And as more of our work becomes instruction-giving to agents, this matters even more:
​The quality of your output increasingly depends on the quality of your instructions.

This is why I think agent skills are so interesting.

At the most basic level, they let you borrow the language of experts. You can take a skill written by someone who understands design, code, research, writing, or slides, plug it into your workflow, and immediately give the agent better instructions than you would have written from scratch.

That alone is valuable. It makes your work with agents more effective.

But the bigger opportunity lies in taking one more step:

If you do not just use the skill passively, but read it, question it, rewrite it, and adapt it to your own work, you start upgrading your own language.

You begin to notice the distinctions experts make. The defaults they encode. The constraints they care about. The words they use to turn a vague request into a precise instruction.

Over time, this changes how you prompt. But it also changes how you think.

You are not just copying someone else’s expertise anymore. You are absorbing it, reshaping it, and combining it with your own point of view.
​
So don't sleep on agent skills and don't just use them passively.
​​
​Thanks for reading,

Robert

Skills to try

• ​thermo-nuclear-code-quality-review – official skill from the Cursor team - generates incredibly good reviews of your code. I use this before every PR.
• ​thermo-nuclear-plan – my own adaption of the above specifically for generating sound plans that take into account the complexity of the existing codebase.
• ​bug-investigate-fix – a skill I created loosely based on Cursor's Debug agent. It systematically tackles bugs through reproduction, then generating and testing hypotheses.
  ​
• --> In general skills.sh run by Vercel is a good way to discover and use skills.
• Not a skill, but a great collection of animation vocabulary: https://animations.dev/vocabulary​

Headlines

• ​Windsurf is no more - the once hyped AI IDE gets reborn as Devin Desktop
• ​OpenAI is officially entering Lovable and Bolt's territory with it's new Sites feature in Codex

Miscellaneous

• ​Playing with Vision Embeddings – cool interactive blog post to better understand how image embeddings work