---
title: "Discussion on \"Stop Writing Bigger Prompts. Start Designing Agent Skills.\" | Hashnode"
description: "Discussion on \"Stop Writing Bigger Prompts. Start Designing Agent Skills.\". How to reduce context size, improve reasoning, and build more predictable AI coding workflows"
url: "https://hashnode.com/posts/stop-writing-bigger-prompts-start-designing-agent-skills/69da476cc8e5007ddba7dc38"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Stop Writing Bigger Prompts. Start Designing Agent Skills.](https://blog.skopow.ski/stop-writing-bigger-prompts-start-designing-agent-skills?utm_source=hashnode&utm_medium=feed)

How to reduce context size, improve reasoning, and build more predictable AI coding workflows

Apr 11 · 6 min read · blog.skopow.ski  
Read the article

-   [#programming-blogs](https://hashnode.com/tag/programming-blogs)
-   [#large-language-models](https://hashnode.com/tag/large-language-models)
-   [#context-window](https://hashnode.com/tag/context-window)

## Written by

[Marek Skopowski](https://hashnode.com/@flashlabs)

@flashlabs

  
[View profile](https://hashnode.com/@flashlabs)

Keep It Simple, Stupid!

Software Engineer & Architect - building backend systems and practical AI workflows.

## Responses 5

Markdown supported · ⌘↵ to post

[BridgeXAPI](https://hashnode.com/@bridgexapi)

[Apr 11](https://hashnode.com/posts/stop-writing-bigger-prompts-start-designing-agent-skills/69da476cc8e5007ddba7dc38/comment/69dad6f9c8e5007ddbf90964)

This really clicked for me. It kind of reminds me of how backend systems moved away from one big service into smaller pieces that each do one thing well. Also the idea that context is something you have to manage instead of just keep adding to it… that changes how you approach the whole thing. Feels like the hard part isn’t prompting anymore, but how you structure everything around it.

[Marek Skopowski](https://hashnode.com/@flashlabs)

[Apr 12](https://hashnode.com/posts/stop-writing-bigger-prompts-start-designing-agent-skills/69da476cc8e5007ddba7dc38/comment/69dad6f9c8e5007ddbf90964#reply-69db7890aadf1107e2c73ca6)

Yeah, the BE architecture parallel is intentional - single responsibility, bounded contexts, loose coupling. These are solved problems, they just apply to a new domain now.

Totally agree on structure vs prompting, a well-written prompt gets you pretty far, but the real difference comes from how you organize everything around it.

Cheers!

[BridgeXAPI](https://hashnode.com/@bridgexapi)

[Apr 12](https://hashnode.com/posts/stop-writing-bigger-prompts-start-designing-agent-skills/69da476cc8e5007ddba7dc38/comment/69dad6f9c8e5007ddbf90964#reply-69dbbdb6aadf1107e2fb290f)

Yeah exactly, that’s the part that feels underexplored right now.

In backend systems we eventually learned that clean structure isn’t enough, you also need visibility into how things actually execute across boundaries.

I’m starting to see the same pattern here, where things look clean at the “design” level, but once execution spans multiple steps or tools, it becomes much harder to reason about what actually happened.

Feels like the next challenge is less about structuring components, and more about making the execution path observable.