alt Hacker News>* I find it hard to justify the value of investing so much of my time perfecting the art of asking a machine to write what I could do perfectly well in less time than it takes to hone the prompt.*
This sums up my interactions with LLMs
Replies
wiredpancake • today at 4:18 AM
[dead]
This is correct if the prompt is single-use. It's wrong if the prompt becomes a reusable skill that fires correctly 200 times.
The problem isn't generation — it's unstructured generation. Prompting ad-hoc and hoping the output holds up. That fails, obviously.
200 skills later: skills are prose instructions matched by description, not slash commands. The thinking happens when you write the skill. The generation happens when you invoke it. That's composition, not improvisation. Plus drift detection that catches when a skill's behavior diverges from its intent.
Don't stop generating. Start composing.