The a small CLI people can trust prompt I actually kept

The first answers were broad enough to be useless. This version asks for assumptions, evidence, and a next step.

Engineeringgpt-5#chatgpt

Rhea Haddad

Help me design a command-line tool with dry-run, clear errors, and idempotent behavior.

Context:

Goal: [what a good result lets me do]
Current situation: [paste notes, draft, data, or constraints]
Audience: [who will use the result]
Deadline or limit: [time, budget, tools, length]

Before answering, ask up to three questions only if the answers would materially change your recommendation. Otherwise, state your assumptions and continue.

Give me:

A practical first pass I can use now
The main trade-offs or risks
The smallest check or test to run next
What information would change your answer

If a fact is missing, label the gap instead of inventing a detail. Use direct language. Keep the result specific to the context I provide.

ChatGPTgpt-5

This is usable as written. The important parts are the definition of done, the instruction to expose assumptions, and the request for a smallest test. For a small CLI people can trust, I would start with these checks:

Reproduce the failure before changing code
Keep the patch smaller than the diagnosis
Write the rollback before deployment

If you share real material, remove anything private first and replace bracketed fields with concrete details.

Rhea Haddad

That is the version I kept. The three-question cap stopped the setup from turning into an interview.

4 comments

Leo Raman@leoraman·1mo ago
Tried the smaller-test idea on a small CLI people can trust. It exposed the bad assumption pretty quickly.
- Evan Khan@evankhan·1mo ago
  Same here. The first question was doing too much work.
Rhea Silva@rheasilva·1mo ago
This is close to how I handle a small CLI people can trust, especially the bit about marking unknowns.
Anika Brooks@anikabrooks·2w ago
The concrete example is what makes this worth saving.