How to write a better prompt
the five things every prompt needs

A prompt usually goes wrong because something is missing, not because a sentence was clumsy.

Download for MacmacOSSend it to your Mac
How to write a better prompt: the five things every prompt needs
  • Every prompt needs five things: a goal, context, steps, limits, and how you’ll know.
  • Context is what the agent can’t see: your screen, the error, what you tried.
  • Typing it all is slow. Say it, with a screenshot, in one go.

You type one line. The agent guesses the rest, and you spend four messages correcting it.

Five things every prompt needs

  1. 1Your goalWhat should be true when it is done.
  2. 2The context it can’t seeThe error, your screen, what you tried.
  3. 3The stepsWhat to do, in order if order matters.
  4. 4What not to touchThe part everyone forgets.
  5. 5How you’ll know it workedSo it can check its own work.
~/Dev/app — claude
Claude Code~/Dev/app

Fix the onboarding redirect for Google sign-ups. New users hit the dashboard before their workspace exists, so it 404s. I already tried a retry, it didn’t help. Fix the race in the callback handler, then add a test for a fresh Google sign-up. Don’t touch the email sign-up path. It’s done when a new Google account lands on its own dashboard.

? for shortcuts

No headings needed. A prompt goes wrong when one of the five is missing, not when it is in the wrong place.

Context is what the agent can’t see

  • No: Your screen: the broken page, the odd layout.
  • No: The error in your browser or your logs.
  • No: What you already tried, so it doesn’t try it again.
  • No: Why the odd-looking code is there.

So show it. A screenshot of the broken page says more than a paragraph about it.

Four rules that hold up

  • Yes: Say what not to do. Cheap to write, expensive to leave out.
  • Yes: Name things exactly. src/main/pipeline.ts, not “the pipeline”.
  • Yes: One example beats three adjectives.
  • No: Skip the padding. Politeness and role-play preambles buy nothing.

That is a lot to type

  • No: Five parts take longer to type than the question.
  • No: Then you save the screenshot, find it and drag it in.
  • No: The “don’t touch that” is the part you forget.

Wouldn’t it be so much easier to just say it?

“um so the export is broken on safari, it throws over ten megabytes, make the banner blue, no wait, red, and maybe add a CSV option”
Claude Code /voice
claude
> um so the export is broken on safari, it throws over ten megabytes, make the banner blue, no wait, red, and maybe add a CSV option
Its docs claim no clean-up
Wispr Flow
claude
> The export is broken on Safari. It throws over ten megabytes. Make the banner red, and maybe add a CSV option.
Tidies it
claude
> The export is broken on Safari. It throws over ten megabytes. Make the banner red.

Maybe add a CSV option.
Shapes it for your agent

Take the screenshot, then talk

With Yappr, a screenshot you take lands on your notch. Hold your key and say what is wrong, and it goes in with your words: in Claude Code, as a file it can open. Yappr keeps your own sentences, in the order you said them. It does not add headings.

Speaking into Claude Code? Compare /voice with a dictation app.

The same rules belong in the standing file: what to put in CLAUDE.md.

Written 6 September 2026. Every fact about another product is from its own pages, checked that day.