Brooke Wright
Brooke Wright · @wright_mode
FREE PROMPT PACK

Get the good answer first go

Three copy-paste prompts that fix Claude's bad answers, without 100 agents eating your plan.

Copy-paste ready Works in Claude chat No Claude Code needed Built by Brooke
Something went wrong. Please try again.

No spam. Unsubscribe anytime.

3 prompts that fix Claude's bad answers (without maxing your plan) Jump to the prompts → Join the Membership
Wright Mode — Free Resource

Fix Claude's Bad Answers

Three copy-paste prompts that get you a good answer first go, without 100 agents burning through your Claude plan. Works in normal Claude chat.

3 copy-paste prompts Works in Claude chat No Claude Code needed Saves your usage

What's inside

Bad answers usually mean Claude's guessing. These three fix the guessing in one chat, without spinning up a single extra agent. They work in normal Claude chat (and ChatGPT).

1

Interview Me First

For anything that depends on your business, your audience or your taste. Paste this at the end of your request. Claude asks what it's missing before it writes a word, so the first answer is built on your details, not its guesses.

Before you start, ask me 3 questions about what I actually need, so you're not guessing. Ask all 3 in one message. Focus on what's missing from my request: who it's for, what a great result looks like, and anything I'd hate to see. Don't start the work until I've answered.
2

The Mini Arena

For when you want the best version, not the first one. It's the same idea as the 100-agent arena (different approaches compete, get critiqued, one wins), but it happens in a single reply.

[Paste your request here] Give me 3 versions, each using a completely different approach. Label them A, B and C, with a one-line summary of each approach. Then critique all three like a brutal editor: what's weak, what's generic and what's missing in each one. Finally, pick the winner and rewrite it, borrowing anything good from the other two. Tell me in one sentence why it won.
3

The Clean Retry

For when the answer's off and you're about to type “no, try again”. Don't. Click edit (the pencil) on your original message, paste this underneath it, fill in the brackets and resend. Claude starts again from your better message, and the chat doesn't keep growing.

Who it's for: [your client, audience or reader] What good looks like: [paste an example you love, or describe it] The goal: [what this needs to achieve] Avoid: [words, tone or ideas you don't want] Format: [e.g. 3 short paragraphs, a table, under 150 words]

Why edit beats “try again”

Every follow-up message makes the chat longer, and Claude counts conversation length against your usage limit. Five rounds of “not quite” costs you more and usually still misses, because the missing context never arrived.


Claude isn't dumb. It's guessing. When your request is missing context, it fills the gaps with the most average answer it can find. Asking again doesn't add context. Giving it the context does.

What you typed

“Write an Instagram caption for my new offer.”

What Claude needed

  • Who the offer is for
  • What it is and what it costs
  • How you sound (paste a caption you've written)
  • How long, and what to avoid

Hot tip

If you keep pasting the same background (your offer, your audience, your voice), put it in a Claude Project once. Every chat inside that Project starts with it, so you stop retyping it and Claude stops guessing.


The arena skill is a free add-on for Claude Code. You give it one task and it runs up to 100 copies of Claude on it, each with a different strategy. They pair off, attack each other's answers and rewrite their own, and a judge scores every match until one answer is left.

How the bracket shrinks

1
100 answers written, one per agent
2
Knockout rounds: 100 → 50 → 25 → 13 → 7 → 4 → 2 → 1
3
Every match means critiques, rewrites and a judge, and every one of those is Claude working on your plan

Why it maxes out your plan

The skill's own instructions say it straight: “The skill is free. The tokens are yours, and 100 agents is a lot of them.” Anthropic's engineering team found multi-agent setups use about 15 times more tokens than a normal chat. On Pro and Max, Claude chat and Claude Code share the same limits, so a big run in Claude Code eats into your normal chat time too.

When it's actually worth it

One high-stakes answer (a sales page, a pricing call, a nasty bug)
Every time an answer's a bit meh
You're already in Claude Code (it won't run in normal chat)
You haven't tried the 3 prompts above yet
Quick mode (16 agents) for everyday jobs, like its own instructions recommend
You're close to your limit for the week

Before you run anything big (an arena run, a long research job, a stack of file uploads), check how much you've got left.

1

Open Settings → Usage

You'll see two progress bars: your current 5-hour session and your weekly limit.

2

Low on the weekly bar?

Save the big jobs for after it resets, and lean on the Mini Arena instead. One reply, three competing answers.


Ready to go deeper?

Where to go from here.