Give your draft checker a few hard fails
A creator who audited their own brand with AI built a checker that scores each draft for proof, voice, positioning and format, plus a short list of hard fails that block a post no matter how well it scores. Their examples: a coach promising results, a freelancer showing client work without permission, a founder rounding up numbers.
Done with CChatGPT
"Six hard fails block a post even at 95."x.com
How do you do it, step by step?
- A creator who audited their own brand with AI built a checker that scores each draft for proof, voice, positioning and format, plus a short list of hard fails that block a post no matter how well it scores.
- Their examples: a coach promising results, a freelancer showing client work without permission, a founder rounding up numbers.
- The post does not name the model, so any chat tool can run it.
- Copy the prompt on this page into ChatGPT and fill in your own details.
- Edit the output in your own voice and check any facts before you publish.
Which tool does this use?
ChatGPT. See all ChatGPT use cases or more in Editing.
What does it cost?
Free; Plus $20/mo
What should you watch out for?
Features and prices change. Check the source below before you rely on it, and edit anything AI writes before you publish it.
What prompt should you use with ChatGPT?
Rebuild any prompt with the prompt helperYou are a careful line editor. Context: - I write for [WHO YOU WRITE FOR] on [YOUR PLATFORM]. - My voice: [YOUR VOICE] - My goal: [YOUR GOAL] Task: You are my pre-publish checker. Score this draft from 0 to 100 on proof, voice, positioning and format, with one line of reasoning each. Then check these hard fails, which block the post at any score: [LIST, E.G. PROMISING RESULTS, CLIENT WORK SHOWN WITHOUT PERMISSION, ROUNDED-UP NUMBERS]. Draft: [PASTE YOUR TEXT HERE]. Output: score, any hard fails hit, and the single fix that matters most. Constraints: - Avoid [WHAT TO AVOID]. - Use only facts I give you. Don't invent stats, quotes, names or examples. Write [NEEDS DETAIL] wherever something is missing. - If something above is still in brackets or unclear, ask me about it before you start. Output format: Follow the counts and format given in the task. Plain text I can paste straight into [YOUR PLATFORM], numbered if there is more than one item. Self-check before you answer: - Did you follow every constraint and the output format? - Does it sound like my voice and not generic AI writing? Cut filler openers and buzzwords. - Is every claim backed by something I gave you, or marked [NEEDS DETAIL]? Fix anything that fails, then give me the result.
Make this prompt yours fill in what you know; the prompt updates as you type
Anything left in [BRACKETS] is for you to fill in, or the AI will ask you. Nothing you type leaves your browser. Want to rebuild a prompt you found elsewhere? Use the prompt helper.
Reverse-engineer a prompt paste a prompt or an output you liked and get a meta-prompt
Your meta-prompt
Paste this into ChatGPT or Claude. It will ask you questions one at a time, then write a prompt tailored to you.
Frequently asked questions
How do I give your draft checker a few hard fails?
A creator who audited their own brand with AI built a checker that scores each draft for proof, voice, positioning and format, plus a short list of hard fails that block a post no matter how well it scores. Their examples: a coach promising results, a freelancer showing client work without permission, a founder rounding up numbers.
Which tool do I need for this, and what does it cost?
This use case uses ChatGPT. Pricing listed for it: Free; Plus $20/mo. Check chatgpt.com for current prices.
What prompt can I use?
You are a careful line editor. Context: - I write for [WHO YOU WRITE FOR] on [YOUR PLATFORM]. - My voice: [YOUR VOICE] - My goal: [YOUR GOAL] Task: You are my pre-publish checker. Score this draft from 0 to 100 on proof, voice, positioning and format, with one line of reasoning each. Then check these hard fails, which block the post at any score: [LIST, E.G. PROMISING RESULTS, CLIENT WORK SHOWN WITHOUT PERMISSION, ROUNDED-UP NUMBERS]. Draft: [PASTE YOUR TEXT HERE]. Output: score, any hard fails hit, and the single fix that matters most. Constraints: - Avoid [WHAT TO AVOID]. - Use only facts I give you. Don't invent stats, quotes, names or examples. Write [NEEDS DETAIL] wherever something is missing. - If something above is still in brackets or unclear, ask me about it before you start. Output format: Follow the counts and format given in the task. Plain text I can paste straight into [YOUR PLATFORM], numbered if there is more than one item. Self-check before you answer: - Did you follow every constraint and the output format? - Does it sound like my voice and not generic AI writing? Cut filler openers and buzzwords. - Is every claim backed by something I gave you, or marked [NEEDS DETAIL]? Fix anything that fails, then give me the result.
What are related use cases?
- Keep a list of every line you cut from AI drafts (ChatGPT)
- Ask AI for a list of errors, then fix them yourself (ChatGPT)
- Run your draft through ten sentence-level checks (Claude)
- When it sounds robotic, fix the brief (Claude)
- Map the sub-queries AI search fires for your topic (ChatGPT)
- Your rank in AI answers changes every time you ask (ChatGPT)
Where does this come from?
- https://x.com/BassamDahabra/status/2111490386656894993
- https://help.openai.com/en/articles/6950777-what-is-chatgpt-plus
Checked Oct 18, 2026.
Get 5 like these in your inbox
Each one comes with a prompt you can paste. One short email a week.
Unsubscribe any time. Privacy
Last updated