ChatGPT Prompts for Twitter That Sound Like You, Not Like ChatGPT

Most prompt lists for Twitter are one line long: “write a viral tweet about X”. They fail for the same reason every time. ChatGPT has never read your posts, so it writes like the average of the internet. Below are 12 prompts I would actually use, each built around material only you have.

The limits inside them come from my own account, where short posts win. They are not a universal rule: across 669 other ClimbX users, longer posts did slightly better, so swap in the length that wins against your own median. They also aim at reach and replies. A post meant to teach something useful, bring in qualified leads or sell often needs more room, and is better judged by saves, clicks and DMs than by reply count.

The two-minute setup before any prompt

Collect three things once and keep them in a note, so every prompt below can use them. (1) Your last 20 original posts, copied as plain text, one per line; skip replies and reposts. (2) Your 5 best and 5 worst posts by impressions, with the number next to each; X shows impressions under every post. (3) A few lines of raw notes from this week: what you shipped, a number that changed, a conversation that surprised you.

Run prompt 1 first and save its answer as your voice notes. Paste those voice notes at the top of every later prompt, or into ChatGPT’s custom instructions so you do not have to repeat them. If you use another chatbot, the prompts work the same way.

12 ChatGPT prompts for Twitter, copy-ready

Replace anything in square brackets. Each prompt asks for options rather than one answer, because picking from three is faster than fixing one.

Here are my last 20 posts on X:

[paste posts]

Describe how I write so another writer could copy it. Cover:
- typical length in words, and the shortest and longest
- capitalization, punctuation, line breaks, emoji use
- how I usually open a post and how I end one
- words and phrases I repeat
- topics I come back to
- 3 things I never do

Be specific and quote my posts as evidence. Do not write any new posts yet.

Below are my 5 best and 5 worst posts on X, with impressions.

BEST:
[post] - [impressions]
WORST:
[post] - [impressions]

List the differences in length, opening, structure, topic and ending.
Only name a difference if it shows up in at least 3 of the 5 best posts.
Then give me 3 rules for my next posts, each under 12 words.

My voice notes: [paste]

Raw notes from my week: [paste]

Find 8 post ideas in these notes. For each, give:
- the specific detail it is built on (a number, a name, a moment)
- the shape: question, observation, milestone, or short story
- one sentence on why my audience would reply

Do not invent anything that is not in my notes.

My voice notes: [paste]

Idea: [one sentence]

Write 6 different first lines for this post. Each must be 12 words or fewer.
Use 6 different openings: a number, a named audience ("Founders,"),
a contradiction, a confession, a direct question, a before-and-after.
No hashtags, no colons after a label like "hot take".
Use emoji only the way my voice notes say I use them.

My voice notes: [paste]

Here is a long thought: [paste]

Find the single sharpest claim in it. Write it as 3 posts:
one under 10 words, one under 20 words, one under 30 words with line breaks.
Keep my words where you can. Do not add advice I did not give.

My audience: [who, in one line]
Topic: [topic]

Write 8 questions my audience can answer from their own experience in under 10 seconds.
Rules:
- start 3 of them by naming the audience ("Founders,")
- make 3 of them ask for a one-word or one-number answer ("in 1 word")
- no question with a right answer you could look up
- each under 15 words

Rewrite this post at half its length: [paste]

Cut adjectives first, then any sentence a reader would not miss.
Keep the specific numbers and names. Keep my casing and line breaks.
Give 3 versions and tell me the word count of each.

Here is a draft: [paste]

Do not rewrite it. Ask me 5 short questions that would pull out
the specific detail behind it: a number, a date, a name, what I saw,
what I did next. Wait for my answers before writing anything.

Check this draft for anything that sounds machine-written: [paste]

Flag: emoji used as bullets, rhetorical "Here's the thing", lists of three
abstract nouns, "game-changer", "unlock", "dive in", closing "Thoughts?",
hashtags, and any claim with no example behind it.
Quote each problem and suggest a plainer replacement in my voice.

I wrote this reply on another post: [paste my reply]
The post I replied to was about: [one line]

Turn my reply into a standalone post that makes sense without the original.
Keep my wording. Under 25 words. Give 3 versions.

My take: [paste]

List the 3 strongest objections a smart person in my audience would raise.
Then tell me which one I should answer inside the post, in one line,
so the post holds up in the replies.

My voice notes: [paste]
My raw material: [notes, numbers, examples]

Outline a thread. Do not write the posts.
- Post 1: one specific promise under 15 words
- Posts 2 to 6: one claim each, plus which example from my material proves it
- Last post: one question my audience can answer from experience
Mark any point where my material has no example, so I can add one or cut it.

Why do generic prompts make tweets sound like ChatGPT?

Because a prompt with no examples asks the model to guess, and its guess is the most common shape of a social post: an emoji, a motivational claim, three abstract tips and a “what do you think?” at the end.

That is why every prompt above starts from your own posts, your own week and your own numbers. Here is the same topic asked both ways. Both outputs are illustrative examples I wrote to show the pattern, not real posts.

Why do the prompts carry hard limits?

Because the traits a model adds by default, length and labels, are the traits that show up in my worst posts, and the traits it skips, a named audience and an easy reply, show up in my best.

I tagged my top 500 and bottom 200 posts by trait and compared how often each trait appeared in each group. A ratio of 4 means the trait was four times more common among the winners than the losers. Below 1 means it shows up more in the losers.

That chart is where the rules in the prompts come from. Prompts 4 and 6 open with a named audience because that trait was 4.0 times more common among my winners, and the word limits are there because posts of 26 words or more were half as common among them. Prompt 6 asks for one-word answers because reply-limited questions such as “in 1 word” did well for me on a small set of posts; the result and its sample size are in how to get more replies on X.

Set your own word limit, not mine. In my 1,218 original posts from the last 180 days, posts of 1 to 8 words reached 1.29 times my median and posts of 26 to 45 words 0.80 times. Across 54,338 posts from 669 other ClimbX users in the same window the pattern flips: posts of 46 words or more reached 1.14 times each author’s median and posts of 1 to 8 words 0.92 times. There is no universal ideal length. Run prompt 2 on your own best and worst posts, and put the length that wins for you into prompts 4, 5 and 7.

Two defaults are worth adding to every prompt whatever your numbers say. Ban the “hot take:” style label, which sat at 0.53 in the chart. And tell the model not to mention your product unless the post is about it: that trait sat at 0.40. For the longer list of what makes AI text read as AI, see what separates good AI content from filler.

ChatGPT prompts for Twitter threads

Use ChatGPT for the outline of a thread, then write the posts yourself. In my experience a fully generated thread repeats the same rhythm in every post, which makes it easy to stop reading. I have no retention data on that, so treat it as an observation, not a measured drop-off.

The workflow that keeps your voice: (1) paste your material, meaning notes, numbers and examples; (2) run prompt 12 for an outline only; (3) fill the gaps by adding an example or cutting the point; (4) write each post yourself, one per point; (5) run prompt 7 to shorten each post. The model does structure and trimming. You do the sentences, which is where voice lives.

The outline step catches the most common thread failure: a point with no example behind it. Prompt 12 asks the model to mark those, and each one is a choice between finding a real example and cutting the point. A five-post thread with five real examples beats a ten-post thread padded to look thorough.

Where does prompting stop being enough?

Prompting stops being enough when the missing piece is data the chat window does not have: how your posts actually performed, what is working right now for accounts like yours, and the context you would otherwise paste in every single day.

If you post a few times a week, the prompts above are enough, and they cost nothing beyond the chatbot. If you post daily, the re-pasting becomes the job. That is the gap ClimbX fills: your past posts, their performance and what is working for accounts a step ahead of you are already loaded, so the drafts start from your material without the copy-paste. You still edit every draft before it goes out. I wrote about how voice-trained drafting works in AI tweet writer in your voice, and about using AI for a personal brand without losing the person in how to use AI for personal branding. If you are worried about reach, the rules and data are in does X penalize AI generated posts.

How these numbers were measured

All numbers were queried on October 3, 2026. My own data is my 1,218 original posts on @DanielSmidstrup from the last 180 days, replies excluded, posts younger than 3 days left out so their impressions had settled. Lift is a post’s impressions divided by my own median, and each group shows the median lift. The trait chart is a separate label study that compares my top 500 and bottom 200 original posts; its ratios count how often a trait appears, not how far those posts reached. The cross-user numbers are 54,338 original posts from 669 ClimbX users with at least 20 posts in the same 180-day window, each post divided by its own author’s median. My account is excluded from them, and no individual user’s post is shown.

Common questions