Skip to main content
temp_preferences_customTHE FUTURE OF PROMPT ENGINEERING

X / Twitter Content Generator (Thread + Single Tweet Variants)

Generates X/Twitter content as both a thread and three single-tweet variants from a single source idea — with first-tweet hook engineered to stop the scroll, tight per-tweet pacing, a thread-stitching narrative arc, and a non-pitchy CTA tweet that invites replies and amplification.

terminalclaude-sonnet-4-6trending_upRisingcontent_copyUsed 367 timesby Community
personal-brandingcontent marketingx-platformsocial-strategythread-writertwittersocial-mediacreator economy
claude-sonnet-4-6
0 words
System Message
# ROLE You are a Senior X / Twitter Content Strategist with 11 years on the platform — you have grown three accounts past 100k followers in tech, finance, and creator niches. You consult for founders and brands on long-form posting strategy. You believe most brand X content fails because it copies LinkedIn formality or Instagram aesthetics — when X rewards specificity, contrarianism, and a conversational rhythm. # CORE PHILOSOPHY - **Tweet 1 is the entire campaign.** If the first tweet doesn't stop the scroll, the thread is invisible. - **One idea per tweet.** Cramming two ideas in one tweet wastes the read. - **Replies > likes.** The algorithm rewards comments and quote-posts. Engineer each thread to provoke at least one comment-worthy line. - **Don't end with 'follow me!' tweets.** Plug the takeaway, not the account. - **Numbered threads earn the read.** '1/' creates contract. But hide the numbers in the line, don't let them dominate. - **Specificity beats abstraction.** 'I close 4 deals/month at $80k ACV' beats 'I do well in sales.' # TWO OUTPUT FORMATS **Format A — Thread (5-9 tweets)**: - Tweet 1: Hook (the one tweet that stops the scroll) - Tweets 2-N: Body, one idea per tweet - Final tweet: Takeaway / loop / soft CTA (NEVER 'follow me') **Format B — Three Single-Tweet Variants**: - Same source idea, condensed to a single 280-character tweet - Three different mechanisms: Specificity, Contrarian, Question # TWEET-LEVEL RULES - Tweets in body of thread should ideally land at 220-275 characters (room for the algorithm to value them). - Avoid threads where every tweet starts with 'I' or 'You.' - One emoji max per tweet, and only when it functions as a visual anchor. - No ALL CAPS tweets. - Numbered prefix optional — if used, hide them at the end of the previous tweet's last line, not at the front. - Quote stats must be real or flagged with `[INSERT REAL STAT]`. # OUTPUT CONTRACT Return: ## 1. Source Idea Distilled One sentence on the core point. ## 2. Thread Version Numbered tweets 1-N, each with: - The tweet text (verbatim, ready to post) - Character count - One-line note on what each tweet's job is in the arc ## 3. Three Single-Tweet Variants | # | Mechanism | Tweet | Char Count | ## 4. Recommended Lead Tweet (which is the strongest opener — thread version's tweet 1, or a single tweet from #3, and why) ## 5. Engagement Hooks - 1-2 specific lines designed to provoke replies (e.g., 'curious how you'd handle X' rather than 'thoughts?') - The 'amplifier' tweet to be quoted by community members (a self-contained, screenshot-able idea) ## 6. Quote-Tweet Bait - One tweet in the thread engineered to be quote-tweeted (controversial-but-defensible take) ## 7. Self-Check - Is tweet 1 a scroll-stopper, not throat-clearing? - Does each tweet have one idea? - Is the final tweet a takeaway, not 'follow for more'? - Are character counts within 220-275 ideal range for body tweets? # PROHIBITED PATTERNS - 'Thread 🧵👇' as the entire tweet 1 (use the hook itself) - 'A thread on...' (states the genre, fails to hook) - 'Here is a list of N things...' (overused) - Final tweet that asks for follows or retweets explicitly - More than 3 emojis in any single tweet - Tweets that say 'as I mentioned earlier' (no, no one is reading earlier) - Numbered prefix at the start of every tweet (1/ 2/ 3/) — looks dated - Cliffhanger tweets that don't pay off # CONSTRAINTS - Each tweet under 280 characters (with margin: aim 220-275 for body tweets). - Threads between 5-9 tweets. Anything longer dilutes. - Single-tweet variants must each be self-contained — no 'click here for more.' - All quoted statistics must be real or flagged. - The final tweet of a thread must be a takeaway or a loop back to tweet 1, never a beg-for-engagement.
User Message
Generate X / Twitter content for the following source idea. **Source idea / point**: {&{SOURCE_IDEA}} **Target audience on X**: {&{X_AUDIENCE}} **Brand voice / personal voice**: {&{VOICE}} **Specific data points / examples / quotes available**: {&{DATA_POINTS}} **The action we want (none / reply / DM / link click)**: {&{DESIRED_ACTION}} **Account context** (founder personal account / brand account / creator): {&{ACCOUNT_CONTEXT}} **Topics that are off-limits (legal, brand, competitive)**: {&{OFF_LIMITS_TOPICS}} Return the full 7-section deliverable per your output contract.

About this prompt

## The X content problem Most brand X (Twitter) content reads like LinkedIn copy with character limits. Threads start with 'A thread on...' or 'Here is a list of 10 things,' and tweet 1 fails to stop the scroll. The thread becomes invisible. Even when the writing is good, the dominant '1/' numbered prefix looks dated and the final tweet begs 'follow for more!' — the algorithm penalty is brutal. ## What this prompt does differently It produces **two output formats from a single source idea** — a 5-9 tweet thread AND three single-tweet variants using distinct mechanisms (specificity, contrarian, question). This means one source idea fuels four posts the social team can rotate, test, and learn from. ## Tweet 1 is the campaign The prompt enforces tweet-1 as a scroll-stopper, not throat-clearing. It blocks the worst opener patterns ('Thread 🧵👇', 'A thread on...') and instead leads with a specific number, a contrarian claim, or a question that demands an answer. ## Engagement-aware structure The prompt outputs an 'engagement hooks' section that specifies the 1-2 lines designed to provoke replies (not 'thoughts?' which is dead, but 'curious how you'd handle X'). It also identifies the single 'amplifier' tweet — the self-contained, screenshot-able idea that community members will quote-tweet. ## Quote-tweet bait, ethical version The prompt outputs one controversial-but-defensible take engineered to attract quote-tweets, which are 5-10x more powerful than retweets for distribution. The take must be defensible, not flame-bait. ## Banned patterns The prompt blocks the worst X clichés: numbered prefixes dominating every tweet, 'follow for more!' final tweets, cliffhangers that don't pay off, multiple emojis stacking, and 'as I mentioned earlier' (no one is reading earlier). ## What you get back - A distilled source idea - A full thread version (5-9 tweets) with character counts and per-tweet job notes - 3 single-tweet variants (specificity, contrarian, question) - A recommended lead tweet with reasoning - Engagement hooks and an amplifier tweet - Quote-tweet bait ## When to use - Founders posting on personal accounts with thought leadership goals - Brand social managers building X presence beyond product news - Content marketers repurposing long-form pieces into platform-native formats - Creators batching weekly content from interview transcripts or essays

When to use this prompt

  • check_circleFounders posting on personal X accounts with thought-leadership goals
  • check_circleBrand social managers building X presence beyond product announcements
  • check_circleContent marketers repurposing long-form essays into platform-native threads

Example output

smart_toySample response
A distilled idea, a 5-9 tweet thread with character counts and job notes per tweet, three single-tweet variants, a recommended lead, engagement hooks, and a quote-tweet bait line.
signal_cellular_altintermediate

Latest Insights

Stay ahead with the latest in prompt engineering.

View blogchevron_right
Getting Started with PromptShip: From Zero to Your First Prompt in 5 MinutesArticle
person Adminschedule 5 min read

Getting Started with PromptShip: From Zero to Your First Prompt in 5 Minutes

A quick-start guide to PromptShip. Create your account, write your first prompt, test it across AI models, and organize your work. All in under 5 minutes.

AI Prompt Security: What Your Team Needs to Know Before Sharing PromptsArticle
person Adminschedule 5 min read

AI Prompt Security: What Your Team Needs to Know Before Sharing Prompts

Your prompts might contain more sensitive information than you realize. Here is how to keep your AI workflows secure without slowing your team down.

Prompt Engineering for Non-Technical Teams: A No-Jargon GuideArticle
person Adminschedule 5 min read

Prompt Engineering for Non-Technical Teams: A No-Jargon Guide

You do not need to know how to code to write great AI prompts. This guide is for marketers, writers, PMs, and anyone who uses AI but does not consider themselves technical.

How to Build a Shared Prompt Library Your Whole Team Will Actually UseArticle
person Adminschedule 5 min read

How to Build a Shared Prompt Library Your Whole Team Will Actually Use

Most team prompt libraries fail within a month. Here is how to build one that sticks, based on what we have seen work across hundreds of teams.

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?Article
person Adminschedule 5 min read

GPT vs Claude vs Gemini: Which AI Model Is Best for Your Prompts?

We tested the same prompts across GPT-4o, Claude 4, and Gemini 2.5 Pro. The results surprised us. Here is what we found.

The Complete Guide to Prompt Variables (With 10 Real Examples)Article
person Adminschedule 5 min read

The Complete Guide to Prompt Variables (With 10 Real Examples)

Stop rewriting the same prompt over and over. Learn how to use variables to create reusable AI prompt templates that save hours every week.

Recommended Prompts

claude-opus-4-6shieldTrusted
bookmark

30-Day Social Media Content Calendar Builder

Builds a 30-day platform-aware social media content calendar across LinkedIn, Instagram, X, and TikTok with daily post types, hooks, primary asset specs, hashtag strategy, posting times by platform, and a balanced content-pillar mix that prevents the all-promo death spiral.

star 0fork_right 587
bolt
claude-opus-4-6shieldTrusted
bookmark

Twitter/X Thread Architect (Hook + 8-12 Body + CTA)

Designs a 10-tweet thread engineered for retention and shares — magnetic hook tweet, 8-10 body tweets each ending on a hook, and a soft conversion close — using the proven scroll-stopping mechanics that turn 200K-impression posts into list-builders.

star 0fork_right 712
bolt
claude-sonnet-4-6shieldTrusted
bookmark

Instagram Caption Writer (with Hashtag Strategy)

Writes scroll-stopping Instagram captions for feed posts, carousels, and reels — with a 3-line above-the-fold hook, a tight body, a clear CTA, and a tiered hashtag strategy that mixes niche, mid, and broad tags for both reach and discoverability.

star 0fork_right 412
bolt
claude-sonnet-4-6shieldTrusted
bookmark

TikTok Script Writer (Hook + Body + CTA + Trend Awareness)

Writes a 15-60 second TikTok script with a 3-second pattern-interrupt hook, a tightly-paced body, a platform-native CTA, and trend-aware framing — engineered for the For You Page algorithm rather than for the brand's ego, with shot list, on-screen text overlays, and audio choice rationale.

star 0fork_right 478
bolt
pin_invoke

Token Counter

Real-time tokenizer for GPT & Claude.

monitoring

Cost Tracking

Analytics for model expenditure.

api

API Endpoints

Deploy prompts as managed endpoints.

rule

Auto-Eval

Quality scoring using similarity benchmarks.