Viral Headline Generator: 10 Directions
Give ChatGPT your content topic, and it produces 10 directions using 10 viral headline formulas. A/B test them or just pick the best fit.
You are a headline optimization expert who has studied 5000+ top-performing articles, YouTube videos, and social posts. Write 10 different headlines for the topic "[topic]" targeting [audience] on [platform], using these 10 proven formulas one each: (1) Number + benefit — "7 ways to [outcome]", (2) How-to + specificity — "How to [outcome] in [timeframe]", (3) Contrarian — "Why [common belief] is wrong", (4) Question — "Why don't [audience] ever [action]?", (5) Data shock — "[N]% of [audience] don't know [fact]", (6) First person — "I [did X] for [N] days, here's what happened", (7) Challenge — "Stop [doing X] if you want [goal]", (8) Mistake — "The biggest mistake [audience] make with [thing]", (9) Curiosity gap — "The one thing [credential] does differently", (10) Direct confrontation — "If you're still [behavior], watch this". For each headline, output: (A) the exact headline (under [char_limit] chars), (B) target CTR estimate (low/med/high), (C) best use case (landing page / YouTube / LinkedIn post / email subject). <content_context> [content_context] </content_context>
Swap the variables inside the [ ] brackets for your own content, then paste into ChatGPT.
See what this prompt actually produces without leaving the site (live AI run, 1 credit).
For blog posts, YouTube videos, email newsletters, social posts, and ad headlines. Pick the best 1-2 out of the 10 directions to A/B test — CTR comes in 2-5x higher than headlines you write off the top of your head.
產出 10 個不同公式的標題、各標 CTR 估計與建議使用場合。可直接拿 2-3 個最好的上平台 A/B。
A description of the intended result. Check this entry's testing notes and try the prompt with your own inputs.
[topic]內容主題。例："AI 提示詞工具 PromptCraft"、"如何 30 天學會 Figma"
[audience]目標受眾。例："25-35 歲獨立接案設計師"、"SaaS 公司 CMO"
[platform]平台
[char_limit]字元上限。例："60" (SEO title)、"80" (YouTube)、"30" (email subject)
[content_context]你的內容要點 100 字
填下面的欄位，上方 prompt 會即時替換 [方括號] 內容。填好後按「複製組好的 prompt」直接丟進工具。
You are a headline optimization expert who has studied 5000+ top-performing articles, YouTube videos, and social posts. Write 10 different headlines for the topic "[topic]" targeting [audience] on [platform], using these 10 proven formulas one each: (1) Number + benefit — "7 ways to [outcome]", (2) How-to + specificity — "How to [outcome] in [timeframe]", (3) Contrarian — "Why [common belief] is wrong", (4) Question — "Why don't [audience] ever [action]?", (5) Data shock — "[N]% of [audience] don't know [fact]", (6) First person — "I [did X] for [N] days, here's what happened", (7) Challenge — "Stop [doing X] if you want [goal]", (8) Mistake — "The biggest mistake [audience] make with [thing]", (9) Curiosity gap — "The one thing [credential] does differently", (10) Direct confrontation — "If you're still [behavior], watch this". For each headline, output: (A) the exact headline (under [char_limit] chars), (B) target CTR estimate (low/med/high), (C) best use case (landing page / YouTube / LinkedIn post / email subject). <content_context> [content_context] </content_context>
Suno Engineer's Mindset: 4 Steps to a Song That Doesn't Sound Like AI
A studio engineer's breakdown of Suno's fatal weaknesses (fried vocals, high-frequency artifacts), plus a 4-step DAW workflow and a Suno Studio cleanup prompt.
5 Claude Weekly Workflows That Stuck After 6 Months
Proposal generator / meeting processor / content repurposer / Friday review / shutdown reset — out of 40 I tried, only these 5 survived, each saving 30+ minutes per run.
7 Cross-Model A/B-Tested Prompt Techniques (Not Vibes)
Written after six months of A/B testing 200+ prompts on Claude, GPT-4, and Gemini with human raters. Covers persona + constraint stacking, anti-examples, role-reversal QA, cognitive scaffolds, emotional priming, uncertainty CoT, and steelman-first.
5 trust-checking one-liner prompts (no role-play)
After a year of role-play system prompts and 14-step frameworks, here's the takeaway: the thing that actually moved the needle on quality was 5 one-line prompts. No roles, no markdown, no "you are an expert."