Post

https://twitter.com/1643695629665722379/status/1927649502917485051

More from @godofprompt

God of Prompt

@godofprompt

Feb 10

I've written 500 articles, 23 whitepapers, and 3 ebooks using Claude over 2 years, and these 10 prompts are the ONLY ones I actually use anymore because they handle 90% of professional writing better than any human editor I've worked with and cost me $0.02 per 1000 words: 👇

1. The 5-Minute First Draft

Prompt:

"Turn these rough notes into an article:

[paste your brain dump]

Target length: [800/1500/3000] words
Audience: [describe reader]
Goal: [inform/persuade/teach]

Keep my ideas and examples. Fix structure and flow."

2. Headline Machine (Steal This)

Prompt:

"Topic: [your topic]

Write 20 headlines using these formulas:
- How to [benefit] without [pain point]
- [Number] ways [audience] can [outcome]
- The [adjective] guide to [topic]
- Why [common belief] is wrong about [topic]
- [Do something] like [authority figure]
- I [did thing] and here's what happened
- What [success case] knows about [topic] that you don't

Rank top 3 by click-through potential."

Read 13 tweets

God of Prompt

@godofprompt

Feb 9

RIP "act as an expert" and basic prompting.

A former OpenAI engineer just exposed "Prompt Contract" - the internal technique that makes LLMs actually obey you.

Works on ChatGPT, Claude, Gemini, everything.

Here's how to use it right now:

Here's why your prompts suck:

You: "Write a professional email"
AI: *writes generic corporate bullshit*

You: "Be more creative"
AI: *adds exclamation marks*

You're giving vibes, not instructions.

The AI is guessing what you want. Guessing = garbage output.

Prompt Contracts change everything.

Instead of "write X," you define 4 things:

1. Goal (exact success metric)
2. Constraints (hard boundaries)
3. Output format (specific structure)
4. Failure conditions (what breaks it)

Think legal contract, not creative brief.

Read 14 tweets

God of Prompt

@godofprompt

Feb 6

Claude Opus 4.6 is a monster.

I just used it for:

- automating marketing tasks
- building full websites and apps
- writing viral X threads, LinkedIn posts, and YouTube scripts

And it did all this in minutes.

Here are 10 prompts you can steal to unlock its full potential:

1. THE CAMPAIGN STRATEGIST

Opus 4.6's 200K context window means it remembers your entire brand voice across all campaigns.

Prompt:

"You are my senior marketing strategist with 10 years of experience in [your industry]. First, analyze my brand voice by reviewing these materials: [paste 3-5 previous posts, your about page, and any brand guidelines].

Then create a comprehensive 30-day content calendar that includes: daily post ideas with specific angles, optimal posting times based on my audience timezone [specify timezone], platform-specific adaptations (Twitter, LinkedIn, Instagram), CTAs tailored to each post's goal, and content themes organized by week.

For the top 5 highest-potential posts, create A/B test variations testing different: hooks, CTAs, content formats (thread vs single post vs carousel), and emotional angles. Include your reasoning for why each variation might outperform.

Finally, identify 3 content gaps my competitors are filling that I'm currently missing."

Opus maintains perfect consistency across 200K tokens. Other models lose your voice after 3-4 posts.

2. THE SPY MACHINE

Opus 4.6 processes competitor data 3x faster than GPT-4 and catches patterns humans miss.

Prompt:

"Act as a competitive intelligence analyst. I need you to reverse-engineer my competitors' entire marketing strategy.

Analyze these 10 competitor assets: [paste competitor landing pages, ad copy, email sequences, social posts, or URLs].

For each competitor, extract and document:
1. Core value proposition and positioning angle
2. Specific CTAs used and where they're placed
3. Social proof tactics (testimonials, logos, stats, case studies)
4. Pricing psychology (anchoring, tiering, urgency tactics)
5. Content strategy patterns (topics, frequency, formats)
6. Unique differentiators they emphasize

Then give me:

- 5 strategies they're ALL using that I'm missing (ranked by potential revenue impact)
- 3 positioning gaps in the market none of them are addressing
- 2 specific weaknesses in their approach I can exploit
- 1 bold contrarian strategy that goes against what everyone's doing

Present findings in a strategic brief format with implementation difficulty and expected timeline for each tactic."

Opus reads entire competitor websites in one shot. No "context too long" errors.

Read 13 tweets

God of Prompt

@godofprompt

Feb 6

Stop telling LLMs like Claude and ChatGPT what to do.

Start asking them questions instead.

I replaced all my instruction prompts with question prompts.

Output quality: 6.2/10 → 9.1/10

This is called "Socratic prompting" and here's how it works:

Most people prompt like this:

"Write a blog post about AI productivity tools"
"Create a marketing strategy for my SaaS"
"Analyze this data and give me insights"

LLMs treat these like tasks to complete.
They optimize for speed, not depth.

You get surface-level garbage.

Socratic prompting flips this.

Instead of telling the AI what to produce, you ask questions that force it to think through the problem.

LLMs are trained on billions of reasoning examples.
Questions activate that reasoning mode.

Instructions don't.

Read 13 tweets

God of Prompt

@godofprompt

Feb 5

I reverse-engineered the actual prompting frameworks that top AI labs use internally.

Not the fluff you see on Twitter.

The real shit that turns vague inputs into precise, structured outputs.

Spent 3 weeks reading OpenAI's model cards, Anthropic's constitutional AI papers, and leaked internal prompt libraries.

Here's what actually moves the needle:

Framework 1: Constitutional Constraints (Anthropic's secret sauce)

Don't just say "be helpful."

Define explicit boundaries BEFORE the task:

"You must: [X]
You must not: [Y]
If conflicted: [Z]"

Claude uses this internally for every single request.

It's why Claude feels more "principled" than other models.

Framework 2: Structured Output Schemas (OpenAI's internal standard)

Stop asking for "a summary."

Define the exact structure:

"Return JSON:
{
"main_point": string,
"evidence": array[3],
"confidence": 0-100
}"

GPT-5 function calling was built for this.

You're just not using it.

Read 13 tweets

God of Prompt

@godofprompt

Feb 3

ChatGPT's custom instructions feature is insanely powerful.

But 99% of people write garbage instructions.

I tested 200+ custom instruction sets.

These 5 patterns increased output quality by 3.4x:

PATTERN 1: Tell ChatGPT what NOT to do

Bad: "Be concise"

Good: "Never use: delve, landscape, robust, utilize, leverage, it's important to note, in conclusion"

Why it works: Negative instructions are specific. Positive instructions are vague.

Output quality jumped 2.1x with this alone.

PATTERN 2: Context over identity

Bad: "I'm a software engineer"

Good: "I build B2B SaaS with React, Node.js, PostgreSQL. My audience is technical founders who need production-ready code, not tutorials."

Same prompt. 10x better output.

The difference? AI knows your environment.

Read 10 tweets

Share this page!

Enter URL or ID to Unroll

God of Prompt

Try unrolling a thread yourself!

More from @godofprompt

God of Prompt

God of Prompt

God of Prompt

God of Prompt

God of Prompt

God of Prompt

Did Thread Reader help you today?

Don't want to be a Premium member but still want to support us?

Send Email!