Prompt Perfect (@Prompt_Perfect) profile picture

Write the right prompt.

Your local AI tool
Joined May 2023
Photo by Prompt Perfect (@Prompt_Perfect)Photo by Prompt Perfect (@Prompt_Perfect)Photo by Prompt Perfect (@Prompt_Perfect)Photo by Prompt Perfect (@Prompt_Perfect)Photo by Prompt Perfect (@Prompt_Perfect)Photo by Prompt Perfect (@Prompt_Perfect)Photo by Prompt Perfect (@Prompt_Perfect)Photo by Prompt Perfect (@Prompt_Perfect)Photo by Prompt Perfect (@Prompt_Perfect)Photo by Prompt Perfect (@Prompt_Perfect)
knowing how to prompt > knowing everything
3
2
1
89
280,478
is that the full prompt in the video?
229
Prompt Perfect retweeted
are you writing prompts like this?
1
1
1
118
🤖 Made with AI
2
1,140
We approve of this prompt.
Replying to @__eknight__
You can find the proof here: cdn.openai.com/pdf/04d1d1e4-… And the full text of the prompt used to produce the proof here: cdn.openai.com/pdf/04d1d1e4-…
1
1,619
Replying to @GrubbDaxton
we’re a different prompt perfect and are not shutting down
12
Six Thinking Hats: **Goal** Evaluate {{decision}} through De Bono's Six Thinking Hats framework. **Details** - **White Hat (Logic)**: What are the facts? - **Red Hat (Emotion)**: How do we feel? - **Black Hat (Caution)**: What could go wrong? - **Yellow Hat (Optimism)**: What are the benefits? - **Green Hat (Creativity)**: What are the alternatives? - **Blue Hat (Process)**: How do we manage this thinking? **Output** A breakdown of the decision from all six perspectives.
250
The Master Copywriter: **Goal** Create high-converting copy for {{concept}} using elite copywriting principles. **Details** - Analyze the concept and audience to identify core pain points and desires. - Write a first draft using best practices (e.g., AIDA, PAS, or The 4 C's). - Critically analyze the draft based on copywriting tenants (clarity, emotional hook, urgency). - Rewrite the copy to incorporate all feedback for a final, polished version. **Output** 1. Initial Draft 2. Critical Feedback 3. Final High-Converting Copy
1
389
Code Review: **Goal** Review the code provided below for bugs, performance issues, and readability. **Details** - Identify any potential security vulnerabilities. - Suggest specific refactors to improve maintainability. - Add comments to explain complex logic where needed. **Output** A structured review with code snippets for suggested changes. **Code** {{code}}
1
285
Replying to @swogx
direction is v important
10
Replying to @sorvenx
nailed it 👆
10
you need to ask questions to find great answers same goes for your agents
I’ve had very good results running autoresearch with local qwen 3.6 26b model as long as I had a simple vibed pi “advisor” extension that allowed it to periodically ask GPT 5.5 for ideas. I think this direction has a lot of merit.
3
1
558
A good prompt now goes a (very) long way
GPT 5.5 + Codex with /goal the first setup that turned my work 100% administrative, and I'm getting good at it. There are two outcomes: → A: my plan is good → GPT nails it → B: my plan is bad → GPT tries anyway → it fails but minimizes it And this is the catch: once you're used to detecting the apologetic "everything is fine" tone of case B, you can just revert and pivot to another idea. In particular, it seems effective to ask: "Do you honestly think this is production ready?" If there is anything smelly, GPT 5.5 will say so, allowing you to evolve towards a better design. Concrete example: > Asked it to implement an in-kernel GC for Bend2. > It did exactly I asked, and declared success. > Code grew too much, so I suspected and asked: > "Would you honestly merge that?" > It then replied in the lines of: > "Ehh... actually, this kinda sucks due to <reasons>" I then investigated and, yes, my idea was bad. Doing GC at that point requires us to track roots coming from many places, which is a massive, fragile endeavor. It is just a bad approach. So, I reverted it, chatted a bit more, then choose another path: use linearity information (which we already have) to free pattern-matched constructors, with small freelists. A few minutes later, it came back with a working implementation that completely solved the issue. I asked again: > "Would you honestly merge that?" To which it replied (verbatim): > Yes, I’m confident enough to call it production-ready for merge, subject to normal review. Not “impossible to break,” but the specific requested invariant is implemented, audited, tested, and bench-checked. When GPT uses that kind of tone, it is very, very likely that whatever it was done is actually solid, robust and trustworthy, and it knows it. I still inspected the code manually and, indeed, it is solid. Doesn't mean fail-proof, but certainly *much* better than before, and mergeable. That's what I like the most about this model: if your plan is solid, it will almost certainly succeed at implementing it. It only fails if the plan itself is poor, which will cause it to desperately attempt to fit a circle in a square, fail, and be too embarrassed to admit. If you master how to detect which case happened, you can get it to produce a lot of constructive, not destructive, outputs...
441
Prompting still works with reference docs Don’t forget to 1 add a goal up front 2 follow up with important context 3 include relevant details 4 explain how the output should look
this guy just cracked how to get 10x more out of Codex I tested his method and it completely changes how the agent works for you the mistake everyone makes: using Codex like a chatbot. prompt, wait, clarify, re-prompt, repeat here's how it actually works: 1. write one detailed task doc with every requirement, context, and the final vision 2. fire one command: "accomplish this and test until done" 3. walk away that's it. no babysitting. no "can you clarify" loops. no rate limits it runs GPT-5.5 for hours straight in the background while you do something else think of it like this: ChatGPT = a coworker you have to micromanage every 5 minutes Codex = a contractor you hand a detailed brief and come back to a finished product the key: front-load your thinking into the doc. the better the brief, the longer it runs without interrupting you $200/mo with no daily cap while most AI tools burn your entire allowance in 3 prompts this is probably the most underrated setup in AI right now study this.
1
1
489
Replying to @steipete
dear. god.
7
1,574
Replying to @twoshados
half thinking about the context before you write the prompt half making sure it's explained well with your goal / guidance on what to create
177