Sorgu Yeniden Yazma Güvenlik Testi
Arama sorgusu iyileştirilirken niyet ve güvenlik sınırlarının korunmasını sağlar.
HAZIR VE KOPYALANABİLİR
Prompt Kütüphanesi
305+ test edilmiş prompt şablonu; yazıdan koda, görsel üretiminden kariyere kadar. Değişkenleri ({böyle}) kendinize göre doldurup doğrudan kullanın.
Anyone else spending more time prompting than building?
I might sound lazy (because I am) but lately it feels like I spend half my day rewriting prompts instead of shipping anything. I'll tweak one prompt five times trying to get the output just right. Then I switch models to see if another one does better. Before I know it an hour is gone and I've barely touched the actual project. At this point I'm wondering if I'm overthinking it
Anyone have a prompt or skill file that actually kills the AI writing rhythm or Claude and GPT-isms
I use Claude and GPT daily and the thing I can't get past is the cadence. Not the vocabulary — the rhythm. Once you notice it you can't unsee it. The specific tics I'm trying to eliminate: Sentences built on "it's not X, it's Y" Em-dash asides everywhere Groups of three, constantly Setup-colon-payoff constructions Openers like "Here's the thing" or "Let's be clear" Every paragr
Are better prompts the answer to bad AI generated websites?
From using Ai website generators(a majority of them) I'm starting to think the difference between getting something usable and complete garbage might be how much context you give it upfront. If I'm writing a massive prompt explaining the layout, style, audience and every little requirement idk if I'm saving myself any time there like how detailed do you need to be with prompts
Best way to use screenshots with ChatGPT & Claude
I paste a lot of screenshots into ChatGPT / Claude. Half the time it latches onto the wrong button, log line, or panel, then I have to explain too much via prompts. To save my time and get work done faster with AI & Screenshots, I made Lookhere to just make screenshot self-explanatory so I don't have to waste my energy in writing prompts. It’s a fast, distraction-free tool desi
Do people still bother writing detailed prompts?
Something I’ve been wondering about lately: When you use ChatGPT or Claude, do you actually write detailed prompts, or have you mostly moved toward just talking to it like a person? I feel like there are two very different ways of using these tools. One is: "Here's the context, here's exactly what I want, here's the format…" The other is basically opening voice mode and saying,
Here's a prompt that audits your own writing for the patterns AI detectors flag, after my honest lab report got flagged
Mechanical engineering junior. I wrote a lab report myself, the way I write everything, and it came back flagged by an AI detector. I hadn't used AI on it at all, which was a fun conversation to have with a professor who'd already made up their mind. The detectors are basically pattern-matchers, and it turns out the patterns they hate are also the patterns you drift into when y
How we get AI to write like a human after thousands of pieces of content (rules, tone scales, exemplars)
I run an agency and we've written thousands of pieces of content with AI at this point. The default writing style is kind of obnoxious with every model, and honestly it seems to have gotten worse as the models got smarter, not better. I think it's because the labs are all optimizing for software engineering now, so the models write like they're optimizing code. Shorthand, missi
I stopped using ChatGPT's memory as project state and turned Google Drive into an external operational memory
With the help of Chatty (that’s what I call ChatGPT), I built a simple system for managing long-term projects without depending too much on ChatGPT’s built-in memory. The problem was pretty simple: ChatGPT was good at remembering things like how I prefer to work, but project information eventually became outdated. “I like to discuss the architecture before writing code” is usef
I turned Wikipedia's "Signs of AI Writing" into an open-source self-edit checklist skill for LLM agents
Wikipedia editors have spent months cataloguing submissions to figure out what gives away AI-generated text. They compiled a detailed community guide called Signs of AI Writing. I turned that guide into an open-source self-edit agent skill called Writ: 👉 https://github.com/Avinashricky211/writ What it catches: • Stock vocabulary: "delve", "tapestry", "testament", "seamless", "r
I was spending more time writing prompts than actually working. This simple system fixed it.
I’ve been using AI daily for about a year now (ChatGPT, Claude, etc.). My biggest bottleneck was always the same: typing out long, specific instructions to get the output I wanted. I found a cheat code recently that I wanted to share with you guys. It’s a system of "Slash Commands" (like /viral, /summarize, or /mindmap). Instead of writing a paragraph, I just type one command.
i've been using 3 one-word codes instead of writing full prompts. AUTOPSY has talked me out of two bad ideas already
Instead of typing out the same long instructions every time, define them once and trigger them with a single word for the rest of the chat. Paste this to switch them on: For the rest of this conversation, treat these as instructions whenever I use them: AUTOPSY = assume this already failed. Work backward and tell me exactly why it died, every weak point, in order of what killed
Most people tell AI what to do. Very few people show it what "good" looks like.
One of the easiest ways to improve AI outputs isn't writing longer prompts. It's giving examples. Instead of this: «Write a product description.» Try this: «Write a product description following this structure: - A short opening hook - Three benefit-focused bullet points - A professional but friendly tone - End with a clear call to action» Notice what's different. You're no l
Prompt Share | I made a prompt cheat sheet for reverse-engineering almost any image
I’ve been doing a lot of image-to-prompt experiments lately, and I realized I kept rewriting the same instructions depending on what kind of image I was analyzing. So I put together a conclusion. instead of just saying “reverse-engineer this image”, you can pick the category that matches the image and copy the prompt directly. might be useful if you often use ChatGPT or other m
Stop asking AI to "make slides." Give it this structure instead and the outline actually holds up
"Make me a presentation about X" gives you a generic table of contents every time. Intro, three vague sections, conclusion. The problem isn't the model, it's that "make slides" has no shape. Give it the shape and it gets a lot better. ``` Before writing any slides, build the spine of the talk. Step 1: State the ONE thing the audience should remember. Just one sentence. Step 2:
Stop describing your tone to an AI writing tool. Make it reverse-engineer it instead.
Every "write in my voice" attempt I made used to be me listing adjectives. Casual but professional, confident not arrogant, and so on. The output always came back sounding like a brand guideline wrote it, because adjectives are not a style, they are a vibe. What actually works is making the tool extract the rules from your own samples first, then write against those rules. Two