305+ test edilmiş prompt şablonu; yazıdan koda, görsel üretiminden kariyere kadar. Değişkenleri ({böyle}) kendinize göre doldurup doğrudan kullanın.
Wanted to share a skill I built for designing and reviewing the prompts that run AI agents. Most prompt engineering advice for agents still treats the system prompt as a text block: "write a clear role, add examples, be specific." That helps with a chat answer, but agents fail in ways text-block advice doesn't cover. I kept watching the same three failures: an agent with overla
Vibe-coded projects usually fail in two places. The code is coupled, so one change breaks three things you did not touch. And the UI has no states, so it looks fine until something is empty, slow, or wrong. Two old methodologies fix most of both. Axiomatic design (Nam Suh, 1990) for the first. Don Norman's design criteria for the second. Neither one is new and neither one is ab
Design background here. The request I get most is "can you make this into an infographic," attached to three paragraphs of dense text with no sense of what the one takeaway is. The tool is never the problem. The thinking that has to happen before the tool is the problem. So I wrote a prompt that does the structuring part, the part people skip. It doesn't design anything. It dec
Solo marketing consultant, tool-fatigued, I mostly lurk. But this one earned its keep, so here it is. The problem was never the design of my decks, it was that they read like a table of contents instead of an argument, and clients glaze over by slide four. This prompt turns the strategy doc into a deck built as a case, not a summary. ``` Role: You are a narrative editor for cli
Most people use LLMs in a confirmatorily biased way: "Tell me why my business plan is great" or "How do I implement X?". This triggers the model's RLHF pleasing bias. Inspired by Karl Popper’s principle of falsifiability, a friend and I designed a prompt framework that flips this dynamic. Instead of validating your idea, it forces the AI to act as a harsh auditor and attempt to
I wanted to share a custom skill I created. Many prompt-optimization templates suffer from "bloat"—they often take a simple request and turn it into a massive, overly complex prompt, or they accidentally alter technical details like code snippets, file paths, and generator flags. To solve this, I built a meta-prompting skill designed to classify the context of the user's prompt
i’ve been playing with prompts that take really ordinary objects and push them into a more graphic, poster-like direction. The goal was to make it feel like a mix of screen printing, retro grocery packaging, flat illustration, grainy texture, and editorial poster design. What helped most was keeping the object simple, then adding very specific design cues like barcodes, promo s
Odanızın tek bir fotoğrafını yükleyip ChatGPT'e gerçekçi bir yeniden tasarım önerisi çizdirten, ardından aynı görsele göre 500 dolar altı bütçeyle gerçek, satın alınabilir bir alışveriş listesi çıkarttıran iki adımlı bir prompt.
Most AI workflows right now are designed around passive automation: hand off a task, let the model generate text, copy-paste, and move on. The problem is that over-relying on LLMs for core thinking causes critical thinking and executive function to atrophy. When you use an AI purely as a ghostwriter or answering engine, you're interacting with a system programmed to be sycophan
