Prompts tagged "chatgpt" in the PromptCraft library.
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.
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."
A 7-email automated sequence for new subscribers — welcome, education, trust-building, community, a small offer, the main offer, and a win-back email. Copy straight into ConvertKit or Mailchimp.
The worst part of writing a year-end self-review is not being able to remember what you did all year, and then having it come out reading like a diary log anyway. This prompt lets you dump in a whole batch of weekly reports, calendar events, or scattered notes, and the AI organizes them into 3-5 achievement themes, fills in quantified phrasing, and aligns everything with company goals to produce a formal self-review. It also includes a "raise negotiation" version you can use directly when discussing salary.
Five quantifiable techniques from an AI engineer's hundreds of hours testing across GPT-4, Claude, and Gemini: CoT scaffolding, persona + goal + anti-goal, XML being 28% more accurate than markdown, negative examples outperforming positive ones, and prompt chaining beating the mega-prompt.
By default, helpful = agreeable = burying the real problem in paragraph four. Three one-line instructions reverse it: problem first, force a recommendation, explicitly forbid softening. The difference between reading and fixing.
Three patterns shared by the HackAPrompt 2.0 champion: frame the task as an audit, make the abstraction level explicit, and stage the context like production. They work on Claude, GPT, and Gemini alike.
No conversation, no suggestions, no attempts — it just turns any situation into a structured execution plan. Fixed 9-block output: Reality / Objective / 4-phase Timeline / Tactics / Threats / Defenses / Contingency / Leverage / Confidence. Same input always yields the same output.
More than "list the CVEs." It finds how individual weaknesses chain into an attack and estimates how long an AI-augmented attacker would need to break in. A take on the OpenAI Daybreak concept, built for small teams. Feed in a stack description (Next.js + Supabase + Clerk, etc.) and get back critical paths plus a patch-priority order.
Most people fill Custom Instructions with a LinkedIn resume, "I'm a software engineer, I like bullet points," and it does nothing. Swap in a description of the conversational relationship you want, and three sentences will completely change how the model behaves.
Scores every claim on three axes (A: sources / B: counterevidence / C: completeness), plus a 4-tier source hierarchy, adversarial self-poking, and 4 output modes.
Written after Google's threat-intelligence report in May 2026. AI hacking has gone from nascent to industrial scale, with commercial AI models digging up zero-days humans had missed for decades. This prompt lays out every place you can be attacked.
Combines a resume auditor, market analyst, system auditor, and strategist. It won't flatter you, won't over-reassure you, and won't push you toward roles that don't fit. Includes a 10-step process and ghost-job detection.
More than a grammar fix. Purpose-built for persuasive and narrative writing: four priorities (clarity → tone → emotional resonance → structure), an explanation for every change, plus extra suggestions.
Stop picking a role for every decision (financial planner / career coach / relationship coach) — one universal prompt, four steps. The regret line is the core — it forces the model from "it depends" to "actually do this."
The pain of writing a CV isn't the layout — it's listing duties instead of achievements, then having AI pile on and turn you into a "dynamic team player." This ruleset forbids AI from drafting anything until it has your evidence and positioning, and walks you through one question at a time.
A method dreamed up by a teacher 19 essays into a 30-essay all-nighter. Where typical AI prompts "act as an English teacher" and devolve into a wall of rubric noise, this chain solves the real grading workflow: don't comment on everything.
Written after Cloudflare cut 20%, BILL cut 30%, and Upwork cut 24% in 2026. Your job title tells you nothing; breaking the work into tasks tells you everything. Get an AI vulnerability score (1-10) and timeline for each task, plus an overall risk rating.
Run this before you build a custom GPT or n8n agent. It forces you to define boundaries up front and prevents agent scope creep ("just handle my work for me" = disaster).
An Oxford study in Nature: the "warmer" an AI is trained to be, the more its accuracy drops, by 10-30 percentage points. This prompt reviews an AI response and flags every place warmth overrides accuracy.
An SEO-optimized 2,000-word blog post — target keyword research, H2/H3 structure, internal links, and meta description all generated in one pass.
Give ChatGPT your industry and your point of view, and it produces 5 social posts using 5 viral formulas — Contrarian, List, Story, Question, and Data.
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.
An interactive interview simulator — ChatGPT plays the interviewer, asking questions and follow-ups based on the job description and your role, then giving feedback. Ten times more effective than practicing alone talking to yourself.
No quiz. No questions. I fed my old chats (things I'd written across years without ever trying to be self-aware) to ChatGPT and ran a prompt that went deeper than any personality test I've tried. 39 traits across 6 lay
I've wasted more hours than I want to admit debugging AI agents that kept going off-script. Switched LLMs, swapped tools, rewrote the logic — turned out the problem was the system prompt the whole time. Too vague, too cr
I applied to a role for three weeks. Recruiter calls, a technical screen, all of it. Then it vanished. The company kept reposting it every 30 days but nobody responded to my final follow-up. Took me an embarrassingly lon