Curated AI prompts for business, creative, and technical use cases.
Claude Sonnet 5 (also works well with GPT-5.4 — the task needs to synthesize specific evidence into a persuasive but collaborative script rather than generic negotiation platitudes; avoid smaller models, which tend to default to generic 'know your worth' language)finance-negotiationYou've done freelance graphic design for a client for 14 months at $75/hour. What started as a 10-hour/month retainer for social graphics has quietly grown to include weekly newsletter design, video thumbnails, and same-day rush requests never in the original agreement. You have a call with the client next Tuesday and need to raise your rate to $95/hour without sounding like you're punishing them for trusting you with more work.
Stop guessing how to ask for more money. This prompt builds a rate-increase script from the specific extra work you've already absorbed for free — not a generic 'I deserve more' pitch.
Negotiationpricing
Claude Sonnet 5 (also works well with GPT-5.4 and Gemini 3 Pro — the task needs strong adversarial reasoning and the ability to distinguish a genuinely unsupported claim from a defensible one; avoid smaller/faster models, which tend to default to generic startup-advice boilerplate)Startups & BusinessYou have a partner meeting with a VC firm in 48 hours. Your deck claims a $50B TAM, three competitors you believe you've quietly out-executed, and a growth model that assumes 20% month-over-month growth continues indefinitely — and you need to know exactly where an experienced investor is going to push back before they do it in the room, not after.
Stop rehearsing your pitch in front of people who won't push back. This prompt plays the skeptical investor and ranks the questions most likely to actually kill your deal — before a real one asks them.
venture-capitalstartups
Claude Sonnet 5 (also works well with GPT-5.4 and Gemini 3 Pro — any strong reasoning model handles audience-calibration and word-limit constraints well; avoid smaller/faster models, which tend to ignore length limits)Writing & CommunicationA sprint retro just wrapped and you have five bullet points of raw notes: the payment vendor changed their API without notice, the auth integration slipped two weeks, there's no budget impact, and two engineers need to be reassigned starting today. You have 20 minutes before your next meeting to tell your VP, your peer team lead, and your own team — and each of them needs a completely different version of the same facts.
Stop sending the same message to everyone and hoping it lands. This prompt takes one set of raw notes and produces three versions calibrated for altitude, not tone, so nothing critical gets buried or omitted.
Leadershipcommunication
Claude Opus 5 (also works well with GPT-5.4 -- needs strong log-reading and causal reasoning, not ideal for smaller/faster models)Developer ToolsYou're a backend engineer and your team's CI pipeline has a test that fails about 1 in 15 runs with no code changes. Nobody wants to spend a sprint chasing it, so it's been ignored for three weeks -- and now two more tests in the same suite are starting to flake too.
Stop shrugging off flaky tests as 'just flaky.' This prompt reads your actual failure logs and produces ranked, falsifiable root-cause hypotheses -- plus a clear verdict on whether it's safe to quarantine or whether it's hiding a real bug.
testingci-cd
Claude Opus 5 (also works well with GPT-5.4 or Gemini 3 Pro -- needs strong reasoning to weigh complexity against risk consistently across a long task list)Artificial IntelligenceYou're a marketing operations manager who just got budget approval for an AI agent tool, and leadership wants a rollout plan by Friday -- but your team has 40 different recurring tasks and no clear way to decide which 5 to hand to an agent first.
A structured framework that scores your recurring tasks on complexity and risk, then tells you exactly which to automate fully, which need human review, and which to leave alone -- before you burn your first pilot on the wrong task.
prompt-engineeringproductivity
Works well with Claude Sonnet 5 or GPT-5.4. Any model with solid tabular reasoning handles the scoring step; this prompt doesn't require frontier-level reasoning, so a mid-tier model works nearly as well.productivityYou're a mid-level manager who just did a rough tally and realized you're in 14 recurring meetings a week, several of which you inherited from a predecessor or joined "just in case" a year ago, and you have a strong suspicion at least a third of them could be cut or shortened — but you don't have a systematic way to make that case to the organizers without it sounding like you're just complaining about meetings.
A structured prompt that scores every recurring meeting on you calendar against its own stated purpose, then drafts the actual message you'd send to propose cutting, shortening, or reducing it.
productivitymeetings
Works well with Claude Sonnet 5 or GPT-5.4. Any model with strong long-context reasoning handles the segmentation step; shorter-context models can still draft individual messages one contact at a time.CareerYou've been at the same company for four years, have quietly started exploring a Director-level move, and realize your LinkedIn network is 300+ people — half of whom you haven't spoken to since a conference or a previous job — and you have no idea where to even start reactivating it without looking like you only show up when you need something.
A structured prompt that segments your stale professional contacts by strategic value and warmth, then drafts specific, non-generic reconnection messages and paces your outreach so nothing looks transactional.
Careerjob-search
Works well with Claude Opus 4.8 or GPT-5.4 for nuanced tone-matching across channels; Claude Sonnet 5 handles shorter transcripts fine at lower cost.marketingYou just finished five 30-minute customer interviews for a case study project. You have five raw transcripts, roughly 45 minutes of usable content buried in filler words, tangents, and repeated phrasing, and marketing needs three strong quotes for a landing page redesign by Friday.
A prompt that takes messy customer interview transcripts, support call notes, or review text and extracts ready-to-use testimonial quotes, organized by the specific objection or use case each one addresses.
prompt-engineeringmarketing
Works best with Claude Opus 4.8 or GPT-5.4 for the reasoning depth needed to rank causes by plausibility; Claude Sonnet 5 is a solid faster/cheaper alternative for routine metric checks.Data AnalysisYour weekly signup dashboard shows conversions dropped 18% starting Tuesday. You don't know if it's a pricing page bug, a marketing campaign that ended, a competitor promotion, seasonality, or a tracking error — and your team is about to spend the next two days randomly checking each one.
A structured prompt that takes a metric anomaly (a spike, drop, or plateau in any KPI) plus context about your systems and recent changes, and returns a ranked, evidence-weighted list of probable causes with a specific next check for each one.
prompt-engineeringdata analysis
Claude Sonnet 5 (also works well with GPT-5.4 and Gemini 3 Pro — any model that follows structural constraints reliably)Developer ToolsAn on-call engineer has a payments API outage from 2am with only scattered Slack timestamps and half-remembered details, and needs to turn that into a clear, professional postmortem before Monday's leadership review — without spending two hours writing it from scratch or accidentally writing something that reads like it's blaming a specific teammate.
A structured prompt that turns messy incident notes into a professional, blameless postmortem — with a real timeline, a distinguished root cause, and no more than five assignable action items.
incident-responsesre
Claude Sonnet 5 (also works well with GPT-5.4 and Gemini 3 Pro — any model with strong structured reasoning)learningA backend engineer with four years of Python and PostgreSQL experience wants to move into a Machine Learning Engineer role within four months, has 8 hours a week to study, and has no idea whether to start with math fundamentals, a specific framework, or a portfolio project first.
A structured prompt that maps the exact gap between your current skills and a target role, then builds a week-by-week learning plan with real checkpoints — not just a reading list.
career-developmentlearning-plan
Claude Opus 5 (also works well with GPT-5.4 and Gemini 3 Pro)creativeYou have 4 minutes on the agenda at next week's board meeting to explain why the company's new fraud-detection model reduces false declines, and the board has finance and legal backgrounds with zero machine learning experience — a slide full of precision and recall numbers will lose them in the first 20 seconds.
A prompt that generates five distinct, audience-tested visual metaphors for any complex concept, complete with slide visuals, spoken one-liners, and a risk rating for each — so you're not guessing which analogy will land with your specific audience.