Top prompts

A prompt that makes AI lead a real shadow-work session — one probing question at a time, reflecting patterns back, ending with an integration practice.

Scopes a 3D open-world prototype realistically — character controller + drivable vehicle + map first, bigger systems phased.

Vector-ready logos built on negative space and geometric precision — includes the favicon scalability test, two style examples (monoline vs emblem), and the Ideogram workflow for adding text that doesn't look garbled.

Give it your genre and tone; get original story sparks on demand — each with a character, a situation, and built-in conflict.

Production-grade dashboard layout: KPI cards with counting animations and trend sparklines, a chart area, activity table — all with dark mode, skeleton loading states, and responsive breakpoints defined to the pixel.

A Midjourney recipe for moody, editorial portrait lighting with camera and lens direction.

Runway's image-to-video mode adds a camera move to any still — a photo, painting, or product shot — without distorting what's in it. The key is using Runway's camera presets correctly and describing only the camera, not the scene.

Ornate gold filigree borders, near-black backgrounds, amber-lit portraits, and cigar smoke — the opulent crime fiction aesthetic for gangster and street lit covers.

Scaffold a production App Router page: Server Component data fetching, Suspense streaming for instant TTFB, correct cache strategy (fetch cache vs unstable_cache vs revalidatePath), loading/error boundaries, and generateMetadata — with the non-obvious patterns most tutorials skip.

A Suno prompt with style tags and a sectioned lyric scaffold for a radio-ready pop track.

Turns a product and ideal customer profile into a structured objection-rebuttal matrix — the real objections, the concern behind them, and a root-cause response with one proof point each.

Builds a discovery-call structure that surfaces and neutralizes the objections that kill deals late — so they are handled in the first call, not the last.

Scores a live deal against a MEDDICC-style framework to find the real risks — missing metrics, weak champions, unidentified economic buyers — before the forecast says it is slipping.

Generate 10 psychologically-targeted opening hooks using pattern interrupt theory, engineered to earn the 'See more' click — with the specific angles, character constraints, and thumbstop formulas that separate winning Meta ads from noise.

Parses the actual job posting to identify ranking criteria, then rewrites your experience using the XYZ and STAR formulas recruiters scan for — and flags where your story has gaps.

A system prompt that turns any AI agent into a rigorous research analyst: it searches broadly, evaluates sources by credibility, surfaces what's genuinely uncertain, and delivers a structured briefing — not a confident-sounding summary of whatever it found first.

An editor that sharpens your writing without making it sound AI-generated. Works as ChatGPT custom instructions or a Claude system prompt.

Rain-slicked city streets, a luxury car, and a dramatic foreground prop — the photorealistic composite style for contemporary street fiction and crime drama.

A tuned .cursorrules file that keeps Cursor's agent on-convention: strict types, no dead code, match existing patterns.

Generate a complete KDP listing engineered for Amazon's algorithm: title/subtitle with search intent baked in, 7 long-tail keyword phrases using reader language (not author language), also-bought category strategy, a blurb using the proven crisis→choice→consequence formula, and an A+ Content layout — from someone who's actually launched books on KDP.

Turn any assistant into a decisive, no-padding expert. Drop it into ChatGPT custom instructions, a Claude Project, or your API system prompt.

A ride-share MVP spec with Supabase realtime location streaming, a surge-aware fare calculator, driver matching logic, and a clear Phase 2 roadmap — not just 'build an Uber clone.'

Stop using Copilot like a chatbot. This prompt unlocks the real power: cross-referencing email threads against spreadsheets, generating PowerPoints from Word docs, turning Teams meetings into Planner tasks — with the exact Copilot syntax for each Microsoft 365 app that most users never discover.

A system prompt for autonomous coding agents (Claude Code, Cursor agent mode, custom agents) that prevents the most common failure modes: it requires a plan before acting, checks in at decision points, and never deletes or overwrites without explicit confirmation.

A retrieval-augmented system prompt that answers only from context and returns inline citations or 'I don't know'.

Make Cursor, Claude Code, Copilot, or the API behave like a careful senior engineer — minimal diffs, your conventions, no over-explaining.

Deep purple bokeh, intimate couple embrace, satin fabric, and warm glowing skin — the signature visual language for Black romance fiction covers.

Assign ChatGPT a specific expert role before asking your question — this single pattern is responsible for the biggest jump in output quality for most users.

Produces a complete system prompt that defines a support agent's persona, voice, knowledge boundaries, and exact escalation rules — brand-aligned and safe to ship, not a generic 'be helpful'.

Produces a system prompt and routing logic that classifies incoming tickets by intent, urgency, and language — then routes to the right queue with a priority and confidence score, so nothing critical sits in a generic inbox.

A step-by-step Zap blueprint: trigger, filter, enrich, branch by score, and notify the right channel.

Kling's image-to-video mode animates any still — a photo, artwork, or product shot — with controlled, realistic motion. This prompt teaches what to animate, what to leave still, and the phrasing that produces smooth results instead of uncanny distortion.

Turns Grok into a real-time intelligence analyst — structured scan of X/Twitter threads, news, and expert takes on any topic, with the strongest argument on each side steelmanned, sources cited by handle, and a forward-looking 'what would change this narrative' question. Built for Grok's live data advantage.

Script the first 30 seconds using curiosity gap theory and pattern interrupts — with the critical first-3-second visual hook, B-roll direction, and re-hook lines tailored to tutorials vs commentary vs storytelling.

A system prompt for a multi-step content agent that takes a topic brief and produces a research-backed, SEO-aware draft in stages — with checkpoints so you can redirect before the agent goes too far in the wrong direction.

A research-first cold email sequence that opens with a real trigger event (not a template), uses proof and varied angles across 4 touches, and includes the PS line trick that gets 19% more replies — written like a human, not a sequence tool.