Explore the library

Cinematic landscapes and interiors with controllable time-of-day, weather, lens, and atmosphere.

Fill-in-the-blanks recipe for art-directed character concepts with controlled style, lighting, and palette — works in any image model.

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.

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.

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.

Grok is uniquely willing to take a side. This prompt turns it into a hard-hitting columnist who argues a position with evidence, owns the counter-argument, and writes like they mean it — not a chatbot listing pros and cons.

Studio shots are static. Kling can put your product in motion, in context, with people — without a production budget. This prompt covers the lifestyle clip formula used by DTC brands: product in environment, natural interaction, and the ambient detail that makes it feel real.

Each prompt is built around a named poetic technique (enjambment, volta, concrete imagery, controlling metaphor) with a constraint that forces you to practice it. Feedback covers rhythm, sound patterns, and line-break logic — not just 'nice imagery.'

The complete Midjourney recipe: the 8-block prompt anatomy, 3 worked examples across cinematic, fantasy, and product photography, plus every parameter decoded (--style raw, --stylize, --chaos, --ar) so you know exactly which dial to turn.

A camera-and-lens recipe for photoreal images that actually explains WHY focal length, color science, and lighting keywords change the output — not just what to type.

Produces a 7-day program of focused, progressively harder craft exercises aimed at a single weak skill — distinct, constraint-driven drills rather than vague daily prompts.

Modern flat illustrations for blogs, decks, and marketing — consistent style, limited palette, zero clutter.

Go beyond single-style prompts — learn to stack art movements, specify medium textures, and blend references for a look that feels genuinely original.

Sale flyers fail when they try to say too much. This prompt creates high-impact promotional designs built around one clear offer, one strong visual, and a layout that reads instantly — whether printed and taped to a window or posted on Instagram.

Not just the tags — understand WHY each negative token exists, when to adjust CFG vs steps, and how to adapt the template for different styles.

Kling delivers best-in-class slow-motion and fluid physics — but only when you give it ONE subject, ONE continuous action, and ONE camera move. This prompt teaches the structure, pacing controls, and what Kling does better than any other video AI.

A grand opening is your one shot at a first impression. This prompt creates launch-day flyers that feel like an event worth attending — with energy, a clear offer, and a design that says 'this business is worth checking out.'

Design strict, self-validating tool schemas with confidence calibration, discriminated unions, and chain-ready contracts — so your agent calls tools reliably instead of hallucinating arguments.

Product flyers need to do two things fast: make the product look good and make the benefit obvious. This prompt builds a product-focused layout with the right visual hierarchy — product first, benefit second, price and CTA third.

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.

Naming a business is harder than it looks. This prompt generates 20 names across four distinct styles (descriptive, invented, founder-based, metaphor) and scores each on the criteria that actually matter: memorability, spell-ability, and whether the domain is probably available.

A well-designed event poster does more than inform — it sets a mood that makes people want to be there. This prompt builds atmosphere-first poster designs across music, art, food, and community event types.

A customer telling their story is 5x more convincing than you telling people how good your product is. This prompt scripts a first-person customer story video — or coaches you to tell your own story — in the format that builds trust and drives purchases on TikTok.

Runway Gen-3 excels at director-level camera control — but only when you lead with the move. This prompt covers the camera-first template, 3 worked examples, a reliability ranking of camera moves, and what Runway does better than any other generator.

Most business taglines are empty ('Your trusted partner in X'). This prompt generates 15 taglines across three strategies — benefit-led, personality-led, and challenger — so you can pick the line that sounds like your business and not every other business in your category.

A brand poster isn't a flyer — it's a statement about who you are. This prompt creates editorial-quality brand images that work as wall art, social content, and marketing visuals, with the kind of visual quality that makes small businesses look established.

Seasonal promotions need to feel timely, not generic. This prompt builds holiday and seasonal posters that capture the moment — without looking like clip art or stock photos — and work as both printed materials and Instagram posts.

A modular prompt formula that explains HOW generators weight your words and what to do when results miss — with two worked examples across different styles.

A subject + motion + camera + style structure tuned for ByteDance Seedance — with the stability tags that keep motion smooth.

Stop copying random prompts — learn the 7 structural patterns behind every great prompt, with copy-ready examples of each and guidance on when to combine them.

A structured Midjourney/DALL·E recipe for creating event flyers that look professionally designed — with the right color hierarchy, readable typography, and a visual that fits the event's mood, not a stock-photo feel.

Produces a complete, local-first RAG pipeline with document loading, chunking, Ollama embeddings, a vector store, retrieval, and a grounded answer step with citations, requiring no cloud APIs.

Each day uses a proven pedagogical exercise (blind contour, thumbnail compositions, master study, texture collection) with a constraint that teaches a specific skill — plus a reflection prompt to build visual thinking, not just output.

Write Sora prompts like a director's shot list — shot size, camera move, action, lighting, lens — for film-quality clips.

Get a complete, deployable system prompt for a Custom GPT, Gemini Gem, or Claude Project — including the sections most people forget: personality guardrails, the 'don't' list, edge case handling, refusal patterns, and token budget management.

The portrait recipe that separates AI slop from editorial quality — why 85mm flatters faces, why 'sharp focus on the eyes' is the #1 realism trigger, and the --stylize range that controls LinkedIn headshot vs Vogue cover.

Show the AI 2-3 outputs you love; it detects structural, tonal, formatting, and content patterns (plus what the examples consistently AVOID), then writes a prompt that reliably reproduces them — with a consistency confidence score.

One reusable shot template for Sora, Veo, Runway, and Seedance — with the key insight most people miss: video prompts need to describe CHANGE, not a still frame.

Grounded in the three scientifically validated components of self-compassion — self-kindness, common humanity, and mindfulness — this prompt replaces vague 'be kinder to yourself' advice with the 'best friend reframe' and a compassionate letter technique.

Paste a mediocre prompt and get a full diagnosis of its failure modes, a rewritten version with every improvement annotated, and a side-by-side scored comparison so you can see exactly what changed and why it's better.