Explore curated prompts optimized for Gemini.
Compose grounded, multimodal-friendly prompts for Gemini.
About
What Gemini is good at and how the prompts on this page are tuned.
Gemini is Google's frontier multimodal model — strong at combining text, images and structured data in a single prompt. It's a great pick when your task needs research, grounding or multi-source reasoning.
These prompts are designed to play to Gemini's strengths: clear assumptions, explicit grounding cues and structured output formats that translate well into spreadsheets, docs and decks.
If your workflow involves research, analytics or multimodal inputs, Gemini is often the most efficient model to reach for.
Editorial
This page collects 229 Gemini prompts engineered specifically for Gemini. Every prompt here has been written, tested and tuned to match how Gemini reads instructions, handles structure and responds to constraints — so you get a strong first output without trial-and-error prompting.
These prompts are built for anyone who uses AI in their daily work. They work across the major AI models — ChatGPT, Claude, Gemini and the leading image and video generators — and they hold up whether you're prompting in a chat window, an editor extension or a workflow tool. Use these whenever you'd otherwise stare at a blank page.
Why these prompts work: each one starts with a clear role, names the audience or scene, defines the output format and adds 2–3 hard constraints. That structure is what separates a vague AI answer from a usable one. The library is curated so you don't have to test 30 versions of the same prompt to find the one that actually performs — that work is already done.
Expect outputs that already match your audience, format and tone — so the next step is shipping, not rewriting. You'll occasionally want to regenerate or refine, especially the first time you use a prompt with your own context. Treat each prompt as a starting structure: the variables and constraints stay, the topic and tone become yours.
Read each prompt before you copy it. Swap the placeholders for your real audience, product and constraints, and add one or two AI-specific details from your own brief. The prompts here are designed to be edited — the more context you bring, the stronger the output.
Pair this page with the matching category and use-case hubs to see how Gemini handles specific workflows like cold email, SEO writing, product copy, debugging or cinematic video. Internal links throughout the page point to the next step.
⭐ Editor's Choice
One prompt we'd ship today. Read why it works, see a preview, and copy it in a click.
Why it works · It includes the four things great prompts always include: role, audience, format and constraints.
Best use case
Best for gemini workflows where story-driven linkedin post with a hook, lesson and cta.
Expected output
Output that already matches your audience, format and tone — so the next step is shipping.
Story-driven LinkedIn post with a hook, lesson and CTA.
Popular Categories
Browse prompts by the workflows this model handles best.
Articles, emails, scripts and stories that read like a human wrote them.
Ads, landing pages, SEO and campaigns that actually convert.
Debugging, refactors, code review and architecture prompts.
Strategy, ops, sales decks and financial analysis prompts.
Lesson plans, study aids and explainers for any subject.
Worldbuilding, music, design briefs and creative direction.
Featured Prompts
Eight prompts to copy, tweak and use right now.
Story-driven LinkedIn post with a hook, lesson and CTA.
Three-email welcome sequence for new SaaS users.
Monthly board update with metrics, narrative and asks.
Mixed-format quiz with answer key and rationale.
Production-ready brief for Suno or Udio.
Expanded prompt for in-depth, polished output.
Builds a structured outline you can hand to a writer or another model.
Expanded prompt for in-depth, polished output.
Prompt Writing Guide
Six habits that consistently produce stronger AI output. Apply them to any prompt on this page.
Replace abstract verbs ("help", "improve") with concrete ones ("rewrite", "summarise in 5 bullets"). Specificity is the single highest-leverage habit.
Audience, goal, constraints, prior attempts. Context turns generic answers into ones you can use.
Bullets, table, JSON, markdown, prose. Telling the model what shape the answer should take prevents reformatting later.
Pick 2–3 descriptors. Tone is the difference between an answer and an answer you'd send.
Word limits, banned phrases, required elements. Constraints raise quality more than longer prompts do.
Don't restart the prompt. Reply with "Keep the structure, tighten paragraph 2, add a number to the opening line."
Best Practices
Apply these in every prompt on this page. Small habits, outsized improvements in output quality.
Three lines at the top of every prompt — they do most of the work.
Length, tone, banned phrases. Constraints sharpen output.
One example beats five sentences of description.
Surgical edits converge in two rounds. Rewrites take five.
Avoid These
The same handful of mistakes are responsible for most weak AI output. Catch them before you hit send.
Ambiguity in the prompt becomes ambiguity in the output. State exactly what you want.
Without audience, goal and constraints the AI defaults to the most generic possible answer.
Stacking unrelated jobs in one prompt produces a half-done answer for each. Split them.
If you don't ask for bullets, a table or JSON, you'll get a wall of text.
One example of the desired output is worth a paragraph of description.
Pro Tips
Side-by-side rewrites that show what separates a weak prompt from a great one.
Instead of
“Help me with this.”
Use
“Act as a senior strategist. Here's the situation: [3 sentences]. I need a 5-bullet recommendation, each bullet under 20 words, ranked by impact, and one risk per recommendation.”
Why it works: Role, context, format and constraints turn vague requests into useful answers.
Instead of
“Make this better.”
Use
“Improve this draft by tightening it 25%, replacing weak verbs with stronger ones, and ending each paragraph with a concrete number or example. Return only the revised draft.”
Why it works: Edits are measurable when constraints are explicit.
Instead of
“Summarise this.”
Use
“Summarise this in 5 bullets for a CEO who has 60 seconds. Each bullet under 18 words. End with the single decision the CEO should make.”
Why it works: Format, length and downstream use guide the output.
Instead of
“Give me ideas.”
Use
“Generate 10 ideas for [topic], aimed at [audience], each framed as a question the audience is already asking. Rank by relevance and add one 1-line rationale per idea.”
Why it works: Audience and ranking turn brainstorms into shortlists.
Instead of
“Rewrite this.”
Use
“Rewrite this in the voice of [reference]. Keep the meaning, change the voice. Sentences under 22 words. No filler phrases. Return only the rewrite.”
Why it works: Style transfer plus constraints replicates voice without losing meaning.
Use Cases
Pick the use case closest to what you're working on.
Long-form articles, outlines and intros that rank.
in Writing
Cold outreach, newsletters and customer replies.
in Writing
Keyword clusters, meta tags and on-page briefs.
in Writing
Hooks, beats and full scripts for any niche.
in Writing
Threads, captions and platform-native posts.
in Writing
Landing pages, ads and high-converting CTAs.
in Writing
Related Models
If you like this model, you'll probably want to explore these too.
Collections
Curated groups for different skill levels and goals.
Generate grounded, multimodal-friendly prompts for Gemini.
FAQ
Common questions about using Gemini prompts.
Related searches
Popular searches related to this page. Each one links to the closest matching prompt library.
Browse the full library of curated prompts and find your next starting point.
