Web Design
Prompts for planning, structuring and reviewing websites, from first sitemap to accessibility checks.
The AI prompt library
Find the right prompt. Get better results from AI.
66 prompts12 categories5 AI tools coveredFree to copy, no account
Twelve areas of professional work, each with a hub that explains which prompt to reach for.
Prompts for planning, structuring and reviewing websites, from first sitemap to accessibility checks.
Prompts for planning, building and reviewing web applications, from schema and API to React and CSS.
Prompts for drafting, outlining, editing and titling written content from your own material.
Prompts for keyword planning, audits, briefs, on-page edits, links and schema that work from your own data.
Prompts for strategy, personas, social calendars, email sequences, ad copy and product launches.
Prompts for planning, strategy, competitive analysis, fundraising, goal setting and hiring.
Prompts for reviewing literature, summarizing papers, sizing markets, planning interviews and analyzing data.
Prompts for writing, debugging, refactoring and testing code with an AI model.
Prompts for logo briefs, image-generator prompts and brand identity direction.
Prompts for meeting notes, weekly planning and structured decisions, built around your own inputs.
Prompts for planning lessons, building study guides and writing quizzes from your own material.
Prompts for product descriptions, product page audits and customer review analysis.
Editor’s picks: the broadest, most complete prompt in each category. See how we choose them.
Web Design
A structured brief that walks an AI model from business goals to sitemap, page layouts, visual direction and responsive rules.
Web Development
Reviews a diff the way a careful senior engineer would: intent first, findings ranked by severity, each tied to a line with a suggested fix.
Content Writing
Turns your own notes and experience into a focused blog post with one clear argument, and marks every spot where it needs a real example or a fact check.
SEO
Turns seed topics and any keyword data you paste into intent-labeled clusters mapped to pages, without the model inventing search volumes.
Marketing
Turns your business facts into a focused strategy: a diagnosis, one priority segment, positioning, three channels at most, and a phased plan sized to your budget.
Business
Turns your idea, customer and known numbers into a structured plan draft, with every unverified figure flagged instead of invented.
Curated sets that cut across categories, with a note on when to use each prompt.
For entrepreneurs
Prompts for founders and operators: planning, analysis, hiring, goals and the decisions in between.
For designers
Prompts for design thinking in words: structure, critique, systems and briefs that come before or alongside the canvas.
For developers
Prompts for the work around writing code: specifying, reviewing, debugging, testing and documenting decisions.
For educators
Prompts for planning lessons, building study materials and writing assessments you can adapt to your learners.
For marketers
Prompts for planning and producing marketing work, from strategy and personas to campaigns and search content.
For researchers
Prompts for reading, synthesising and analysing material you supply, with guardrails against invented citations.
For writers
Prompts that help with outlining, drafting, editing and headlines without flattening your voice.
The prompts here are written to be model-independent: plain structure, explicit inputs, a stated output format. Each prompt page lists the tools it is expected to work with and any adjustment worth making. A prompt is only labelled Tested for a model when a test record exists.
How to prompt ChatGPT: clear instructions, the right context, and standing preferences set once instead of repeated.
How to prompt Claude: explain the task as you would to a capable colleague, structure long inputs, and show examples.
How to prompt Gemini: specific instructions, stated constraints, a few examples, and the question after the context.
How to prompt Perplexity: ask a precise research question, say which sources count, and check the citations it returns.
Cursor is an AI code editor, not a model. To prompt it well: reference the right files, set project rules, review diffs.
Not sure where to start? Answer eight short questions and get a structured prompt you can copy and edit. Runs in your browser.
Objective, context, role, inputs, constraints and output format assembled into one coherent prompt.
Paste a prompt and get a rule-based checklist of what is missing: context, constraints, format, success criteria.
Compare two versions side by side and see added, removed and restructured instructions.
Taken from the editorial review log. Every entry is a real record with a date and a review type.
| Prompt | Category | Review | Date | Testing status |
|---|---|---|---|---|
| Core Web Vitals Diagnosis Prompt | Web Development | Structural review | Untested | |
| Technical Specification Prompt | Web Development | Structural review | Untested | |
| React Component Prompt | Web Development | Structural review | Untested | |
| Next.js App Router Feature Prompt | Web Development | Structural review | Untested | |
| Relational Database Schema Prompt | Web Development | Structural review | Untested | |
| Responsive CSS Layout Prompt | Web Development | Structural review | Untested |
Guides on the techniques behind the library, grounded in the model vendors’ own documentation.
Guide
The five parts of a complete prompt (goal, context, task, constraints, output format), with a worked rewrite and a pre-send checklist.
Guide
What prompt engineering is, the techniques the major model vendors agree on, the working loop behind them, and what prompting cannot fix.
Technical guide
What a system prompt is, what belongs in it versus the user message, a worked example, and the limits to plan for when building on one.
Guide
A diagnostic approach to weak AI answers: name the fault, trace it to the gap in your prompt, then follow up precisely or rewrite and start again.
We would rather label a prompt honestly than call everything “tested”.
Each prompt starts from a real task and the inputs a practitioner would ask for, with explicit constraints against invented facts and padding.
Every prompt is checked for structure: variables resolve, the output format is stated, limitations are listed and sources are real.
A prompt is labelled Tested only when a test record exists: model and version, inputs, actual output and notes against a seven-point rubric. No invented scores.
Prompts are versioned. When a model changes or feedback points to a problem, the prompt is flagged for retesting and the label changes with it.