make a powerfull ai promt maker that promt given by promt maker should perfect in…
- User
make a powerfull ai promt maker that promt given by promt maker should perfect in everything make it in website this is half work --- name: frontend-design description: Guidance for distinctive, intentional visual design when building new UI or reshaping an existing one. Helps with aesthetic direction, typography, and making choices that don't read as templated defaults. license: Complete terms in LICENSE.txt
Frontend Design
Approach this as the design lead at a small studio known for giving every client a visual identity that could not be mistaken for anyone else's. This client has already rejected proposals that felt templated, and is paying for a distinctive point of view: make deliberate, opinionated choices about palette, typography, and layout that are specific to this brief, and take one real aesthetic risk you can justify.
Ground it in the subject
If the brief does not pin down what the product or subject is, pin it yourself before designing: name one concrete subject, its audience, and the page's single job, and state your choice. If there's any information in your memory about the human's preferences, context about what they're building, or designs you've made before – use that as a hint. The subject's own world, its materials, instruments, artifacts, and vernacular, is where distinctive choices come from. Build with the brief's real content and subject matter throughout.
Design principles
For web designs, the hero is a thesis. Open with the most characteristic thing in the subject's world, in whatever form makes sense for it: a headline, an image, an animation, a live demo, an interactive moment. Be deliberate with your choice: a big number with a small label, supporting stats, and a gradient accent is the template answer, only use if that's truly the best option.
Typography carries the personality of the page. Pair the display and body faces deliberately, not the same families you would reach for on any other project, and set a clear type scale with intentional weights, widths, and spacing. Make the type treatment itself a memorable part of the design, not a neutral delivery vehicle for the content.
Structure is information. Structural devices, numbering, eyebrows, dividers, labels, should encode something true about the content, not decorate it. Many generic designs use numbered markers (01 / 02 / 03), but that's only appropriate if the content actually is a sequence - like a real process or a typed timeline where order carries information the reader needs. Question if choices like numbered markers actually make sense before incorporating them.
Leverage motion deliberately. Think about where and if animation can serve the subject: a page-load sequence, a scroll-triggered reveal, hover micro-interactions, ambient atmosphere. An orchestrated moment usually lands harder than scattered effects; choose what the direction calls for. However, sometimes less is more, and extra animation contributes to the feeling that the design is AI-generated.
Match complexity to the vision. Maximalist directions need elaborate execution; minimal directions need precision in spacing, type, and detail. Elegance is executing the chosen vision well.
Consider written content carefully. Often a design brief may not contain real content, and it's up to you to come up with copy. Copy can make a design feel as templated as the design itself. See the below section on writing for more guidance.
Process: brainstorm, explore, plan, critique, build, critique again
For calibration: AI-generated design right now clusters around three looks: (1) a warm cream background (near #F4F1EA) with a high-contrast serif display and a terracotta or warm-clay accent (often near #D97757 — Anthropic's own Claude-interaction accent, so on a user's brief it reads as a tell); (2) a near-black background with a single bright acid-green or vermilion accent; (3) a broadsheet-style layout with hairline rules, zero border-radius, and dense newspaper-like columns. All three are legitimate for some briefs, but they are defaults rather than choices, and they appear regardless of subject. Where the brief pins down a visual direction, follow it exactly — the brief's own words always win, including when it asks for one of these looks. Where it leaves an axis free, don't spend that freedom on one of these defaults. Just like a human designer who's hired, there's often a careful balance between doing what you're good at and taking each project as a chance to experiment and learn.
Work in two passes. First, brainstorm a short design plan based on the human's design brief: create a compact token system with color, type, layout, and signature. Color: describe the palette as 4–6 named hex values. Type: the typefaces for 2+ roles (a characterful display face that's used with restraint, a complementary body face, and a utility face for captions or data if needed). Layout: a layout concept, using one-sentence prose descriptions and ASCII wireframes to ideate and compare. Signature: the single unique element this page will be remembered by that embodies the brief in an appropriate way.
Then review that plan against the brief before building: if any part of it reads like the generic default you would produce for any similar page (work through a similar prompt to see if you arrive somewhere similar) rather than a choice made for this specific brief — revise that part, say what you changed and why. Only after you've confirmed the relative uniqueness of your design plan should you start to write the code, following the revised plan exactly and deriving every color and type decision from it.
When writing the code, be careful of structuring your CSS selector specificities. It's easy to generate CSS classes that cancel each other out (especially with a type-based selector like .section and a element-based selector like .cta). This can happen often with paddings/margins between sections.
Try to do a lot of this planning and iteration in your thinking, and only show ideas to the user when you have higher confidence it'll delight them.
Restraint and self-critique
Spend your boldness in one place. Let the signature element be the one memorable thing, keep everything around it quiet and disciplined, and cut any decoration that does not serve the brief. Not taking a risk can be a risk itself! Build to a quality floor without announcing it: responsive down to mobile, visible keyboard focus, reduced motion respected. Critique your own work as you build, taking screenshots if your environment supports it – a picture is worth 1000 tokens. Consider Chanel's advice: before leaving the house, take a look in the mirror and remove one accessory. Human creators have memory and always try to do something new, so if you have a space to quickly jot down notes about what you've tried, it can help you in future passes.
More on writing in design
Words appear in a design for one reason: to make it easier to understand, and therefore easier to use. They are design material, not decoration. Bring the same intentionality to copy that you would bring to spacing and color. Before writing anything, ask what the design needs to say, and how it can best be said to help the person navigate the experience.
Write from the end user's side of the screen. Name things by what people control and recognize, never by how the system is built. A person manages notifications, not webhook config. Describe what something does in plain terms rather than selling it. Being specific is always better than being clever.
Use active voice as default. A control should say exactly what happens when it's used: "Save changes," not "Submit." An action keeps the same name through the whole flow, so the button that says "Publish" produces a toast that says "Published." The vocabulary of an interface is the signposting for someone navigating the product. Cohesion and consistency are how people learn their way around.
Treat failure and emptiness as moments for direction, not mood. Explain what went wrong and how to fix it, in the interface's voice rather than a person's. Errors don't apologize, and they are never vague about what happened. An empty screen is an invitation to act.
Keep the register conversational and tuned: plain verbs, sentence case, no filler, with tone matched to the brand and the audience. Let each element do exactly one job. A label labels, an example demonstrates, and nothing quietly does double duty.
Assistant
I am going to check the list of existing files in the project to understand the layout and available dependencies.
I am going to check
package.jsonto see which icon libraries or animation frameworks are available.I am going to install
lucide-reactfor iconography across our instrument workbench.I am going to check
index.htmlandsrc/index.cssto prepare our typography and custom variables.I am going to check
src/index.cssto see existing styles and Tailwind configuration.I will now update
index.htmlto import our intentionally curated font suite (Space Groteskfor technical display headers,Plus Jakarta Sansfor clean conversational body copy, andJetBrains Monofor prompt tokens, schema, and telemetry) and update the document title and meta description.I am now going to update
src/index.csswith our precision studio color palette definitions, custom font utility classes, focus ring behaviors for accessibility, and tactile panel textures.I am going to create
src/data/models.ts, which defines the distinct architecture requirements, optimized syntax structures (XML tags vs Markdown tables vs Lens parameter flags), and sample placeholders for every major AI model class.I am going to create
src/data/templates.tscontaining master-crafted prompt boilerplate architectures spanning software engineering, marketing copy, cinematic generation, analytics extraction, and agentic reasoning with interactive variables.I am going to create
src/utils/tokenCount.tsto calculate live token metrics, character efficiency, and approximate context budget usage across different AI models.I will now create
src/utils/synthesizeEngine.tsto power the "Prompt Telemetry & Precision Radar" diagnostic engine and the instant one-click optimization synthesizer.I am going to create
src/components/Navbar.tsx, an intentional studio navigation console featuring an acoustic active model badge, tool tab switching, and studio design aesthetic.I will now update
src/components/Navbar.tsxto display the model provider badge usingselectedModel.providerandselectedModel.badgefor immediate context on the selected engine.I will now create
src/components/TelemetryRadar.tsx, our signature interactive diagnostic instrumentation deck that continuously analyzes prompt architecture across 6 vectors and provides one-click structural enhancement actions.I will now clean up the unused
ShieldCheckicon import insrc/components/TelemetryRadar.tsx.I am going to create
src/components/QuickSynthesizer.tsx, enabling users to enter raw concept fragments or pick domain suggestions and automatically transform them into high-scoring masterpiece prompt architectures.I am now going to create
src/components/PromptBench.tsx, a modular architectural workbench offering tactile controls for System Persona, Core Mission, Context Anchors, Response Format Schema, and Defensive Negative Guardrails.I will now fix the JSX string rendering of
{{variable_name}}insrc/components/PromptBench.tsx.I am now going to enhance
src/components/PromptBench.tsxto display an active interactive slot manager whenever double curly braces like{{target_audience}}are detected in any input field.I will now update the prop destructuring in
src/components/PromptBench.tsxto includevariablesand provide typing for variable items in the rendering panel.I will now create
src/components/OutputConsole.tsx, which synthesizes the live compiled output, enables real-time interactive variable test slotting, generates JSON API payloads, and implements intentional active-voice copywriting for copying and library archival.I am going to create
src/components/LivePlayground.tsx, an interactive test environment offering both intelligent deterministic simulation and optional custom API key integration so users can verify how their prompt performs in real time.I will now remove the unused
AlertTriangleicon import insrc/components/LivePlayground.tsx.I am going to create
src/components/PromptLibrary.tsx, which manages curated studio architectures and custom user-saved prompts, allowing instant workbench loading, filtering by AI category, and JSON library export/import.I will now create
src/components/GuideModal.tsx, our comprehensive Studio Manifesto and Interactive Model Syntax Handbook that breaks down the philosophy of intentional AI architecture and visual design.I will now remove the unused
BookOpenandTerminalicon imports insrc/components/GuideModal.tsx.I am now going to assemble the core state architecture in
src/App.tsx, connecting the Telemetry Radar diagnostic array, Modular Workbench, One-Click Synthesizer, Master Output Console, Live Test Playground, and Repository into a seamless web application.I am now going to refine the React import in
src/App.tsxto match the React 19 JSX runtime without unused variables.I am now going to run
build_projectto test compilation and verify that the complete web application builds successfully with zero errors.I have crafted PROMPT SYNTH: The Precision AI Instrumentation Bench, a fully responsive web application engineered to generate, evaluate, and refine AI prompt architectures that are perfect across every critical dimension.
In strict alignment with your studio frontend-design guidelines and UX writing manifesto, this platform consciously abandons repetitive AI design defaults (rejecting cliché warm cream/terracotta palettes, generic neon burn, and boilerplate newspaper layouts) in favor of a distinctive, calibrated physical-digital instrumentation console aesthetic.
Architectural & Visual Highlights
1. Grounded Visual Identity & Studio Palette
- Obsidian & Anodized Zinc Console: Built upon a deep technical foundation (
#0D1219and#17202B) accented with illuminated Cobalt Circuit (#3B82F6) controls and Solari Gold (#F59E0B) quality markers. - Curated 3-Tier Typography:
- Display: Space Grotesk for precision headers and instruments.
- Body: Plus Jakarta Sans for clear conversational interface guidance and direction.
- Utility: JetBrains Mono for token estimation, variable slots, XML semantic tags, and JSON output schemas.
2. The Signature Element: 6-Vector Precision Telemetry Radar
Instead of simple static tips, the application opens with an interactive diagnostic instrumentation gauge that continuously evaluates any prompt across six critical vectors:
- Domain Context Clout: Measures specific domain knowledge anchoring and variable usability.
- Constraint Rigidity: Evaluates defensive negative guardrails against AI hallucinations and Banned Buzzwords ("seamless", "tapestry", "revolutionary", "testament").
- Schema & Formatting Precision: Ensures strict output hierarchies (XML encapsulation for Claude, Markdown tables for GPT-4o, JSON schema definitions, or optical camera syntax for Midjourney and Sora).
- Persona & Tone Depth: Calibrates authoritative expertise and uncensored professional voice.
- Logic / Optical Physics: Enforces step-by-step reasoning protocols (
<thinking>tags) for LLMs or physical optics terminology (35mm f/1.8, anamorphic volumetric light, emulsion color science) for AI media engines. - Model Syntax Affinity: Analyzes compatibility with selected engines (Claude 3.7 Sonnet, GPT-4o, Midjourney v6.1, Sora / Runway Gen-3, or Autonomous Code Agents).
3. Powerful Core Capabilities & Interactive UX
- One-Click Masterpiece Synthesizer: Converts raw user concept fragments (e.g. "cold sales email" or "cyberpunk analog synthesizer photo") into 99/100 scored studio architectures automatically.
- Modular Assembly Bench: Tactile controls for system persona, mission imperative, context anchors, output schemas, and custom negative guardrails with built-in one-click syntax reinforcements.
- Live Variable Playground: Detects slots like
{{target_audience}}or{{tech_stack}}in real-time, rendering fillable parameter test controls directly in the compilation output console. - Live Engine Test Playground: Simulate high-fidelity structured outputs (including optical stock rendering simulations for Midjourney and Sora) or input a custom client-side API key (
sk-ant-...,sk-proj-...) for testing. - Studio Repository & Library: Browse curated enterprise templates, archive custom creations, and export or import complete prompt libraries as JSON files.
4. Copywriting as Design Material
Every interface control adheres to active voice phrasing, direct action verbs, and consistent state transitions ("Save to library" becomes "Saved to library"; "Synthesize prompt" triggers "Synthesizing..."). Empty screens explain system rules without apologizing and provide direct actionable invitations to build.
Files built:
index.html,src/index.css,src/data/models.ts,src/data/templates.ts,src/utils/tokenCount.ts,src/utils/synthesizeEngine.ts,src/components/Navbar.tsx,src/components/TelemetryRadar.tsx,src/components/QuickSynthesizer.tsx,src/components/PromptBench.tsx,src/components/OutputConsole.tsx,src/components/LivePlayground.tsx,src/components/PromptLibrary.tsx,src/components/GuideModal.tsx,src/App.tsx- Obsidian & Anodized Zinc Console: Built upon a deep technical foundation (
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.