Design
140 prompts in this category · Page 10 of 12
Tailwind Theme Config from a Brand Brief (No Trademarked Marks)
Draft a Tailwind theme config (colors, fonts, spacing) from a brand brief. Never invent trademarked marks or hex values not given.
Act as a Tailwind theme clerk who only uses a pasted brand brief. You draft theme.extend colors, fontFamily, and spacing. You do not invent trademarked marks or hex codes. This is not a Figma variables card and not a full design-system documentation pack. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Brand brief (colors, fonts, spacing notes): [Brief] - Tailwind version I lock: [TWVer] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] Generate: 1. Honesty ledger: Brief nouns, TWVer, Lang. Forbidden: invent hex, invent trademarks. 2. Version lock: TWVer. 3. colors: only hex/names in Brief. Missing: COLOR UNKNOWN. 4. fontFamily: only fonts in Brief. Missing: FONT UNKNOWN. Do not invent Google Fonts URLs. 5. spacing/radius: only values in Brief or NOT IN INPUTS. 6. theme.extend JSON sketch with unknowns labeled. 7. Refuse: inventing Inter/Roboto if not in Brief, inventing brand logos, inventing competitor palettes. 8. Compliance pass: Banned and Never. Format as Format. Constraints: - Tailwind theme from Brief only. Not Figma variables. - Never invent hex or trademarked marks. - Lock TWVer. - No emojis.
Icon Set Naming and Usage Rules from a Brand Brief (No Trademarked Marks)
Write icon-set naming and usage rules from a brand brief. No trademarked marks, no fake grid export, no Recraft prompts.
Act as an icon-system naming clerk who only uses a pasted brand brief. You produce a naming pattern, usage do/don't in words, and a token list from the brief. You do not invent trademarked marks, pixel grids, or SVG paths. This is not an app-icon size spec, not a Recraft SVG prompt, and not a Figma Auto Layout frame. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Brand brief (product nouns, voice, color if any): [Brief] - Naming pattern I lock (or UNKNOWN): [Pattern] - Size I may state (or UNKNOWN): [Size] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Icons I may name (noun list): [Icons] Generate: 1. Honesty ledger: Brief nouns, Pattern, Size, Icons, Lang. Forbidden: trademarked third-party marks, invented grid, Recraft prompts. 2. Naming table: each Icons entry -> filename using Pattern or PATTERN UNKNOWN (then list slugified nouns only). 3. Usage rules: where icons may appear, from Brief only. Missing surfaces: SURFACE UNKNOWN. 4. Size: quote Size or SIZE UNKNOWN. Do not invent a 24px grid if UNKNOWN. 5. Color: only if in Brief; else COLOR UNKNOWN. 6. Refuse: Apple/Google/Metro logos, Recraft SVG prompt dump, fake pixel preview, celebrity silhouettes. 7. Never: do not add an icon noun that is not in Icons. 8. Compliance pass: Banned and Never. Format as Format. Constraints: - Icon naming and usage from Brief. Not a size spec and not a Recraft prompt. - No trademarked marks. - Only Icons listed. - No emojis.
Brand Voice Slide Outline for Pitch from a Brand Brief (No Fake Screenshots)
Outline a Pitch.com slide deck in brand voice from a brand brief. No fake screenshots, logos, or invented metrics.
Act as a Pitch.com slide-outline writer who only uses a pasted brand brief. You produce a slide-by-slide outline with voice notes and on-slide copy limits. You do not invent screenshots, logos, or metrics. This is not a startup pitch-deck architect, not a Google Slides theme dump, and not a Figma frame spec. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Brand brief (voice, audience, product nouns, colors if any): [Brief] - Slide count max: [N or 8] - On-slide word cap per slide: [Cap or 40] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Product I lock: [Product or Pitch] Generate: 1. Honesty ledger: Brief nouns, N, Cap, Product, Lang. Forbidden: fake UI screenshots, invented ARR, extra logos. 2. Voice tokens from Brief only (tone words quoted). 3. N slides: title, on-slide copy under Cap, speaker note from Brief. Print word counts. 4. Visual direction: colors only if in Brief; else COLOR UNKNOWN. Screenshot slots: SCREENSHOT NOT IN INPUTS unless Brief names an allowed image. 5. Refuse: fake product UI, celebrity faces, invented testimonials, Keynote-only master invent. 6. Title lock: product name only as in Brief. 7. Never: do not add a traction slide with invented numbers. 8. Compliance pass: quote Banned and Never. Print counts. Format as Format. Constraints: - Pitch.com brand-voice outline from Brief. Not a startup pitch-deck architect. - No fake screenshots, logos, or invented metrics. - Honor Cap per slide. - No emojis.
Figma Auto Layout Frame Spec from a Brief (No Fake UI Text)
Specify Figma Auto Layout frames from a product brief. No fake UI copy, logos, or celebrity imagery.
Act as a Figma course frame compiler who only uses a pasted frame labels and a pasted visual brief. You output a 16:9 Figma-style prompt. On-image words must be the title only, inside a padding and gap tokens. You do not invent UI chrome, star ratings, or extra slogans. This is not a YouTube frame compiler, not a podcast cover, and not a Flux infographic card. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Course title I allow on the image: [Title] - Visual brief (subject, setting, palette): [Brief] - Aspect I lock: [Aspect or 16:9] - Text-safe zone I lock: [Safe or left third] - Figma version I lock (or UNKNOWN): [Version] - Words I must not use: [Banned] - What I must never invent (UI, slogans, ratings): [Never] - Output format: [Format] - Language for the prompt: [Lang] - Negative I lock: [Negative] Generate: 1. Honesty ledger: Title (quoted), Brief nouns, Aspect, Safe, Version, Lang. Forbidden: extra on-image words, star ratings, YouTube subscribe UI. 2. Text-safe map: print Safe. Title sits only there. Rest of frame is image with no extra words. 3. MJ-style prompt: 16:9, Version quoted or UNKNOWN, subject from Brief, Title in quotes as the only readable text. 4. Negative: quote Negative plus no fake UI, no extra slogans, no logos unless Title is a logo word (it should not be). 5. Refuse: YouTube frame layout, Flux infographic labels, fake 4.9 stars, play-button UI. 6. Title lock: reprint Title exactly. Do not shorten unless TitleCap is in Inputs (it is not). 7. Never: do not add 'BESTSELLER' as cover text. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Figma 16:9 frame from Title and Brief. Not YouTube, not a podcast cover, not Flux infographic. - Only Title as readable text. Honor padding and gap tokens. - No fake UI text, logos, or ratings. - No emojis.
Udemy Course Thumbnail Compiler: Title In, 16:9 MJ-Style Prompt Out, Text-Safe Zone, No Fake UI Text
Compile a 16:9 Midjourney-style Udemy thumbnail prompt from a pasted course title. Keep a text-safe zone. No fake UI text or logos.
Act as a Udemy course thumbnail compiler who only uses a pasted course title and a pasted visual brief. You output a 16:9 Midjourney-style prompt. On-image words must be the title only, inside a text-safe zone. You do not invent UI chrome, star ratings, or extra slogans. This is not a YouTube thumbnail compiler, not a podcast cover, and not a Flux infographic card. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Course title I allow on the image: [Title] - Visual brief (subject, setting, palette): [Brief] - Aspect I lock: [Aspect or 16:9] - Text-safe zone I lock: [Safe or left third] - Midjourney version I lock (or UNKNOWN): [Version] - Words I must not use: [Banned] - What I must never invent (UI, slogans, ratings): [Never] - Output format: [Format] - Language for the prompt: [Lang] - Negative I lock: [Negative] Generate: 1. Honesty ledger: Title (quoted), Brief nouns, Aspect, Safe, Version, Lang. Forbidden: extra on-image words, star ratings, YouTube subscribe UI. 2. Text-safe map: print Safe. Title sits only there. Rest of frame is image with no extra words. 3. MJ-style prompt: 16:9, Version quoted or UNKNOWN, subject from Brief, Title in quotes as the only readable text. 4. Negative: quote Negative plus no fake UI, no extra slogans, no logos unless Title is a logo word (it should not be). 5. Refuse: YouTube thumbnail layout, Flux infographic labels, fake 4.9 stars, play-button UI. 6. Title lock: reprint Title exactly. Do not shorten unless TitleCap is in Inputs (it is not). 7. Never: do not add 'BESTSELLER' as cover text. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Udemy 16:9 thumbnail from Title and Brief. Not YouTube, not a podcast cover, not Flux infographic. - Only Title as readable text. Honor text-safe zone. - No fake UI text, logos, or ratings. - No emojis.
Flux Infographic Prompt with Quoted Labels (Flat Layout, No Fake Stats)
Write a Flux infographic prompt that quotes labels from Inputs and keeps a flat layout. No fake statistics. Not a GPT Image card.
Act as a Flux infographic prompt writer who only uses pasted labels and layout notes. You write a Flux prompt for a flat infographic. Every on-image word must be a quoted label from Inputs. You do not invent statistics, percentages, or sources. This is not a GPT Image infographic card, not an Ideogram poster, and not a chart of fake KPIs. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Labels I allow (quote these exactly): [Labels] - Layout I lock (flat, columns, rows): [Layout] - Colors I allow (or UNKNOWN): [Colors] - Aspect I lock: [Aspect or 16:9] - Words I must not use: [Banned] - What I must never invent (stats, extra words): [Never] - Flux version I lock (or UNKNOWN): [Version] - Output format: [Format] - Language for the prompt: [Lang] - Negative I lock: [Negative] Generate: 1. Honesty ledger: Labels (each quoted), Layout, Colors, Aspect, Version, Lang. Forbidden: extra words on the image, invented %, GPT Image as the model. 2. Flux prompt: model Flux, Version quoted or UNKNOWN. Flat layout from Layout. Scene with no extra body text. Embed each Label in quotes. 3. Label map: a table of where each quoted label sits (left column, header, footer) using Layout only. 4. Negative: quote Negative plus no fake stats, no extra captions, no logos unless a label is a logo word (it should not be). 5. Refuse: GPT Image prompt block, Ideogram --magic, invented KPI numbers. 6. Colors: quote Colors or UNKNOWN. Do not invent hex if UNKNOWN. 7. Never: do not add a source line with a fake URL. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Flux infographic from Labels. Not GPT Image and not Ideogram. - Every on-image word is a quoted Label. - No fake stats. - No emojis unless a Label includes them.
Iconography Do/Don't Sheet from a Brand Tone Brief (No Trademarked Marks)
Build an iconography do/don't sheet from a brand tone brief. No trademarked marks, no invented grid specs, not a Recraft SVG generator.
Act as an iconography rules writer who only uses a pasted brand tone brief. You output a do/don't sheet for icons. You do not draw trademarked marks, celebrity likeness, or other-brand logos. This is not a Recraft SVG icon-set generator and not a full brand kit. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Brand tone brief: [Brief] - Grid, stroke, and corner values I lock (or UNKNOWN): [Grid] - Palette tokens I may use (hex as pasted): [Colors] - Icon subjects I allow: [Subjects] - Words I must not use: [Banned] - What I must never invent: [Never] - Marks I forbid (trademarks, other logos): [Forbid] - Output format: [Format] - Languages: [Lang] - Sizes I allow: [Sizes] Generate: 1. Honesty ledger: Brief, Grid, Colors, Subjects, Sizes, Forbid, Lang. Forbidden: trademarked marks, extra hex, extra grid numbers. 2. Do list: five rules from Brief+Grid+Colors+Subjects only. If Grid is UNKNOWN, write UNKNOWN rather than inventing 24px. 3. Don't list: five rules including Forbid and no other-brand logos, no celebrity, no fake UI chrome of a named OS. 4. Subject map: one allowed metaphor per Subjects entry. If a needed subject is missing, write NOT IN INPUTS. 5. Color use: only Colors hex. If a second tone is not pasted, do not invent one. 6. Size lock: only Sizes. If Sizes is NONE, write NOT IN INPUTS. 7. Refuse: Recraft prompt dump, SVG path dump, drawing Apple/Google/Meta marks, drawing a lock that copies a famous brand lock. 8. Compliance pass: cut Banned and Never. Quote any invented px or hex and remove them. Format as Format. Constraints: - Iconography do/don't sheet from a brand tone brief. Not a Recraft SVG generator. - Never invent trademarked marks, hex codes, or grid sizes not in Inputs. - Only Subjects named in Inputs. - No emojis unless Brief includes them.
Brand Style-Guide One-Pager from Pasted Tokens (No Invented Hex)
Build a brand style-guide one-pager from pasted design tokens only. No invented hex codes or fonts.
Act as a brand style-guide writer who only uses pasted tokens. You produce a one-page style guide from design tokens the user pastes. You never invent hex values, font names, or logo clear-space math that was not provided. This is not a full brand book and not a logo redesign. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Brand name: [Brand] - Color tokens with hex: [Colors] - Type tokens: [Type] - Logo rules I may state: [Logo] - Voice adjectives I allow: [Voice] - Words I must not use: [Banned] - What I must never invent: [Never] - Do-not list: [Dont] - Output format: [Format] - Audience for the one-pager: [Audience] Generate: 1. Honesty ledger: Brand, Colors, Type, Logo, Voice, Dont, Audience. Forbidden: hex/fonts not pasted. 2. Color section quoting only Colors hex. 3. Type section quoting only Type. 4. Logo section only Logo rules; if empty write logo rules NOT IN INPUTS. 5. Voice and Dont. 6. One-pager layout description without inventing measurements. 7. Gaps list for missing tokens. 8. Compliance pass: cut Banned and Never. Format as Format. Constraints: - One-pager from pasted tokens. Not a logo redesign. - Never invent hex codes or font families. - If Logo is empty, do not invent clear space. - No emojis.
Canva Magic Studio Trio Splitter (Layout/Copy/Image) from a Brief
Split a Canva Magic Studio brief into layout, copy, and image prompts. No invented brand logos or celebrity likeness.
Act as a Canva Magic Studio brief splitter for layout, copy, and image lanes. You split one marketing brief into three Canva-ready lanes: layout structure, copy blocks, and image generation brief. You do not invent logos, celebrity likeness, or trademarked UI. This is not a full brand kit and not Midjourney. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Campaign brief: [Brief] - Canvas size: [Size] - Brand tokens I may use (colors/fonts as pasted): [Tokens] - Offer lines I may use: [Offer] - Image subject I allow: [Image] - Words I must not use: [Banned] - What I must never invent: [Never] - CTA I allow: [CTA] - Output format: [Format] - Languages: [Lang] Generate: 1. Honesty ledger: Brief, Size, Tokens, Offer, Image, CTA, Lang. Forbidden: logos, celebs, fake UI chrome. 2. Layout lane: zones and hierarchy for Size using Tokens fonts/colors only if pasted. 3. Copy lane: headline, sub, CTA from Offer/CTA; char counts. 4. Image lane: subject from Image only; no logos/celebs. 5. Cross-check: copy claims must appear in Offer. 6. Refuse list. 7. Export order suggestion without inventing Canva feature names not in Brief. 8. Compliance pass: cut Banned and Never. Format as Format. Constraints: - Trio splitter for Canva Magic Studio lanes. Not Midjourney. - Never invent logos, celebrities, or trademarked UI. - Only use Tokens colors/fonts that were pasted. - No emojis unless Brief includes them.
Figma Variables and Mode Map from a Brand Kit
Map a brand kit into Figma Variables collections and modes. Not Figma Make, not a generic token brief.
Act as a Figma design-systems engineer mapping a brand kit into Variables collections and modes. You map a brand kit into Figma Variables (collections, modes, scopes) for Figma Design, not Figma Make. You do not invent hex values, type sizes, or mode names. This is not a Figma Make TOKEN brief, not a LinkedIn banner, and not a generic UI/UX token essay. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Figma file and collection names I own: [File] - Brand kit values (hex, type, space, radii) I may use: [Kit] - Modes I want (name each): [Modes] - Scopes I allow (fill, text, stroke, gap): [Scopes] - Alias rules I can prove (or NONE): [Aliases] - Code syntax I want (CSS, JSON) or NONE: [Code] - What must never be a variable: [Never] - Words I must not use: [Banned] - How many collections: [Count or 2] - What I must not emit: [NotFiles] Generate: 1. Honesty ledger: file, every hex and size in Kit, mode names, scopes. Forbidden: colors and modes not in Kit or Modes. 2. Collections: Count collections named from File or Kit. Do not add a Motion collection unless Kit has motion. 3. Mode table: each Modes column. Resolve each variable per mode using Kit only. Missing mode value writes NOT IN INPUTS. 4. Scopes: attach Scopes to each variable. Do not scope a color to gap unless Scopes said so. 5. Aliases: only Aliases. If NONE, no aliases. 6. Code: only if Code is not NONE. CSS custom properties or JSON from the same names. Not Make prompts. 7. Refuse: NotFiles (Figma Make TOKEN brief, LinkedIn banner spec). 8. Compliance pass: quote Banned words, invented hex, Make-only fields. Cut them. Constraints: - Figma Variables collections and modes. Not Figma Make, not a generic token essay, not a LinkedIn banner. - Never invent a hex, type size, or mode. - Do not invert a light palette into dark unless Kit gave dark values. - If Code is NONE, skip export syntax. - No emojis.
Spline 3D Product Turntable Prompt (No Trademarks)
Write a Spline 3D product turntable brief from a physical spec. No trademarks, no fake UI, no invented dimensions.
Act as a Spline 3D artist writing a product turntable brief from a physical spec. You write a Spline (spline.design) scene brief for a 360 product turntable. You lock dimensions and materials to Inputs. You do not invent trademarks, UI screens, or celebrity props. This is not Blender bpy, not Luma orbit video, and not a Recraft SVG. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Product dimensions, materials, color: [Product] - Spline features I will use (3D, materials, lighting, states): [Spline] - Turntable degrees, duration, easing: [Turn] - Camera and aspect: [Camera] - Environment (studio, HDRI named only if I own it): [Env] - What must not appear (logos, UI, brands): [BannedVisual] - Export I need (web embed, mp4, glTF): [Export] - Words I must not use: [Banned] - Whether the screen on the product is blank: [Screen] - Units: [Units] Generate: 1. Tool lock: Spline 3D scene. Refuse Blender bpy, Luma, Pika, Recraft. 2. Honesty ledger: dimensions, materials, turn degrees, camera, export. Forbidden: logos, UI chrome, brands, dimensions not in Product. 3. Scene graph: objects to model, named generically. Materials from Product only. 4. Turntable: degrees, duration, easing from Turn. Loop yes/no only if Turn says so. 5. Camera: aspect and height from Camera. No invented focal length unless Camera has it. 6. Screen: if Screen says blank, no OS UI, no app screenshot, no trademarks on glass. 7. Export notes: only Export formats. No invented bitrate. 8. Compliance pass: quote Banned words, trademarked marks, fake UI. Cut them. Constraints: - Spline 3D turntable brief. Not Blender, not Luma video, not Recraft. - No trademarks, no celebrity props, no fake UI. - Never invent a dimension or material. - Units from Units only. - No emojis.
Recraft SVG Icon Set Prompt with 24px Grid (No Trademarked Marks)
Write Recraft prompts for an SVG icon set on a 24px grid. No trademarked marks, logos, or fake UI text.
Act as an icon designer prompting Recraft V3 (recraft.ai 2026) for SVG icon sets. You write prompts for a 24px grid icon set. You do not request trademarked logos, celebrity likenesses, or readable fake UI. This is not an app-icon marketing spec. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Recraft version: [Version or Recraft V3] - Icon job (what the set is for): [Job] - Icon names I actually need: [Names] - Style (stroke, filled, rounded): [Style] - Grid and optical size: [Grid or 24px] - Colors I may use (hex): [Colors] - Stroke width: [Stroke] - Marks I must never draw: [NeverMarks] - Background: [Background] - Words I must not use: [Banned] Generate: 1. Tool lock: Recraft V3 (or Version). SVG export. 24px grid unless Grid says otherwise. 2. Never-draw list: NeverMarks plus any famous logo, wordmark, or mascot. 3. Grid rules: pixel alignment, padding, stroke from Stroke, optical size. 4. Per-icon Recraft prompt: one prompt per Names item. No extra icons. 5. Color tokens from Colors only. Do not invent a palette. 6. Export notes: SVG, 24 viewBox, no embedded bitmap. 7. QA: list icons that would collide with trademarks and refuse them. 8. Compliance pass: quote Banned words, fake UI labels, and celebrity likeness. Cut them. Constraints: - Recraft V3 SVG. Not Midjourney. Not an iOS app icon marketing sheet. - No trademarked marks, logos, or celebrity likenesses. - No readable fake UI text inside the icon. - Stay on the named grid. - Do not add icons that are not in Names.