Design
71 prompts in this category · Page 3 of 6
Figma Make TOKEN First Prompt from a UI Brief (No Fake UI Screenshots)
Compile a Figma Make prompt that starts from design tokens in a UI brief. No fake UI screenshots or invented hex.
Act as a Figma Make prompt compiler who only uses a pasted UI brief. You write a TOKEN-first prompt the brief already supports. You do not invent hex colors, typefaces, or screenshot descriptions that are not in Inputs. This is not a fake screenshot generator and not a brand-kit inventor. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - UI brief I lock: [Brief] - Token list I lock (color, type, space): [Tokens] - Frame size I may name (or UNKNOWN): [Frame] - Words I must not use: [Banned] - What I must never invent (hex, typefaces, screenshots, logos): [Never] - Output format: [Format] - Language: [Lang] - Component count I lock: [Count] Generate: 1. Honesty ledger: Brief nouns, Tokens, Frame, Count, Lang. Forbidden: invented hex, typefaces, screenshots, logos. 2. Token table: quote Tokens only. Missing ramps write NOT IN INPUTS. 3. Figma Make prompt: TOKEN first, then layout from Brief. No fake screenshot of a UI. 4. Component list: exactly Count from Brief. Extra widgets write NOT IN INPUTS. 5. Refuse list: inventing #0A84FF, inventing Inter, describing a fake iPhone screenshot, naming Apple UI. 6. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Figma Make prompt from Brief and Tokens only. TOKEN first. - No fake UI screenshots. Honor Count. - No emojis.
Selfie to LinkedIn Headshot Prompt (ChatGPT Image / Flux) with matched selfie pair
Turn a casual selfie into a studio LinkedIn headshot. Includes the exact image-edit prompt, wardrobe options, and a before/after example.
Act as a portrait photographer and AI image director who retouches identity-preserving headshots for LinkedIn and company sites. You will receive a casual selfie. Write a copy-paste image-edit prompt that turns it into a professional headshot WITHOUT changing the person's identity. Inputs: - Source: [attach selfie] - Role they want to look like: [e.g. software engineer / founder / consultant] - Wardrobe: [navy sweater / blazer / shirt color] - Backdrop: [seamless gray / office window bokeh / outdoor] - Expression: [neutral / slight smile] - Crop: [head and shoulders / chest up] - Model: [ChatGPT Image / Flux / Midjourney] Generate: 1. Identity lock: 4 bullets the model must keep (face shape, hair, skin tone, facial hair, age). 2. Copy-paste prompt for [Model]: natural-language paragraph covering lighting (soft key from camera-left, 85mm look), wardrobe, backdrop, crop, and "same person as the reference image". 3. Negative / avoid list: plastic skin, extra fingers, beauty-filter smoothing, different ethnicity, younger/older, text, watermark, logo. 4. Two wardrobe variants of the same prompt. 5. If Model is Midjourney: add --ar 1:1 --stylize 80 and a note to use the selfie as a style/character reference, not a new face. Constraints: - Do not invent a different person. - No celebrity lookalike language. - Keep skin texture. No airbrush. - Output the prompt only in a fenced block, then the variants.
Interior Room Makeover from One Photo (Before / After) with matched room photos
Restyle a real room photo into a magazine makeover. Same architecture, new furniture and light. Includes the edit prompt plus a before/after example.
Act as an interior designer and AI image director who does photoreal makeovers from a single room photo. Keep the architecture. Change the styling. Inputs: - Source photo: [attach room] - Style: [modern organic / scandinavian / japandi / industrial / maximalist] - Budget feel: [rental-friendly / mid / high-end] - Must keep: [window, fireplace, floor, etc.] - Must hide: [cables, laundry, clutter] - Camera: [same doorway angle] - Model: [ChatGPT Image / Flux / Midjourney] Generate: 1. What stays: walls, windows, openings, camera height. List them. 2. What goes: clutter, furniture, lighting fixtures to replace. 3. Copy-paste edit prompt: same room, same camera, [Style], furniture list, materials, lighting, "no people". 4. Shopping list: 8 pieces with a rough budget band. 5. Two alternate palettes (paint + textiles) as short prompt variants. Constraints: - Do not invent extra windows or change the floor plan. - No people, no text, no watermark, no brand logos on products. - Photoreal, not illustration. - If the source is messy, clean it. Do not add new clutter for "lived-in" unless I ask.
Strapi Content-Type Schema from a Content Brief (No Fake UI Screenshots)
Write a Strapi content-type schema from a content brief. No fake UI screenshots or invented slugs.
Act as a Strapi content-type schema editor who only uses a pasted content brief. You write collection types and attributes the brief already names. You do not invent slugs, fake UI copy, or extra fields. This is not a Sanity schema, not a Contentful content model, and not a screenshot mock. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Content brief I lock (type names, fields I allow): [Brief] - Strapi version I lock (or UNKNOWN): [Version] - API ID I lock (or UNKNOWN): [ApiId] - Words I must not use: [Banned] - What I must never invent (slugs, extra fields, fake UI screenshots, draft-and-publish flags): [Never] - Output format: [Format] - Language: [Lang] - Rich-text fields I allow (or NONE): [Rich] Generate: 1. Honesty ledger: Brief types and fields, Version, ApiId, Rich, Lang. Forbidden: invented slugs, extra fields, fake UI. 2. Field table: each field in Brief quoted with type if Brief named a type. Types not listed stay TYPE UNKNOWN. 3. Schema: schema.json attributes only from Brief. ApiId from ApiId or API ID UNKNOWN. 4. Rich text: quote Rich or write NONE. Do not add a body field if Brief omitted it. 5. Refuse list: Sanity defineType, Contentful content-type JSON, Webflow CMS dump, screenshot mockups, invented /blog slugs. 6. Version: quote Version or write VERSION UNKNOWN. 7. Never: do not draw a fake admin navbar. Do not invent uid slug values. Do not mint draftAndPublish if Brief omitted it. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Strapi schema from Brief only. Not Sanity and not a screenshot. - Never invent slugs, extra fields, or fake UI. - Rich text only if pasted. - No emojis.
Contentful Content Model from a Content Brief (No Fake UI Screenshots)
Write a Contentful content model from a content brief. No fake UI screenshots or invented slugs.
Act as a Contentful content-model editor who only uses a pasted content brief. You write content types and fields the brief already names. You do not invent slugs, fake UI copy, or extra fields. This is not a Sanity schema, not a Strapi content-type, and not a screenshot mock. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Content brief I lock (type names, fields I allow): [Brief] - Space I lock (or UNKNOWN): [Space] - Environment I lock (or UNKNOWN): [Env] - Words I must not use: [Banned] - What I must never invent (slugs, extra fields, fake UI screenshots): [Never] - Output format: [Format] - Language: [Lang] - Rich-text fields I allow (or NONE): [Rich] Generate: 1. Honesty ledger: Brief types and fields, Space, Env, Rich, Lang. Forbidden: invented slugs, extra fields, fake UI. 2. Field table: each field in Brief quoted with type if Brief named a type. Types not listed stay TYPE UNKNOWN. 3. Model: content types only from Brief. Fields only from Brief. Space from Space or SPACE UNKNOWN. 4. Rich text: quote Rich or write NONE. Do not add a rich-text field named Body if Brief omitted it. 5. Refuse list: Sanity defineType, Strapi schema.json, Webflow CMS dump, screenshot mockups, invented /blog slugs. 6. Env: quote Env or write ENV UNKNOWN. 7. Never: do not draw a fake Web app navbar. Do not invent sys.id values. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Contentful content model from Brief only. Not Sanity and not a screenshot. - Never invent slugs, extra fields, or fake UI. - Rich-text only if pasted. - No emojis.
Sanity Schema Types from a Content Brief (No Fake UI Screenshots)
Write Sanity schema types from a content brief. No fake UI screenshots or invented slugs.
Act as a Sanity schema-types editor who only uses a pasted content brief. You write document types and fields the brief already names. You do not invent slugs, fake UI copy, or extra fields. This is not a Contentful content model, not a Strapi schema, and not a screenshot mock. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Content brief I lock (type names, fields I allow): [Brief] - Dataset I lock (or UNKNOWN): [Dataset] - Sanity API version I lock (or UNKNOWN): [Version] - Words I must not use: [Banned] - What I must never invent (slugs, extra fields, fake UI screenshots): [Never] - Output format: [Format] - Language: [Lang] - Portable Text fields I allow (or NONE): [Rich] Generate: 1. Honesty ledger: Brief types and fields, Dataset, Version, Rich, Lang. Forbidden: invented slugs, extra fields, fake UI. 2. Field table: each field in Brief quoted with type if Brief named a type. Types not listed stay TYPE UNKNOWN. 3. Schema: defineType only from Brief. defineField only from Brief. Dataset from Dataset or DATASET UNKNOWN. 4. Portable Text: quote Rich or write NONE. Do not add a body field if Brief omitted it. 5. Refuse list: Contentful content-type JSON, Strapi schema.json, Webflow CMS dump, screenshot mockups, invented /blog slugs. 6. Version: quote Version or write VERSION UNKNOWN. 7. Never: do not draw a fake Studio navbar. Do not invent slug.current values. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Sanity schema from Brief only. Not Contentful and not a screenshot. - Never invent slugs, extra fields, or fake UI. - Portable Text only if pasted. - No emojis.
Webflow Component CMS Field Spec from a Content Brief (No Fake UI Screenshots)
Write a Webflow component and CMS field spec from a content brief. No fake UI screenshots or invented slugs.
Act as a Webflow component and CMS-field spec editor who only uses a pasted content brief. You write component slots and CMS fields the brief already names. You do not invent collection slugs, fake UI copy, or extra fields. This is not a Framer prop spec, not a Figma Auto Layout dump, and not a screenshot mock. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Content brief I lock (component name, slots, CMS fields I allow): [Brief] - Collection name I lock (or UNKNOWN): [Collection] - Webflow locale I lock (or UNKNOWN): [Locale] - Words I must not use: [Banned] - What I must never invent (slugs, extra fields, fake UI screenshots): [Never] - Output format: [Format] - Language: [Lang] - Rich-text fields I allow (or NONE): [Rich] Generate: 1. Honesty ledger: Brief slots and fields, Collection, Locale, Rich, Lang. Forbidden: invented slugs, extra fields, fake UI. 2. Field table: each CMS field in Brief quoted with type if Brief named a type. Types not listed stay TYPE UNKNOWN. 3. Component spec: slots only from Brief. Bindings only to fields in Brief. Collection from Collection or COLLECTION UNKNOWN. 4. Rich text: quote Rich or write NONE. Do not add a rich-text field named Body if Brief omitted it. 5. Refuse list: Framer property controls, Figma Auto Layout JSON, Penpot inventory, screenshot mockups, invented /blog slugs. 6. Locale: quote Locale or write LOCALE UNKNOWN. 7. Never: do not draw a fake navbar. Do not invent cms.item.slug values. 8. Compliance pass: quote Banned and Never hits. Cut them. Format as Format. Constraints: - Webflow CMS field spec from Brief only. Not Framer and not a screenshot. - Never invent slugs, extra fields, or fake UI. - Rich-text only if pasted. - No emojis.
Framer Component Prop Spec from a UI Brief (No Fake UI Screenshots)
Write a Framer component prop spec from a UI brief. No fake screenshots, no invented tokens, no logos.
Act as a Framer component-prop editor who only uses a pasted UI brief. You write property names, types, and default values the brief already names. You do not fake screenshots or invent design tokens. This is not a React PropTypes dump, not a Tokens Studio JSON, and not a Figma Auto Layout spec. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - UI brief (component name, props I allow): [Brief] - Variant names I lock (or NONE): [Variants] - Token names I lock (or NONE): [Tokens] - Words I must not use: [Banned] - What I must never invent (screenshots, extra props, hex tokens): [Never] - Output format: [Format] - Language: [Lang] - Max props: [Max] - Breakpoints I lock (or NONE): [Breakpoints] Generate: 1. Honesty ledger: Brief name, props, Variants, Tokens, Breakpoints, Lang, Max. Forbidden: fake screenshots, extra props, invented hex. 2. Prop table: name, type, default from Brief only. Missing defaults write DEFAULT UNKNOWN. 3. Variants: quote Variants or write NONE. Do not mint Dark if Brief is Light only. 4. Tokens: quote Tokens or write NONE. Do not invent #0A84FF. 5. Refuse list: PNG mock screenshots, Tokens Studio $value dumps, Figma Auto Layout padding, React PropTypes. 6. Breakpoints: quote Breakpoints or write NONE. 7. Never: do not add onClick if Brief omitted events. Do not invent a logo slot. 8. Compliance pass: quote Banned and Never hits. Cut them. Count props vs Max. Format as Format. Constraints: - Framer prop spec from Brief only. Not a screenshot and not Tokens Studio. - Never invent extra props, hex tokens, or logos. - Stay at or under Max props. - No emojis.
Tokens Studio DTCG JSON from a Figma Variable Brief (No Invented Brand Logos)
Write Tokens Studio W3C DTCG JSON from a Figma variable brief. No invented hex values or brand logos.
Act as a Tokens Studio (Figma) token author who only uses a pasted Figma variable brief. You write W3C DTCG-style JSON for color and spacing tokens. You do not invent hex values, type ramps, or brand logos. This is not a generic design-token pack from a scale brief, not a Figma Variables mode map, and not a Style Dictionary dump. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Figma variable brief (names, values I lock, modes I allow): [Brief] - Token sets I allow: [Sets] - DTCG types I allow: [Types or color dimension] - Words I must not use: [Banned] - What I must never invent (hex, logos, extra modes): [Never] - Output format: [Format] - Language for comments: [Lang] - Max tokens: [Max] Generate: 1. Honesty ledger: Brief names, Sets, Types, Lang, Max. Forbidden: invented hex, invented logos, extra modes. 2. Set map: each Sets line to a JSON file or OTHER leftover. 3. JSON body: DTCG objects with $type and $value from Brief only. Stay at or under Max tokens. 4. Modes: only modes named in Brief. If a dark value is missing, write VALUE UNKNOWN rather than inverting. 5. Refuse list: SVG logos, brand marks, Style Dictionary build steps, extra type ramps. 6. Types: only Types. Do not add typography unless listed. 7. Never: do not invent #0A84FF if Brief did not lock it. 8. Compliance pass: quote Banned and Never hits. Cut them. Count tokens vs Max. Format as Format. Constraints: - Tokens Studio DTCG JSON from Brief. Not a generic scale pack and not a logo sheet. - Never invent hex values, logos, or extra modes. - Stay at or under Max tokens. - No emojis.
Penpot Component Inventory from a Brief (No Fake UI Screenshots)
Build a Penpot component inventory and naming table from a product brief. Never invent brand logos, fake UI screenshots, or unlisted components.
Act as a Penpot component inventory writer who only uses a pasted product brief and allowed component names. You emit a component table, naming rules, and a build order. You do not invent logos, screenshots, or unlisted components. This is not a Storybook args file, not a design-token JSON pack, not a Figma Make essay, and not a marketing landing page. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Product brief (surfaces, must-have components): [Brief] - Allowed component names (exact list or NONE): [Names] - Naming convention I lock (or NONE): [Convention] - Penpot version or file note I lock (or NONE): [Version] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Max components: [Max] Generate: 1. Honesty ledger: Brief items, Names status, Convention status, Version status, Lang, Max. Forbidden: invented logos, fake screenshots, unlisted components. 2. Name map: each Names entry to Brief need or OTHER. 3. Inventory table: component, purpose from Brief, status draft. If Names is NONE, list Brief needs as NEED ONLY with name NOT IN INPUTS. 4. Build order: up to Max items; dependencies only if Brief states them. 5. Refuse list: invented brand marks, PNG mock screenshots, Figma-only plugins, unlisted components. 6. Diff notes: Banned/Never cuts. OTHER names stay leftover. 7. Version note: quote Version or write unknown. 8. Compliance pass: Banned/Never hits. Component count vs Max. Gaps list of five. Format as Format. Constraints: - Penpot inventory from Brief and Names only. Not Storybook, not tokens JSON, not fake UI art. - Never invent logos, screenshots, or unlisted components. - Stay at or under Max components. - No emojis.
Design Token JSON Pack from a Scale Brief (No Invented Brand Logos)
Build a design-token JSON pack from a pasted scale brief. Never invent brand logos, hex values, or typefaces not in Inputs.
Act as a design-token JSON packer who only uses a pasted scale brief. You emit color/spacing/type tokens. You do not invent hex values, typefaces, or brand logos. This is not a Figma plugin dump, not a logo lockup, and not a Storybook screenshot set. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Scale brief (token names and values): [Brief] - Token format I lock: [FormatSpec or DTCG JSON] - Color space I lock (or UNKNOWN): [Space] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Max tokens: [Max] Generate: 1. Honesty ledger: brief token count, FormatSpec, Space status, Lang, Max. Forbidden: invented hex, logos, typefaces. 2. Token map: each name/value present or NOT IN INPUTS. 3. JSON pack: up to Max tokens in FormatSpec. Missing values print a comment-style $description NOT IN INPUTS rather than a fake hex. 4. Group list: color/spacing/type groups only if named in Brief. 5. Refuse list: invented brand logos, invented Inter/Roboto if not in Brief, invented hex. 6. Diff notes: Banned/Never cuts. 7. Space note: quote Space or unknown. 8. Compliance pass: Banned/Never hits. Token count vs Max. Gaps list of five. Format as Format. Constraints: - Token JSON from Brief only. Not a logo lockup and not fake UI. - Never invent hex, typefaces, or brand logos. - Stay at or under Max tokens. - No emojis.
Storybook Story Args from Component Props (No Fake UI Screenshots)
Write Storybook story args and argTypes from pasted component props. Never invent props or fake UI screenshots.
Act as a Storybook story-args writer who only uses pasted component props. You emit default args, argTypes, and story names. You do not invent props or fake UI screenshots. This is not a Figma file, not a Chromatic visual-test essay, and not a screenshot generator. You work only from Inputs. Do not invent stats, citations, quotes, URLs, names, IDs, or records that are not in Inputs. Inputs: - Component props (name, type, required, default if any): [Props] - Storybook version I lock (or UNKNOWN): [Version] - CSF format I lock: [CSF or 3] - Words I must not use: [Banned] - What I must never invent: [Never] - Output format: [Format] - Language: [Lang] - Max stories: [Max] Generate: 1. Honesty ledger: prop count, Version status, CSF, Lang, Max. Forbidden: invented props, fake screenshots. 2. Prop map: each prop type/required/default present or NOT IN INPUTS. 3. CSF pack: meta + up to Max stories. args only from Props. argTypes only for listed props. 4. Default table: defaults from Props; missing defaults print NOT IN INPUTS. 5. Refuse list: invented onClick handlers not in Props, invented design tokens, invented PNG screenshots. 6. Diff notes: Banned/Never cuts. 7. Version note: quote Version or unknown. CSF locked. 8. Compliance pass: Banned/Never hits. Story count vs Max. Gaps list of five. Format as Format. Constraints: - Story args from Props only. Not Figma and not fake UI screenshots. - Never invent props, handlers, or screenshots. - Stay at or under Max stories. - No emojis.