Browse Prompts
3315 prompts available · Page 28 of 277
Couples Photo Prompt: ChatGPT Shoot From Your Own Photo
Turn a photo of you and your partner into a styled couples shoot in ChatGPT: identity lock, setting, pose, light, and camera details, plus three variations.
Act as a wedding and couples portrait photographer who also writes ChatGPT image prompts, and who keeps both people looking exactly like themselves while changing the setting, light, and pose. Inputs: - Reference photo notes: who is on the left and right, hair, glasses, skin and eye details, anything that must not change: [CouplePhotoNotes] - The shoot setting we want: [Setting] - Mood and story of the photo: [Mood] - Clothes for each person: [Wardrobe] - Pose and how they touch or interact: [PoseAndTouch] - Light and camera look, such as golden hour, 50mm, film grain: [LightAndCamera] - Format: aspect ratio and where it will be used: [Output] Generate: 1. An identity lock block for both people: the features from CouplePhotoNotes that must stay the same, written as plain instructions, with who stands on which side. 2. One final ChatGPT image prompt for the couples shoot in natural photographer language: Setting, PoseAndTouch, Wardrobe, LightAndCamera, Mood, and Output, followed by the identity lock. 3. Three couples photo variations (one wide, one close, one candid moment), each as a short replacement for the pose and framing lines only. 4. A short avoid list: extra fingers, merged hands, changed face shape, beauty filter skin, text, logos, extra people. 5. A check list to compare the result with the reference photo: faces, hands, sides, rings or jewelry, and clothing colors. Rules: - Only use photos of people who agreed to the edit. Never use a celebrity or a stranger's likeness. - Do not slim, age, or change anyone's body unless they asked for it in CouplePhotoNotes.
Image Prompts for Men: ChatGPT Six Looks From Your Photo
Write six ChatGPT image prompts for men from one photo: a face lock, then editorial, outdoor, streetwear, cinematic, vintage, and workshop looks with fixes.
Act as a men's editorial stylist and portrait photographer who writes ChatGPT image prompts, keeping the man's real face, build, and age while changing the outfit, setting, and light for each look. Inputs: - Face and body notes from the photo: hair, beard, skin tone, eye color, glasses, tattoos, build, age range: [FaceNotes] - Six looks to create (or "choose for me"): [LookList] - Clothes he owns or likes, colors he wears, anything he never wears: [StylePreferences] - Where the images will be used, such as a profile picture, a dating profile, a portfolio: [UseCase] - Aspect ratio for each use: [AspectRatios] - Anything to avoid, such as muscles added, suits, sunglasses: [AvoidList] Generate: 1. A face lock paragraph from FaceNotes that goes at the end of every look, saying exactly what must not change. 2. Six image prompts for men, one per look in LookList: setting, outfit from StylePreferences, pose, expression, light, lens, and the aspect ratio from AspectRatios that fits UseCase. 3. For each look, one line on where it works best (for example "good profile picture" or "too dramatic for a work profile") based on UseCase. 4. A shared negative list built from AvoidList plus common errors: changed jaw or nose, added muscles, younger or older face, extra fingers, logos, text. 5. A fix line for each of the three most likely errors, to paste as a follow up message if the first image drifts. Rules: - Use only photos of the man himself or of someone who agreed. No celebrity likeness, no "looks like" a famous actor. - Keep his real build and age unless FaceNotes asks for a change.
Work Productivity Prompt: Weekly Workload Triage and Focus
Triage a messy work week: rank tasks by impact, decide what to drop or delegate, audit meetings, and get focus blocks plus a daily shutdown checklist.
Act as a workplace productivity coach who helps busy employees and managers decide what NOT to do this week, then protect time for the work that matters most. Inputs: - Everything on my plate this week, as a messy list with deadlines if known: [TaskList] - My meetings this week with length and my role in each (deciding, presenting, listening): [Meetings] - My top goals or priorities this quarter, or what my manager said matters: [Priorities] - What usually interrupts me (chat, email, walk ups, urgent requests) and when: [Interruptions] - When I do my best focused work and when my energy dips: [EnergyPattern] - Hard limits: working hours, days off, commitments I cannot move: [Constraints] - People I can delegate to or ask for help, and what they are good at: [Helpers] Generate: 1. A task inventory table: task, deadline, which item in Priorities it serves (or "none"), impact (high, medium, low), effort in hours, and a decision: do, delegate, defer, or drop. 2. A short "not this week" list with a one line message I can send for each deferred or dropped item that affects someone else. 3. A delegation note for each task going to Helpers: what done looks like, the deadline, and when to check in. 4. A meeting audit of Meetings: keep, shorten, send someone else, or decline, with a polite reply for each decline. 5. A weekly time map inside Constraints: focus blocks placed in my EnergyPattern peak hours for the high impact tasks, shallow work batched into low energy windows, and buffer time each day. 6. Interruption rules for Interruptions: when I check chat and email, a status message, and what counts as truly urgent. 7. A five step daily shutdown checklist and three questions for a Friday review. Rules: - Use only tasks and meetings from my inputs. If the total effort does not fit the hours in Constraints, say how many hours over it is and what must move. - Do not promise a productivity gain or quote research numbers.
English Teacher Prompt: Essay Feedback and a Mini Lesson
Turn a set of student essays into class wide feedback patterns, a 15 minute mini lesson, ELL supports, a comment bank, and an exit ticket for English class.
Act as a secondary English language arts teacher and ESL specialist who reads a stack of student essays, finds the two or three patterns that matter most, and turns them into feedback and a short lesson the teacher can use tomorrow. Inputs: - Grade level, course, and the unit or text we are studying: [GradeAndUnit] - The writing task students answered, word for word: [WritingTask] - The rubric or standards I grade against: [Rubric] - Anonymized student writing samples, labeled Student A, B, C (3 to 8 short excerpts): [StudentSamples] - English learners in the class and their proficiency levels, no names: [ELLProfile] - Minutes I have for the mini lesson and what students already learned: [LessonTimeAndPriorLearning] - What I want students to revise next: [RevisionGoal] Generate: 1. A pattern table across StudentSamples: each pattern, which students show it, a short quoted example, and the rubric row it affects. Separate strengths from problems. 2. The top two teaching priorities, chosen by how many students they affect and how much they move the rubric score, with one sentence on why. 3. A mini lesson that fits LessonTimeAndPriorLearning: learning target in student language, a model paragraph written fresh for this lesson (not copied from a student), a think aloud, a we do activity, and a you do revision task tied to RevisionGoal. 4. ELL supports for the lesson, matched to each level in ELLProfile: sentence frames, a word bank from WritingTask, and one modified task. 5. A comment bank of 8 to 10 short comments, each naming the rubric row, praising or pointing to one specific move, and ending with a next step. 6. A one question exit ticket that checks the first priority, with what a strong, partial, and missing answer looks like. Rules: - Quote only words that appear in StudentSamples. Do not guess scores the rubric cannot support; say when a sample is too short to judge. - Write comments a student in GradeAndUnit can read, in second person, without sarcasm.
B2B Marketing Prompt: Buying Committee Campaign Plan
Plan a B2B marketing campaign around the whole buying committee: message map by role, content by funnel stage, channel plan, lead handoff rules, and KPIs.
Act as a B2B demand generation marketer who plans campaigns around the full buying committee, not one persona, and who writes lead definitions that sales actually agrees to. Inputs: - Product, what it replaces, and the main problem it solves: [Product] - Ideal customer profile: industry, company size, region, and trigger events: [ICP] - Roles in the buying committee and what each cares about: [BuyingCommittee] - Proof we can use: customer quotes, case studies, results we are allowed to share: [CustomerEvidence] - Typical sales cycle length, deal size, and how deals are lost today: [SalesCycle] - Channels and budget for this quarter: [ChannelsAndBudget] - Main alternatives buyers compare us with, including doing nothing: [Alternatives] - Campaign goal and timeframe: [CampaignGoal] Generate: 1. A message map: one row per role in BuyingCommittee with their main worry, the message that answers it, the proof from CustomerEvidence, and the objection to expect. 2. A one sentence campaign promise and three proof points, each tied to an item in CustomerEvidence. 3. A content plan by funnel stage (problem aware, solution comparing, deciding): one asset per stage, which role it is for, and its call to action. Include one asset that helps a champion sell internally. 4. A channel plan inside ChannelsAndBudget: what runs where, budget split, and why that channel reaches the roles in step 1. 5. Lead handoff rules: what makes a lead marketing qualified and sales qualified, the follow up time sales commits to, and what happens to leads that are not ready. 6. A competitive angle for each item in Alternatives, written as a fair comparison buyers could check. 7. A measurement plan for CampaignGoal with leading and lagging metrics and a review date. Use targets only from my inputs; otherwise leave a blank for me to fill. Rules: - Do not invent customers, logos, quotes, or results. Mark any message without proof as "needs evidence". - Write for busy buyers: plain words, no jargon stacks like "synergistic platform".
GPT-5 Custom Instructions Builder From Your Work Profile
Write ChatGPT custom instructions for GPT-5 from how you actually work: an about me block, response rules without conflicts, memory notes, and test prompts.
Act as a ChatGPT personalization specialist who writes custom instructions for people who use GPT-5 and newer models in ChatGPT every day, and who keeps instructions short, specific, and free of conflicting rules. Inputs: - My role, field, and what I use ChatGPT for most (top three tasks): [RoleAndTasks] - My current custom instructions, pasted, or "none": [CurrentInstructions] - What annoys me in ChatGPT's answers today (length, tone, filler, flattery, guessing): [Annoyances] - How I want answers formatted (length, bullets or prose, tables, code style, spelling variant): [FormatPreferences] - How I want uncertainty and mistakes handled (say I don't know, ask questions, cite sources): [HonestyPreferences] - Context ChatGPT should always know (tools I use, audience I write for, level of expertise): [StandingContext] - Things that belong to one project only, not every chat: [ProjectOnlyContext] Generate: 1. An audit of CurrentInstructions: rules that conflict with each other, vague rules ("be helpful"), and rules that fight Annoyances, each with a fix. 2. The "about me" block: role, tasks, StandingContext, and expertise level in 5 to 8 short sentences. 3. The "how to respond" block: rules for length, format, tone, HonestyPreferences, when to ask a clarifying question, and when to just answer, written as direct instructions with no rule repeated or contradicted. Keep it under 1,500 characters so it fits every plan. 4. A conflict check of the two new blocks: list any pair of rules that could pull in opposite directions and how the final wording resolves it. 5. A placement plan: what stays in custom instructions, what to move to a ChatGPT Project's instructions (from ProjectOnlyContext), and what to save as a memory or leave out. 6. Three test prompts based on RoleAndTasks, each with what a good reply should look like if the instructions work, and what to change if it does not. 7. A short version of both blocks under 600 characters total, for people who want the lightest setup. Rules: - Do not claim features, limits, or model behavior you cannot verify. If a setting may differ by app version, say so. - No instructions that try to override safety rules or ask ChatGPT to pretend it has tools it does not have.
SEO Keyword Research Prompt: Clusters From Your Search Data
Turn a Search Console export and your keyword tool list into a keyword research sheet: intent clusters, one page per cluster, priority, and SERP checks.
Act as an SEO specialist who does keyword research for small sites from the site's own Search Console queries and a keyword tool export, and who never guesses search volume or difficulty. Inputs: - The site, what it sells or publishes, and who it is for: [SiteAndAudience] - Seed topics the business wants to be found for: [SeedTopics] - Search Console queries export (query, clicks, impressions, average position): [SearchConsoleRows] - Keyword tool export (keyword, volume, difficulty, as given by the tool): [KeywordToolRows] - Pages that already exist, with URL and the main topic of each: [ExistingPages] - Competitor or SERP notes you checked by hand: [SerpNotes] - How many new pages you can publish per month: [PublishingCapacity] Generate: 1. A cleaned keyword list: merge SearchConsoleRows and KeywordToolRows, remove duplicates and off-topic queries, and keep every number exactly as exported. 2. Intent labels for each keyword: informational, commercial, transactional, or navigational, with one line on what the searcher wants. 3. Keyword clusters: group keywords a single page could rank for, name the primary keyword of each cluster, and list its secondary keywords. 4. A cluster to page map: for each cluster, the ExistingPages URL that should target it, or "new page" with a proposed slug and page type (guide, list, tool, product, comparison). 5. Quick wins: SearchConsoleRows queries with impressions but an average position between about 8 and 20, the page that ranks, and the one change to test. 6. A cannibalization check: clusters where two ExistingPages compete, and which page should own the cluster. 7. A priority table: cluster, intent, total volume from the export, difficulty from the export, business fit (high, medium, low with a reason), and a priority score explained in one line. 8. A publishing plan that fits PublishingCapacity for the next 3 months, highest priority first. 9. A SERP check list: for the top 5 new pages, what to verify by hand in the live results before writing (page types ranking, forum results, featured snippets). Rules: - Never invent volume, difficulty, clicks, or rankings. Mark anything missing as [CHECK IN TOOL]. - Use SerpNotes as given and do not claim to have seen live search results.
Real Estate Marketing Prompt: Social Ads and Lead Campaign
Plan a 4 week real estate marketing campaign for a farm area or listing: social posts, ad variations, a lead magnet, follow up texts, and a Fair Housing check.
Act as a real estate marketing strategist who plans social media and paid ad campaigns for individual agents and small teams, built on the agent's own market data and written to pass a Fair Housing review. Inputs: - Agent or team, brokerage, and service area: [AgentAndArea] - Campaign goal (seller leads in a farm area, buyer leads for a listing, or past client referrals): [CampaignGoal] - Market facts you can stand behind (your MLS numbers, listing facts, local amenities): [MarketFacts] - Lead magnet you can actually deliver (home value report, buyer guide, open house, seminar): [LeadMagnet] - Channels you use and how often you can post: [Channels] - Monthly ad budget and where leads go (CRM, spreadsheet, phone): [BudgetAndCRM] - How fast and how often you can follow up with a new lead: [FollowUpCapacity] - Brokerage and state advertising rules you must follow (brokerage name, license number, MLS rules): [ComplianceRules] Generate: 1. One campaign angle in two sentences that ties CampaignGoal to MarketFacts, plus the single promise the lead magnet keeps. 2. The audience described by need and situation (for example, owners thinking about downsizing), never by race, color, religion, sex, disability, familial status, national origin, or any other protected class. 3. A 4 week social calendar for Channels: post topic, format (photo, short video, carousel, story), hook line, and call to action for each post. 4. Three paid ad variations for the lead magnet: primary text, headline, and call to action button, each with the brokerage disclosure from ComplianceRules. Note that housing ads on Meta must run under its housing special ad category, which limits targeting. 5. Lead magnet outline and a short landing page: headline, three bullets, form fields (keep it to name, email, phone, address if needed), and the thank you message. 6. A 5 touch follow up sequence for new leads that fits FollowUpCapacity: channel, timing, and the message for each touch. 7. A budget and tracking plan: how to split BudgetAndCRM across ads, UTM tags for each channel, and the formula for cost per lead using your real results. 8. A Fair Housing and compliance check: flag any word or image idea that describes the people who should live there instead of the property, and any missing disclosure. Rules: - Use only MarketFacts for numbers. Do not invent prices, days on market, or sales counts. - Describe the property and the area's features, not the neighbors.
Poetry Workshop Prompt: Free Verse From Your Own Images
Turn a memory and your own concrete images into a free verse poem draft, then workshop it: line break notes, cliche cuts, a stronger ending, and title ideas.
Act as a poet and poetry workshop leader who helps writers turn their own memories and images into free verse, then revises line by line the way a good workshop does, without replacing the writer's voice. Inputs: - The memory, moment, or subject of the poem: [Moment] - Concrete images I remember (sounds, smells, objects, gestures): [MyImages] - A line or phrase of mine I want to keep: [KeeperLine] - The feeling under the poem that I do not want to state directly: [UnderlyingFeeling] - Poems or styles I like, described in craft terms (short lines, long sentences, plain speech, no rhyme): [StyleNotes] - Where the poem is going (journal submission, class, gift, private): [Purpose] - Length I want, in lines: [LineCount] Generate: 1. An image inventory: MyImages sorted from strongest to weakest, with a note on which ones carry UnderlyingFeeling without naming it. 2. Three possible openings for the poem, each starting from a different image, and a one line note on the tone each sets. 3. A full free verse draft at LineCount lines, built around KeeperLine, using MyImages and following StyleNotes. Do not name UnderlyingFeeling in the poem. 4. Line break notes: three places where a different break would change the meaning or the pause, shown as before and after. 5. A cliche and abstraction cut list: phrases in the draft that are vague, borrowed, or tell the feeling, with a concrete replacement drawn from MyImages. 6. Two alternative endings: one that closes on an image and one that turns or opens the poem out, with what each does. 7. Five title options that add something the poem does not already say. 8. Three workshop questions for me to answer before my next revision. Rules: - Use my images and words first. Mark any image you add as [NEW IMAGE] so I can decide. - No rhyme unless StyleNotes asks for it. Do not imitate a named living poet.
Math Teacher Prompt: Lesson, Practice Set, and Exit Ticket
Build a math lesson from one standard: warm up, worked examples, misconceptions to watch for, a tiered practice set with answers, and a 3 question exit ticket.
Act as an experienced middle and high school math teacher and instructional coach who plans lessons that use worked examples, then guided practice, then independent practice, and who checks every answer. Inputs: - Grade level, course, and class length: [GradeAndCourse] - Standard or learning objective, in your own words or your state's wording: [Standard] - What students already know and what came in the last lesson: [PriorKnowledge] - Mistakes and misconceptions you have seen on this topic: [KnownMisconceptions] - Class needs to plan for (mixed readiness, English learners, students who finish early), without names: [ClassNeeds] - Materials you have (whiteboards, calculators, graphing tool, manipulatives): [Materials] - A real world context your students care about: [StudentContext] Generate: 1. A lesson goal in student friendly words and one success criterion students can check themselves against. 2. A 5 minute warm up of 3 problems that review PriorKnowledge and set up today's Standard, with answers. 3. Two worked examples solved step by step, each step with the reason in words, plus one common wrong way to solve it and why it fails, drawn from KnownMisconceptions. 4. Three "we do" problems for guided practice, with the questions to ask students at each step. 5. A tiered practice set: 4 core problems, 3 stretch problems, and 2 support problems with a scaffold, including one word problem set in StudentContext. 6. A full answer key for every problem in sections 2 to 5, with the solution steps. 7. A misconception watch list: what each mistake looks like in student work and a one line question that helps the student find it. 8. A 3 question exit ticket that checks the success criterion, with answers and what to reteach if a student misses each question. 9. Pacing for the class length in GradeAndCourse, minute by minute. Rules: - Check every answer by substituting it back. Show the check for the worked examples. - Keep numbers clean enough to solve without a calculator unless Materials includes calculators and the Standard needs them.
Executive Assistant Prompt: Weekly Brief and Calendar Triage
Turn your executive's calendar, inbox items, and priorities into a weekly brief: conflicts to fix, meeting prep notes, decisions due, and drafts ready to send.
Act as a senior executive assistant who supports a busy executive and prepares a Monday weekly brief that fixes calendar problems before they happen and puts every decision in front of the executive on time. Inputs: - Executive's role and the top three priorities this quarter: [ExecPriorities] - This week's calendar, pasted as a list (day, time, meeting, attendees, location or link): [WeekCalendar] - Open inbox items and requests waiting on the executive: [InboxItems] - Deadlines and decisions due this week or next: [DecisionsDue] - Travel this week (flights, hotels, ground transport) if any: [TravelDetails] - Executive's working preferences (focus blocks, no meetings before a time, buffer rules): [WorkingPreferences] - What you, the assistant, can decide or send without asking: [AssistantAuthority] Generate: 1. A calendar triage list: double bookings, meetings without an agenda or link, missing buffers per WorkingPreferences, and meetings that do not serve ExecPriorities, each with a recommended fix (move, shorten, delegate, decline) and who to contact. 2. A protected time plan: where to place focus blocks this week and which meetings must move to make room. 3. Meeting prep notes for each meeting the executive leads or where a decision is made: purpose, what the executive needs to know, the one decision or ask, and the pre-read to send. 4. A decisions and deadlines table: item, due date, who is waiting, what the executive needs to decide, and the recommended slot on the calendar to do it. 5. Inbox triage of InboxItems: reply needed from the executive, assistant can handle under AssistantAuthority, delegate to someone else, or file. Include a two line draft for each item the assistant can handle. 6. A travel check of TravelDetails: timing risks between flights and meetings, confirmations to collect, and a one page itinerary. 7. The Monday brief itself: five lines or fewer at the top (the week in one look), then the sections above, written so the executive can read it in three minutes. Rules: - Never send or accept anything outside AssistantAuthority; list it as "needs your OK." - Do not invent attendees, times, flight numbers, or confirmation codes. Mark gaps [CONFIRM].
Construction PM Prompt: 3 Week Look Ahead and Constraint Log
Turn your schedule, open RFIs, submittals, and field notes into a 3 week look ahead, a constraint log with owners, an owner update, and an OAC meeting agenda.
Act as a construction project manager for a general contractor who runs weekly planning from the master schedule, open RFIs and submittals, and field notes, and who removes constraints before they stop a crew. Inputs: - Project type, size, location, and current phase: [ProjectSnapshot] - Master schedule milestones and activities for the next 3 weeks, with dates: [ScheduleActivities] - Open RFIs with number, question, date sent, and who owes the answer: [OpenRFIs] - Submittals with status (not sent, in review, approved, revise and resubmit) and lead times: [Submittals] - Inspections needed and how they are scheduled with the authority having jurisdiction: [Inspections] - Subcontractor crews, manpower, and any issues raised in the last foreman meeting: [SubsAndCrews] - Field notes from this week (weather, delays, deliveries, safety observations): [FieldNotes] Generate: 1. A 3 week look ahead table by week: activity, trade, area, start and finish, and the constraint that could stop it (RFI, submittal, inspection, material, manpower, predecessor work). 2. A constraint log: each constraint, the activity it blocks, the owner, the date it must clear to hold the schedule, and the next action. 3. An RFI and submittal hot list: items that will block work in the look ahead, ordered by need by date, with a one line follow up message for each. 4. An inspection plan: each inspection in the look ahead, what must be complete before calling it, and when to request it. 5. A schedule risk note: activities on or near the critical path that are at risk, the days at risk, and two recovery options for each (resequence, add crew, split area, expedite). 6. A one page owner update: progress this week, the look ahead in three lines, decisions needed from the owner or architect, and risks in plain words. 7. An OAC (owner, architect, contractor) meeting agenda with timed items and the decisions needed. 8. A foreman meeting script: what each trade needs to hear this week, in the order of work. Rules: - Do not invent dates, RFI answers, or approval statuses. Mark gaps [CONFIRM]. - Do not decide contract or change order entitlement; flag possible changes as "notify per contract." - Safety items from FieldNotes go to the top of the foreman script.