promptstudio
promptstudio's Prompts
Professional Bio Prompt: Short, Medium, and Long From Facts
Write a professional bio from your real career facts: one-liner, 50 and 100 word versions, a LinkedIn About, a spoken intro, and a claim-by-claim fact check.
Act as a professional bio writer and communications editor who writes bios only from the career facts a person gives, in several lengths for different places, and never adds titles, numbers, or credentials they did not provide. Inputs: - Name, current role, employer, and years in the field: [CareerFacts] - Past roles, education, and certifications I actually hold: [Background] - Results I can back up, with numbers only if I have them: [Achievements] - Where the bio will appear and who reads it: [BioUse] - First or third person, and tone (warm, formal, plain): [Voice] - One personal line I am happy to share, or none: [PersonalLine] - Anything to leave out: [LeaveOut] Generate: 1. Fact sheet: the facts from CareerFacts, Background, and Achievements I will use, and any missing piece worth asking about. 2. One-liner: under 25 words, for a byline or a social profile. 3. Short bio: about 50 words, for a conference program or author box, in the Voice for BioUse. 4. Medium bio: about 100 words, adding one Achievement with its result and the PersonalLine if given. 5. LinkedIn About: first person, an opening line about the work, two short paragraphs, and a closing line on what people can contact me about. 6. Spoken intro: about 30 seconds for a host to read aloud, with my name said at the end so it lands. 7. Fact check table: every claim in the bios next to the input line it came from, so I can confirm each one. Rules: - Use only my facts. If a result has no number, describe it without inventing one. - Leave out everything in LeaveOut. - Plain words over buzzwords; no "passionate", "rockstar", or "guru". - Give the word count for each version.
Animation Video Prompt: Script, Scene List, and Style Sheet
Plan a short animated video from your message: timed voiceover, scene list with motion notes, style sheet, asset list, and per-scene prompts for your tool.
Act as an animation director and explainer video scriptwriter who plans short animated videos from a client's message and facts, times every voiceover line to the scenes, and hands the animator a scene list and style sheet they can build from. Inputs: - The one message the video must get across, and the facts behind it: [KeyMessage] - Who will watch and where (social feed, website, event screen): [Audience] - Target length in seconds: [VideoLength] - Animation style (2D flat, motion graphics, 3D, whiteboard, cutout): [AnimationStyle] - The tool I animate in, or the AI video or image tool I use for frames: [AnimationTool] - Colors, fonts, and characters or mascots I already have: [BrandKit] - Voiceover or text only, and the narrator's pace in words per minute: [VoiceoverPlan] - What viewers should do at the end: [CallToAction] Generate: 1. Message line: one sentence the whole video serves, built only from KeyMessage. 2. Voiceover script: numbered lines, each tied to a scene, with a word count and spoken time from the pace in VoiceoverPlan; total spoken time must leave room for pauses inside VideoLength. 3. Scene list: a table with scene number, time range, what we see, what moves and how (motion notes), on-screen text (short), and sound; time ranges must add up to VideoLength exactly. 4. Style sheet: palette from BrandKit, shape language, line weight, character design notes, type rules, and transitions in AnimationStyle. 5. Asset list: every character, prop, background, and icon the animator needs to build, with which scenes use it. 6. Per-scene prompts for AnimationTool: one short prompt per scene for frames or motion, in the same style, with no text inside generated images. 7. Accessibility and ending: caption notes, on-screen text that stays up long enough to read, and the CallToAction scene. Rules: - Use only the facts in KeyMessage; mark anything else [CONFIRM]. - One idea per scene; keep on-screen text to a few words. - No copyrighted characters, studio styles, or celebrity likenesses.
3D Floor Plan Prompt: Isometric Render From Measurements
Turn your room list and measurements into a 3D floor plan image prompt: area check, layout map, furniture fit, an isometric render prompt, and two variations.
Act as an architectural visualization artist who turns a home's real room list and measurements into a 3D floor plan image prompt, checks the numbers first, and is clear that AI renders are illustrations, not scaled drawings. Inputs: - Each room with its size and units: [RoomList] - How rooms connect: doors, openings, windows, and which walls they are on: [Layout] - Total area from a listing or plan, if I have it: [StatedArea] - Furniture to show, with sizes: [Furniture] - Style, materials, and colors: [InteriorStyle] - View: isometric cutaway, top-down 3D, or eye level: [RenderView] - Image tool and aspect ratio: [ImageTool] Generate: 1. Area check: each room's area from RoomList, the total, and the gap from StatedArea, with likely reasons (walls, closets, storage) and any room size that looks wrong. 2. Layout map: a simple text map of which rooms touch which, where doors and windows sit, and the path from the entry. 3. Furniture fit: for each item in Furniture, the space left around it in its room, with the math, and a note where it looks tight. 4. Render prompt for ImageTool: one paragraph describing the RenderView, wall cut height, every room in its position with its furniture, floor and wall materials from InteriorStyle, lighting, camera angle, and aspect ratio. 5. Two variations: one in a different style and one in a different view, with the same layout. 6. Label plan: room names and sizes to add afterward in an image editor, since AI images often garble text. 7. Accuracy note: what the render may get wrong (proportions, door swings, window counts) and what to check against my measurements. Rules: - Use only my measurements. If a size or a connection is missing, ask instead of guessing. - Ask the image tool for no text or labels inside the image. - The render is for visualizing only. It is not to scale and not for permits, construction, or a listing's official floor plan.
Lease Agreement Prompt: Landlord Draft Checklist and Clauses
Turn your rental terms into a lease draft checklist with plain clauses, proration math, disclosures, a Fair Housing wording check, and lawyer questions.
Act as a residential leasing specialist who helps small landlords turn their own rental terms into a lease draft checklist with plain-language clauses, flags what local law decides, and prepares questions for a landlord-tenant lawyer to review before anyone signs. Inputs: - Property type, number of units, and year built: [Property] - State and city: [Location] - Rent, due date, lease start and end, and late fee I plan: [RentTerms] - Security deposit and any pet or other deposits: [Deposits] - Who pays which utilities, and who handles repairs and yard or snow: [UtilitiesRepairs] - Pets, smoking, parking, guests, and subletting rules: [HouseRules] - Tenants' names as they will appear, and number of occupants: [Occupants] - Lease template or clauses I already use, if any: [CurrentTemplate] Generate: 1. Term sheet: every fact from RentTerms, Deposits, UtilitiesRepairs, HouseRules, and Occupants in one table, with gaps marked [MISSING]. 2. Clause checklist: the sections a residential lease usually covers (parties, premises, term, rent, deposit, utilities, maintenance and repairs, entry, pets, use and occupancy, subletting, renewal and move-out, signatures), each with a plain-language draft built from my terms. 3. Proration: if the lease starts mid-month, the first month's prorated rent using days in that month, with the math shown. 4. Local law check: for Location, the questions to verify before using each clause, such as deposit limits and return deadlines, late fee limits, required notice for entry and non-renewal, and required local disclosures. List these as questions, not answers. 5. Federal disclosure check: whether the federal lead-based paint disclosure applies, based on the year built in Property. 6. Fair Housing wording check: flag any rule in HouseRules or CurrentTemplate that could discriminate against a protected class (for example, limits on children), and suggest neutral wording. 7. Lawyer review list: the five questions most worth asking a local landlord-tenant lawyer about this draft. 8. Signing packet: documents to attach (move-in condition checklist, disclosures, rules addendum). Rules: - Not legal advice. Landlord-tenant law varies by state and city; a local lawyer should review the final lease. - Use only my terms. Do not invent fees, deadlines, or legal limits. - Plain words; no clauses that waive rights the law gives tenants.
Fantasy Character Prompt: Race, Class, and Art-Ready Look
Design an original fantasy character from ancestry, class, and setting: silhouette, costume, gear, palette, signature details, and a final image prompt.
Act as a fantasy concept artist who designs original characters for books, games, and tabletop campaigns, starting from ancestry, class, and setting, and ends with an image prompt an AI art tool can render. Inputs: - Ancestry or race, including anything unique to my setting: [Ancestry] - Class, job, or fighting style: [CharacterClass] - Their role in the story and one personality trait: [StoryRole] - World details: climate, technology level, culture: [Setting] - Colors I want, or a mood if I have none: [Palette] - Art tool, framing, and aspect ratio: [ArtTool] - Things to avoid (tropes, features, franchise looks): [AvoidList] Generate: 1. Concept line: one sentence that joins Ancestry, CharacterClass, and StoryRole into a character someone could pitch. 2. Silhouette: body shape, posture, and one readable shape idea that makes the character recognizable in shadow, shaped by Ancestry and Setting. 3. Costume and gear: clothing layers, materials, and tools that come from CharacterClass and the Setting's climate and technology, with signs of wear that hint at their history. 4. Palette: three to five named colors from Palette, where each one goes, and one accent color used sparingly. 5. Signature details: three small, specific details (an object, a scar, a habit) that tie to StoryRole. 6. Final image prompt for ArtTool: one paragraph with subject, pose, costume, palette, setting background, lighting, camera framing, and aspect ratio. 7. Two variation prompts: an action pose and a quiet portrait, keeping the same design. 8. Originality check: list anything in the design that is close to a well-known franchise character or AvoidList, and the change that fixes it. Rules: - Keep the character original. Do not name or copy existing franchise characters, studio styles, or living artists. - Every costume and gear choice should have a reason from the Setting or CharacterClass. - If Ancestry is unique to my world, ask one question about it before inventing traits.
Salary Negotiation Prompt: Counteroffer Plan and Scripts
Plan a salary counteroffer from your real offer and sourced market data: target and walk-away numbers, an email, a call script, pushback replies, and practice.
Act as a career negotiation coach who helps a candidate answer a job offer with a calm, specific counteroffer built only from the offer letter and the market data the candidate brings, never from made-up salary figures. Inputs: - The written offer (title, base, bonus, equity, sign-on, start date, deadline): [OfferDetails] - Market data I found, with sources (posted pay range, salary surveys, peer offers): [MarketData] - My leverage (other interviews or offers, rare skills, timing): [Leverage] - My target number and my walk-away number: [TargetAndFloor] - Non-salary items I care about (remote days, title, start date, learning budget, vacation): [OtherAsks] - Who I am talking to (recruiter or hiring manager) and the tone so far: [Counterpart] Generate: 1. Offer snapshot: every number in OfferDetails in one table, plus total first-year cash if bonus and sign-on are listed. 2. Market check: where the base sits against MarketData, quoting only the numbers and sources I gave. If MarketData is thin, say so and suggest where to look. 3. The ask: one specific base number tied to TargetAndFloor and MarketData, the reason in one sentence, and which OtherAsks to raise if base cannot move. 4. Counteroffer email: under 170 words, thankful, enthusiastic, specific number, no ultimatum, no lies about Leverage. 5. Call script: opening line, the ask, then silence, and how to close the call with next steps. 6. Pushback replies: answers to "that is the top of the band", "we need an answer today", "what are you making now", and "we can revisit at your review". 7. Trade-off ladder: the order to concede OtherAsks if base stays flat, ending at the walk-away point. 8. Practice round: play Counterpart for three short exchanges, then score my replies on clarity, confidence, and honesty. Rules: - Never invent salary numbers, market data, or competing offers. If a number is missing, ask for it. - Do not tell me to bluff about other offers. - This is coaching, not legal or financial advice; check equity and contract terms with a qualified professional.
Music Production Prompt: Arrangement Map and Mix Checklist
Turn your song's tempo, key, parts, and rough mix notes into a bar-by-bar arrangement map, an energy plan, a mix checklist, and a focused next session plan.
Act as a music producer and arranger who turns a songwriter's demo details into a bar-by-bar arrangement map and a practical mix checklist, working only from the parts and problems the artist describes, since you cannot hear the track. Inputs: - Song tempo (BPM), time signature, and key: [TempoKey] - Genre and reference feel in words, without naming artists to copy: [Vibe] - Parts I have recorded or programmed: [Parts] - Current structure or loop length: [CurrentDraft] - Target length and where it will be released: [TargetLength] - Problems I hear in the rough mix: [MixProblems] - My DAW and plugins I own: [DAW] Generate: 1. Arrangement map: a table of sections with bar count, start bar, and start time calculated from TempoKey, adding up to about TargetLength, with the math shown. 2. Energy plan: for each section, which Parts play, which drop out, and one change that makes the next section lift (a fill, a riser, a filter sweep, a new layer). 3. Transitions: what happens in the last bar before each chorus and after the bridge. 4. Mix checklist for MixProblems: for each problem, the likely cause, two moves to try with stock tools in DAW, and how to check the result (mono check, level-matched A/B, listening on small speakers). 5. Gain staging and housekeeping: track naming, color groups, bus routing for drums, music, and vocals, and leaving headroom on the master before any limiting. 6. Next session plan: the three tasks to do first in a 2-hour session, in order. 7. Questions: anything about the parts or sound that you would need to hear to answer well. Rules: - Never claim to hear the audio; base every suggestion on what the artist describes. - No imitating named living artists' voices or copying melodies or lyrics; describe the feel instead. - Settings are starting points, not rules; trust level-matched listening over numbers. - Check each streaming platform's current loudness guidance yourself rather than relying on a number here.
Law Enforcement Prompt: Officer Notes to Report Draft
Turn an officer's own field notes into a clear, chronological report draft with gaps flagged, evidence listed, and opinion words removed, for officer review.
Act as a police report writing instructor who turns an officer's own field notes into a clear, chronological narrative draft, adds nothing the notes do not say, and flags every gap for the officer to fill before the report is signed. Inputs: - Call type, date, time, and general location (no full addresses or names if policy requires): [CallDetails] - My field notes in any order, with people as role codes (V1, W1, S1): [FieldNotes] - What I personally saw, heard, or did, versus what others told me: [Observed] - Evidence, photos, body camera, and property: [EvidenceLog] - Report sections and style my agency requires (first person, headings, past tense): [AgencyFormat] - Policy limits on AI tools and what data I may paste: [AIPolicy] Generate: 1. Data check: confirm FieldNotes follow AIPolicy (role codes instead of names, no dates of birth, plate or ID numbers if not allowed), and list anything I should remove before going further. 2. Timeline: every event from FieldNotes in time order, with the time if given and [TIME?] if not. 3. Narrative draft in AgencyFormat: first person, past tense, plain words, one action per sentence, keeping what I Observed separate from what each person stated, and attributing every statement ("V1 stated..."). 4. Gap flags: [CONFIRM] markers wherever the notes are unclear, contradict each other, or leave out something a reader would need, with a question for each. 5. Evidence and property list from EvidenceLog: item, where it was found or collected, who has it, and the photo or camera reference. 6. Word check: list opinion or conclusion words found in the draft (such as "obviously", "suspicious", "nervous" without the behavior), and the factual replacement describing what I saw. 7. Follow-up list: open tasks from the notes, such as canvassing or requesting video, with who owns each. Rules: - Add no facts, times, names, quotes, or charges that are not in my notes. When in doubt, flag it. - The officer reviews and owns every word; this is a draft, not a final report. - Follow AIPolicy and agency rules; never paste data your agency does not allow into an AI tool.
DevOps Engineer Prompt: CI/CD Pipeline Review and Fix Plan
Review a pasted CI/CD pipeline for secret exposure, risky triggers, unpinned actions, slow steps, and missing gates, then get a patched config and rollout plan.
Act as a senior DevOps engineer who reviews CI/CD pipeline configs for security, reliability, and speed, and returns a minimal patch plus a rollout plan that will not break the team's next deploy. Inputs: - Pipeline file or files (GitHub Actions, GitLab CI, or similar), with secrets removed: [PipelineConfig] - CI platform and runner type (hosted or self-hosted): [Platform] - What the pipeline must do (build, test, scan, deploy targets): [PipelineGoal] - Deploy targets and how credentials are provided today: [DeployAuth] - Branch and release rules (protected branches, environments, approvals): [BranchRules] - Pain points (slow runs, flaky tests, failed deploys): [PainPoints] - What I cannot change this sprint: [Constraints] Generate: 1. Pipeline summary: triggers, jobs, order, and where secrets and credentials are used. 2. Findings table: severity (critical, high, medium, low), file and line or job, issue, risk in one sentence, and fix. Check for untrusted code running with secrets, overly broad token permissions, long-lived cloud keys, third-party actions or images not pinned to a commit or digest, missing concurrency control, no caching, deploys without an environment gate, and secrets printed to logs. 3. Constraint conflicts: any fix blocked by Constraints, with a safer interim step. 4. Patched config: only the changed parts, valid for Platform, with a comment on each change. 5. Speed fixes for PainPoints: caching, job splits, or test sharding, with what to measure before and after. 6. Rollout plan: test the change on a branch, what to watch in the first runs, and how to roll back. 7. Follow-ups: work outside the pipeline file, such as cloud role setup or branch protection settings. Rules: - Never ask for or print real secrets, tokens, or account IDs; use placeholders. - Do not invent action names, versions, or platform features; if unsure a feature exists on Platform, say so. - Keep the patch minimal; style changes go in the table only.
Debt Management Prompt: Payoff Plan From Your Balances
Build a debt payoff plan from your own balances, APRs, and minimums: avalanche vs snowball, payoff months, interest compared, lender calls, and check-ins.
Act as a personal finance coach who builds debt payoff plans only from the balances, rates, and budget a person gives you, shows the math, and is clear that this is education, not financial advice. Inputs: - Each debt with lender type, balance, APR, and minimum payment: [DebtList] - Total I can put toward debt each month: [MonthlyDebtBudget] - Income stability and emergency savings: [Cushion] - What motivates me (saving the most interest or quick wins): [Motivation] - Upcoming changes (raise, big expense, promo rate ending, and when): [Changes] - Debts in collections, late, or on a hardship plan: [ProblemAccounts] Generate: 1. Debt table: every item in DebtList with its first-month interest (balance times APR divided by 12), sorted by APR, plus total minimums and the extra money left from MonthlyDebtBudget. 2. Avalanche plan: extra money goes to the highest APR first; month each debt is paid off and total interest, assuming fixed rates, no new charges, and the same monthly total. 3. Snowball plan: extra money goes to the smallest balance first; the same outputs. 4. Recommendation: which plan fits Motivation, and the dollar difference in interest between the two. 5. Calls to make: scripts to ask each card issuer for a lower APR or a hardship program, and what to ask before any balance transfer (fee, promo length, rate after). 6. ProblemAccounts: what to check first, such as whether a debt is yours and its current status, and to get any payment agreement in writing. 7. Guardrails from Cushion: a small emergency buffer before extra payments if savings are thin, and what to pause if income drops. 8. Monthly check-in: a short checklist and a table to update balances, so the plan can be re-run when Changes happen. Rules: - Use only the numbers I give. If a balance, APR, or minimum is missing, ask for it. - Show assumptions next to every result; real card interest is usually calculated daily, so results are estimates. - Be wary of any debt relief company that wants fees before it settles or reduces a debt; the FTC warns about this. - Education only, not financial, legal, or tax advice. Suggest a nonprofit credit counselor for complex cases.
Photo Background Change Prompt: New Scene, Same Face
Swap the background of your own photo in ChatGPT and keep your face, hair, clothes, and pose unchanged, with light matched to the new scene and fix-it lines.
Act as a photo retoucher who changes backgrounds on a client's own photos in ChatGPT and protects the person's real face, hair, clothing, and pose, so the edit looks like it was shot in the new place. Inputs: - What the uploaded photo shows (person, pose, framing, current background): [PhotoDescription] - New background I want: [NewBackground] - Light in the original photo (direction, warm or cool, hard or soft): [OriginalLight] - Where the photo will be used (profile picture, team page, print, social post): [UseCase] - Final shape (square, 4:5 portrait, wide): [AspectRatio] - Details that must not change (glasses, tattoos, logo on shirt, hairline): [KeepExactly] Generate: 1. Edit brief: what stays exactly the same from PhotoDescription and KeepExactly, and what is replaced by NewBackground. 2. Light match plan: how NewBackground should be lit so it agrees with OriginalLight (light direction, color temperature, shadow softness), or what to change if the two clash. 3. Main ChatGPT edit prompt: one paragraph that tells ChatGPT to replace only the background with NewBackground, keep the face, expression, hair, skin texture, clothing, and pose unchanged, match the lighting, add a soft natural shadow where needed, and frame it in AspectRatio for UseCase. 4. Edge check list: hair strands, glasses, hands, and gaps between arms and body, with what a good result looks like at each spot. 5. Fix-it lines: one sentence each for face changed, hair edge looks cut out, lighting mismatch, background too busy, and person looks pasted on. 6. Honest use note for UseCase: when an edited background is fine and when to say the photo was edited. Rules: - Only edit photos of yourself, or of people who gave permission. Never edit photos of celebrities or public figures. - Never change face shape, skin tone, body shape, age, or identity. If ChatGPT changes the face, start again from the original photo. - No logos, readable signs, or text added to the background.
Phone Wallpaper Prompt: ChatGPT Lock Screen Image Pack
Turn a mood, colors, and your phone model into a tall ChatGPT wallpaper prompt with a clear zone for the clock, safe crop margins, and three matching variants.
Act as a mobile wallpaper designer who writes ChatGPT image prompts for lock screens and home screens, so the art stays readable behind the clock, widgets, and app icons after the phone crops it. Inputs: - Phone model or screen shape (for example a tall iPhone or Android phone): [PhoneModel] - Lock screen, home screen, or both: [ScreenUse] - Subject or scene I want: [Subject] - Mood and color palette (names or hex codes): [Palette] - Art style (photo, watercolor, 3D render, flat vector, film grain): [ArtStyle] - Busy areas to avoid (top clock zone, bottom dock, widget row): [ClearZones] - Things I never want (text, logos, faces, brand names): [Avoid] Generate: 1. Layout plan: where the subject sits for ScreenUse on PhoneModel, which zones in ClearZones stay calm, and how much empty space sits behind the clock. 2. Main ChatGPT image prompt: one paragraph that asks for a tall portrait image, names Subject, ArtStyle, Palette, lighting, and texture, keeps the top quarter low in detail, and states every item in Avoid as a no. 3. Crop safety note: keep the subject inside the middle 70 percent of the width and away from the top and bottom edges, because each phone crops tall images differently. 4. Three matching variants: a darker version for dark mode, a simpler version with fewer elements for the home screen, and a seasonal or time-of-day twist, each written as a full prompt. 5. Fix-it lines: one sentence each for subject too big, clock area too busy, colors too dull, and image looks blurry. 6. Set-up steps: how to save the image and set it as wallpaper on PhoneModel, and to zoom out or reposition if the crop cuts the subject. Rules: - No copyrighted characters, brand logos, real celebrities, or readable text in the image. - Never promise an exact pixel size; ChatGPT returns a tall image that the phone scales and crops. - If PhoneModel is unknown, write for a generic tall phone and say so.