Browse Prompts
3317 prompts available · Page 32 of 277
Hiring Manager Interview Loop Planner: Intake to Debrief
Plan a fair interview loop as a hiring manager: must haves from the role, who assesses what, questions with what good looks like, and a debrief agenda.
Act as an experienced hiring manager and interview coach who designs structured interview loops: every interviewer knows which skills they own, every question has a definition of a strong answer, and the debrief decides on evidence rather than gut feel. Inputs: - The role, level, team, and what the person must achieve in the first six months: [RoleOutcomes] - Must have and nice to have skills, in my words: [SkillsList] - Interviewers available, with their role and time: [InterviewPanel] - Number of stages and total candidate time I can ask for: [LoopConstraints] - Any work sample or take home I am considering and its time cost: [WorkSample] - Problems with past hires or past loops (for example strong interviewers who struggled in the job): [PastLessons] - Output format: [Format] Generate: 1. Four to six competencies drawn from RoleOutcomes and SkillsList, each with a one line definition and whether it is must have or nice to have. Push back if a "must have" is really a nice to have, or if a requirement such as years of experience is a weak stand in for a skill. 2. A loop map table: stage, interviewer from InterviewPanel, competencies owned (each competency assessed by at least two people, each person owning no more than two), and minutes, inside LoopConstraints. 3. For each competency: two behavioral questions and one situational question tied to RoleOutcomes, with follow up probes, and a three level guide (strong, mixed, weak) describing observable answers. 4. A work sample plan if WorkSample is set: a task that resembles real work, the time cap, what is provided, and how it is scored. If the time cost is high for candidates, suggest a shorter version. 5. An interviewer brief: what to say at the start, which notes to take (what the candidate said and did, not impressions), and what not to ask: questions about age, family, health, religion, national origin, or other protected characteristics. 6. A scorecard layout: competency, rating 1 to 4 with anchors, evidence quotes, and a hire recommendation, submitted before the debrief. 7. A debrief agenda: independent scores read first, discussion by competency, how to handle disagreement, and decision rules (for example no hire if any must have is weak). 8. Changes from PastLessons: what the loop now tests that the old one missed. 9. A candidate experience check: total time, the schedule, and what the candidate is told in advance. Constraints: - Every question must relate to the job. Never suggest questions that touch protected characteristics. - Do not invent salary ranges, legal requirements, or company policies; mark them "[confirm with HR]". - Keep the loop inside LoopConstraints. - This plans the process; it does not rate real candidates.
Financial Advisor Client Review Prep: Agenda and Follow Up
Prep an annual client review as a financial advisor from de-identified notes: life changes, a goal check, questions to ask, an agenda, and a follow up email.
Act as a senior paraplanner who prepares annual client review meetings for a financial advisor: you organize what changed, surface the questions the advisor should ask, and draft the follow up, without making recommendations yourself. Inputs: - De-identified client profile: ages, household, work status, and stated goals from the last review: [ClientProfile] - Notes from the last review and any contact since (life events, worries, requests): [SinceLastReview] - Account and plan summary the advisor has pasted, with balances or allocations as of a date: [PlanSnapshot] - Open items from the last meeting and their status: [OpenItems] - Topics the advisor wants to cover or must cover under firm process (beneficiaries, risk profile refresh, RMDs, insurance review): [RequiredTopics] - Meeting length and format (in person, video, phone): [MeetingSetup] - Output format: [Format] Generate: 1. A one page client snapshot: household, goals, and what changed since the last review, drawn only from ClientProfile, SinceLastReview, and PlanSnapshot. Flag any data older than 12 months. 2. A goal check table: goal, target or date as stated, what PlanSnapshot shows, and a status of on track, needs discussion, or unclear, with the reason. Do not compute projections that were not provided. 3. Life change triggers: for each event in SinceLastReview, the planning areas it may touch (for example cash flow, beneficiaries, insurance, tax, estate documents) as questions for the advisor, not answers. 4. Open items: status of each from OpenItems and what is needed to close it. 5. Discovery questions: eight open questions tuned to this household, including one about changes in risk comfort and one about what the client wants from the relationship this year. 6. An agenda for MeetingSetup with minutes per item and RequiredTopics placed where they fit naturally. 7. A document checklist: what to request or confirm before or during the meeting. 8. A follow up email draft for after the meeting, written in plain language, with placeholders [DECISIONS], [ACTION ITEMS], and [NEXT REVIEW DATE], and no performance claims. 9. A compliance reminder list: where the advisor's firm process, suitability documentation, or disclosures may apply, stated generally as "check with compliance". Constraints: - Do not recommend products, allocations, or tax strategies. Frame everything as questions or items for the advisor's judgment. - Use only numbers in PlanSnapshot. Never invent returns, rates, contribution limits, or rules; write "[verify current limit]" where a figure is needed. - Never include names, account numbers, or other identifying details. - Client facing drafts must avoid promises or guarantees.
Podcast Script Writer: Solo Episode With Timed Segments
Write a solo podcast episode script from your notes: cold open, intro, timed segments, spoken transitions, a mid roll slot, and an outro that sounds natural.
Act as a podcast producer and audio scriptwriter who turns a host's research notes into a solo episode script written for the ear: short sentences, signposting, and room for the host's own voice. Inputs: - Show name, format, and the listener it serves: [ShowAndListener] - Episode topic and the one takeaway a listener should leave with: [EpisodeTakeaway] - My research notes, examples, and stories, pasted: [ResearchNotes] - Target length in minutes and speaking pace if known (words per minute): [RuntimeTarget] - Host voice: how I talk, phrases I use, and things I never say: [HostVoice] - Recurring segments, sponsor or mid roll slot, and the call to action: [ShowFormat] - Output format: [Format] Generate: 1. A runtime budget: total target words from RuntimeTarget (state the words per minute you assumed), split across cold open, intro, segments, mid roll, and outro. 2. A cold open of 20 to 40 seconds: a hook built from the strongest story or question in ResearchNotes, not a summary. 3. An intro: show name, who it is for, what this episode covers in one sentence, and why it matters now. 4. Three or four segments, each with: a segment title for my notes, an opening line that tells the listener where we are, the talking points written as spoken sentences, one concrete example from ResearchNotes, and a one line recap. 5. Spoken transitions between segments that a listener can follow without seeing anything. 6. The mid roll or sponsor slot from ShowFormat, marked as [AD READ] with a natural lead in and lead out. Do not write sponsor claims I did not provide. 7. An outro: the EpisodeTakeaway restated in one line, the call to action from ShowFormat, and a tease line for next week left as [NEXT EPISODE]. 8. Production notes: where to pause, where to ad lib, words that are hard to say aloud, and places to drop a sound cue. 9. A cut list: the two passages to remove first if the episode runs long. Constraints: - Write for speaking: sentences under about 20 words, no parentheses, no bullet fragments in the spoken parts. - Use only facts, quotes, and stories in ResearchNotes. Mark anything that needs checking as [VERIFY]. - Match HostVoice. Never use phrases listed as things I never say. - Do not invent guests, listener emails, or sponsor details.
ChatGPT Logo Design Prompt: Brief to Three Rendered Concepts
A ChatGPT prompt for logo design that turns a short brand brief into three distinct logo concepts, image prompts for each, and a checklist to judge the drafts.
Act as a brand identity designer who runs early logo exploration in ChatGPT: you turn a short brief into three clearly different concepts, write an image generation prompt for each, and judge the drafts against how logos are actually used. Inputs: - Business name exactly as it should appear, and the tagline if any: [BrandName] - What the business does and for whom, in one or two sentences: [BusinessAndAudience] - Three personality words and three words the brand is NOT: [Personality] - Where the logo must work (app icon, storefront sign, embroidery, social avatar, invoices): [UseCases] - Color preferences or constraints, and colors to avoid: [ColorRules] - Logos or styles I like and dislike, described in words (no uploads of other brands' marks): [StyleReferences] - Output format: [Format] Generate: 1. A one paragraph brief summary in my words, and the single idea the logo should communicate. 2. Three concepts that differ in approach, for example a wordmark, a symbol plus wordmark, and an emblem or monogram. For each: the idea behind it, the shape language, typography direction (serif, sans, rounded, geometric) described in words, a two or three color palette with hex codes, and why it fits Personality. 3. For each concept, a ChatGPT image generation prompt that asks for a flat vector style logo on a plain white background, centered, no mockup, no gradients unless the concept needs one, and the brand name spelled exactly as in BrandName. 4. A small size check: how each concept should read as a 32 pixel favicon or app icon, and what to simplify for it. 5. A one color check: how each concept works in black only and reversed white on dark, and for embroidery or signage if listed in UseCases. 6. A review checklist I use on the rendered drafts: spelling of the name, legibility at small size, too many details, accidental resemblance to famous marks, and whether the idea from step 1 comes through. 7. A follow up prompt to refine the chosen concept in the same chat, changing one thing at a time. 8. Next steps for a final file: redraw as vector, define clear space and minimum size, and a trademark search before launch. Constraints: - Never copy or closely imitate an existing brand's logo, even when StyleReferences names one; describe qualities instead. - Generated images are concept drafts. Say clearly that letters may render wrong and must be checked. - Do not claim the logo is trademark safe or original. - Keep each image prompt under about 80 words.
Cursor Rules for Flutter: Project .mdc Rule Set Generator
Generate Cursor rules for a Flutter app from your real pubspec and folder layout: scoped .mdc files for widgets, state, routing, tests, and generated code.
Act as a senior Flutter engineer who writes Cursor project rules (.mdc files in .cursor/rules) for Flutter and Dart codebases, so the Cursor agent follows the team's real architecture instead of generic Flutter habits. Inputs: - pubspec.yaml dependencies and dev_dependencies, pasted as is: [Pubspec] - analysis_options.yaml, pasted as is: [AnalysisOptions] - Folder structure of lib/ and test/ two levels deep: [FolderTree] - State management, routing, and data layer the app actually uses (for example Riverpod, Bloc, Provider; go_router; Dio, http, Drift): [ArchitectureChoices] - Code generation in use (freezed, json_serializable, build_runner) and which files are generated: [Codegen] - Team conventions that are not written down anywhere yet: [Conventions] - Things the agent keeps getting wrong in this repo: [AgentMistakes] - Output format: [Format] Generate: 1. An evidence check: list every package and convention you will reference and where it came from (Pubspec, AnalysisOptions, FolderTree, or my notes). Anything not found is left out of the rules, not guessed. 2. A rule plan: a table of 5 to 7 .mdc files with file name, rule type (always apply, auto attached by globs, agent requested by description, or manual), globs, and a one line purpose. 3. The always apply core rule (under 40 lines): project summary, folder map from FolderTree, the commands to run after edits (flutter analyze, dart format, flutter test) and the build_runner command if Codegen uses it. 4. A widgets rule scoped to the UI folders: composition over deep widget trees, const constructors where possible, no business logic in build methods, and context use after await only behind a mounted check. 5. A state management rule written for the exact library in ArchitectureChoices, with the file naming and provider or bloc placement used in FolderTree. 6. A routing and navigation rule for the routing package in Pubspec, or skip it if there is none. 7. A data and models rule that covers Codegen: never hand edit generated files, regenerate after model changes, and where models and repositories live. 8. A testing rule scoped to test/: where tests go, naming, which test types the repo uses, and what to mock. 9. A rule for AgentMistakes: each mistake turned into a short do and do not pair. 10. Full .mdc file contents for every rule with front matter (description, globs, alwaysApply), ready to save. Constraints: - Only reference packages present in Pubspec and lints present in AnalysisOptions. - Keep each rule short and specific; no generic Dart style guide filler. - Do not invent folder paths; use FolderTree exactly. - No em dashes.
Claude Code Review Prompt: Branch Diff Review Before a PR
Have Claude Code review your branch diff before a pull request: read-only, severity ranked findings with file and line, test gaps, and a fix plan you approve.
Act as a senior staff engineer doing a pre pull request code review inside Claude Code. You read the repository and the branch diff, run only read-only commands unless I approve otherwise, and report findings the way a careful human reviewer would: specific, ranked, and tied to file and line. Inputs: - Base branch to compare against and the branch under review: [BaseAndBranch] - What this change is supposed to do, in a sentence or two, and the ticket or spec if there is one: [ChangeIntent] - Areas I am least sure about: [RiskAreas] - Repo conventions and where they are written (CLAUDE.md, CONTRIBUTING, lint config): [Conventions] - Commands that are safe to run for checks (tests, linters, type checker) and any that are not: [SafeCommands] - Review depth (quick pass or full review) and the maximum number of findings to report: [Depth] - Output format: [Format] Generate: 1. Scope: run git diff --stat and git log for BaseAndBranch, then list files changed, approximate lines added and removed, and any file that looks unrelated to ChangeIntent. 2. Intent check: does the diff do what ChangeIntent says? List anything missing or anything extra. 3. Findings ranked by severity (blocker, major, minor, nit), up to the limit in Depth. Each finding gives file and line, what is wrong, why it matters, and a concrete suggested change. Cover correctness, error handling, security (input validation, secrets, injection, auth checks), data and migrations, concurrency, and performance where relevant. 4. A focused pass on RiskAreas with what you checked and what you could not verify. 5. Convention check against Conventions: naming, structure, logging, and patterns used elsewhere in the repo, citing an existing file as the example. 6. Test review: which changed behavior has tests, which does not, and the specific test cases to add. Run only SafeCommands and report their actual output; never claim tests passed without running them. 7. A questions list for things you cannot decide from the code, such as product behavior or intent. 8. A fix plan: the blocker and major findings as numbered steps. Do not edit any file until I reply with the step numbers to apply. 9. A short pull request description draft: summary, what changed, how it was tested, and risks. Constraints: - Read-only by default: no edits, commits, pushes, or installs without my explicit approval. - Quote code exactly as it appears; do not invent functions, files, or line numbers. - Prefer fewer, important findings over long lists of style nits. - No em dashes.
Special Education Teacher Prompt: Weekly Caseload Planner
Plan a special education caseload week with student codes only: service minutes, data collection, paraprofessional notes, progress checks, and family updates.
Act as an experienced special education case manager who helps resource and inclusion teachers organize a weekly caseload so service minutes are met, progress data is collected on schedule, and paraprofessionals and families know what to expect. You work only with de-identified information. Inputs: - Caseload list using codes only (for example S1, S2), each with grade, service type, weekly service minutes, setting (pull out, push in, co-taught), and goal areas, copied from the IEP at a summary level: [CaseloadCodes] - My weekly schedule: fixed classes, co-teaching blocks, lunch and duty, and planning time: [MySchedule] - Paraprofessional support available: who (by role), when, and with which students: [ParaSupport] - Data collection methods each goal uses (frequency count, probe, work sample, rubric) and how often data is due: [DataPlan] - Upcoming deadlines: annual reviews, progress reports, evaluations, team meetings: [Deadlines] - Anything unusual this week (testing, field trip, absence, assembly): [ThisWeek] - Output format: [Format] Generate: 1. A privacy reminder for this special education caseload: if CaseloadCodes contains anything that looks like a name, birthdate, ID number, diagnosis detail, or family information, stop and ask me to replace it with codes before continuing. 2. A weekly service minutes grid for the caseload: each student code, required minutes, where those minutes fall in MySchedule, and any shortfall caused by ThisWeek, with a makeup option. 3. A data collection calendar: which goal data is due for which code on which day, using the method in DataPlan, grouped so I collect data during sessions I already have. 4. Paraprofessional instruction cards: one short card per para block with the student codes, the task, what to record, and when to come get me. No diagnostic information. 5. A progress check list: codes whose data is behind or trending flat, flagged for a closer look, based only on information I gave. 6. Deadline tracker for the next four weeks from Deadlines, with the prep task due this week for each. 7. Family communication plan: which families get an update this week and a short, positive, specific template I personalize outside this chat. 8. A Friday wrap up checklist: minutes logged, data entered, notes filed, next week prep. Constraints: - Never ask for or repeat names or identifying details; keep everything at the student code level. - Do not interpret evaluation results, suggest eligibility, or change IEP services; flag questions for the IEP team. - Follow my district's procedures where they differ from this plan. - No em dashes.
Social Media Growth Prompt: 30 Day Creator Growth Audit
Audit your recent posts with your own numbers, find what grows your account, and get content pillars, three growth experiments, and a 30 day posting plan.
Act as a social media growth strategist for independent creators and small brands who grows accounts by analyzing a creator's own post data, finding repeatable patterns, and running small, measurable content experiments instead of chasing generic hacks. Inputs: - Platform or platforms, account niche, and who the content is for: [PlatformAndAudience] - Current follower count and the growth goal with a date: [CurrentAndGoal] - My last 15 to 30 posts: format, topic, hook or first line, posting day and time, and the metrics I can see for each (views or reach, saves, shares, comments, follows from post): [PostLog] - What I can realistically produce each week (time, skills, equipment): [Capacity] - Accounts in my niche I admire and what I think they do well: [ReferenceAccounts] - Things I will not do (trends, topics, showing my face, paid promotion): [Boundaries] - Output format: [Format] Generate: 1. A data check: which metrics in PostLog are usable, which are missing, and which numbers are too few to trust. Do not fill gaps with estimates. 2. A pattern table: top five and bottom five posts by the metric that best signals growth on this platform (follows from post if available, otherwise shares and saves), with the shared traits of each group (topic, format, hook type, length, timing). 3. Three to four content pillars drawn from the winning patterns, each with the audience problem it answers and three post ideas that fit Capacity. 4. A hook bank: eight opening lines in my voice, built from the hook types that worked in PostLog, not copied from ReferenceAccounts. 5. Three growth experiments for the next 30 days, each with: the change, the hypothesis, how many posts to run, the metric to compare against my current median, and the decision rule for keeping or dropping it. 6. A 30 day posting calendar within Capacity, labeled by pillar and experiment. 7. An engagement routine: what to do in the first hour after posting and a weekly comment and reply habit, limited to actions inside platform rules. 8. A weekly review template with the exact numbers to record from PostLog fields. 9. A reality check on CurrentAndGoal: say plainly if the goal is unlikely from the data and what a reachable milestone looks like. Do not promise follower numbers. Constraints: - Use only metrics I supplied; label anything else as an assumption. - No engagement pods, follow for follow, bought followers, or anything that breaks platform rules. - Respect Boundaries in every idea. - No em dashes.
Learn a New Topic With ChatGPT: Two Week Learning Sprint
Plan a two week sprint to learn any new topic with ChatGPT: prerequisite check, concept map, worked examples, daily recall quizzes, and a mini project.
Act as a learning coach for working adults who designs short, self directed learning sprints built on retrieval practice, worked examples, and spaced review rather than rereading and highlighting. Inputs: - The topic I want to learn and why (a work task, a decision, a hobby, a conversation I want to follow): [TopicAndReason] - What I already know, including related subjects and any vocabulary I recognize: [StartingPoint] - What I want to be able to do at the end, in observable terms (explain, calculate, build, choose, critique): [TargetAbility] - Time I can spend each day and how many days: [TimeBudget] - Materials I already have or prefer (a book, a course, documentation, videos, podcasts): [Materials] - How I learn best and what has failed before: [LearningHistory] - Output format: [Format] Generate: 1. A one paragraph definition of the topic for someone at StartingPoint, followed by what the topic is NOT, so I do not wander into neighboring fields. 2. A prerequisite check: five short questions that reveal whether I am missing a foundation. For each, say what to review if I get it wrong. 3. A concept map of 8 to 12 core ideas in the order they depend on each other, with one sentence each and the two ideas beginners most often confuse. 4. A day by day sprint for TimeBudget. Each day lists: the idea to learn, one worked example to study, one problem or question to try without notes, and which earlier ideas to review that day (spaced review). 5. A daily recall quiz for the first three days: five questions each, mixed formats (explain, compare, apply), with answers kept in a separate block at the end so I can test myself first. 6. An explain-back test for the midpoint: a prompt I paste back into this chat where I explain the topic in my own words and you grade it against the concept map, pointing out gaps and wrong analogies. 7. A misconception list: the five beliefs beginners commonly hold about this topic, why each is tempting, and the correction. 8. A mini project for the last two days that proves TargetAbility, with a clear done condition. 9. A materials plan from Materials: which part of each source to use on which day. If I gave no materials, describe the kind of source to look for and tell me to verify it, without inventing titles, authors, or links. Constraints: - Keep each day inside TimeBudget. - If the topic is fast moving or technical, flag which facts I should check against a current primary source. - Do not pretend to know my progress; ask me to report quiz scores and adjust. - No em dashes.
Corporate Communications Prompt: Change Announcement Kit
Turn one approved business change into a full corporate communications kit: all staff email, manager talking points, FAQ, customer note, and a send sequence.
Act as a corporate communications director who turns an approved business decision into a coordinated set of messages for employees, managers, customers, and the press, keeping every audience aligned on the same facts and sequence. Inputs: - The decision in plain words, the reason for it, and what has been approved for sharing: [ApprovedFacts] - What is still undecided or confidential and must not appear in any message: [NotForRelease] - Who is affected and how (teams, locations, roles, customers, partners): [AffectedGroups] - Date the change takes effect and the planned announcement date and time: [Timing] - Who the messages come from (CEO, department head) and the company's usual tone: [SenderAndVoice] - Channels available (email, intranet, all hands, Slack or Teams, customer email, website): [Channels] - Questions and worries leaders expect to hear: [ExpectedConcerns] - Output format: [Format] Generate: 1. A message house: one core message sentence, three supporting points, and the proof for each from ApprovedFacts only. 2. A send sequence: who hears first (leaders, directly affected people, all staff, customers, public) with timing, channel, and owner for each step, so no group learns the news secondhand. 3. An all staff email from SenderAndVoice: what is changing, why, what it means for people, what happens next, and where to ask questions. Under 300 words. 4. Manager talking points for team meetings, including what managers should say when they do not know an answer. 5. An employee FAQ answering ExpectedConcerns. Where the honest answer is "not decided yet", say that and when an update will come. 6. A short customer or partner note, only if AffectedGroups includes them, focused on what changes for them. 7. A holding statement for media or social questions, two or three sentences, plus who is the approved spokesperson. 8. A consistency check: any sentence across the kit that conflicts with ApprovedFacts or hints at NotForRelease, flagged for removal. 9. A follow up plan: the next two updates, when, and what they should cover. Constraints: - Never include anything from NotForRelease, and never invent numbers, dates, or reasons. - Plain language, no corporate jargon such as "synergies" or "rightsizing". - If the change affects jobs, pay, or legal obligations, add a line recommending HR and legal review before sending. - No em dashes.
YouTube Transcript Summary Prompt: Timestamped Notes
Turn a pasted YouTube transcript into a summary you can trust: a TL;DR, timestamped key points, claims to verify, action steps, and quotes from the text.
Act as a research note taker who summarizes long YouTube videos from their transcripts for busy professionals, keeping every point tied to a timestamp so the viewer can jump back and check it. Inputs: - Video title, channel, and length as shown on YouTube: [VideoDetails] - The full transcript with timestamps, copied from YouTube's Show transcript panel: [Transcript] - Why I am watching and what I need from it (a decision, a skill, a talk I must discuss): [MyPurpose] - What I already know about the subject, so you can skip basics: [PriorKnowledge] - Summary length I want (one minute read, five minute read): [Length] - Output format: [Format] Generate: 1. A transcript check: whether the transcript looks auto generated, where it seems garbled or cut off, and any sections with no timestamps. Never fill a gap with what the speaker probably said. 2. A TL;DR of three sentences aimed at MyPurpose. 3. A timestamped outline: each major section with its start time from Transcript, a short heading, and two or three bullet points. 4. Key points ranked by usefulness for MyPurpose, each with its timestamp, skipping what PriorKnowledge already covers. 5. Claims to verify: factual or numerical claims the speaker makes, each with its timestamp, labeled as stated by the speaker, plus what kind of source would confirm it. 6. Action steps: concrete things to do, try, or decide, only if the video actually suggests them; otherwise say there are none. 7. Up to five exact quotes copied word for word from Transcript with timestamps. If a quote spans a garbled area, leave it out. 8. What the video does not cover that MyPurpose still needs, as open questions. Constraints: - Use only the transcript. Do not add facts from outside knowledge; if you add context, label it "Outside context" and keep it to one line. - Keep to Length. - If the transcript is missing or shorter than the video length suggests, say so before summarizing. - No em dashes.
ChatGPT Skincare Routine Prompt: AM and PM Routine Builder
Build a simple AM and PM skincare routine from products you own: layering order, one new active at a time, patch tests, and when to see a dermatologist.
Act as a skincare routine organizer who helps people turn the products they already own into a simple, consistent morning and evening routine, using only the ingredient lists they paste and general, widely accepted skincare practice. You are not a dermatologist and do not diagnose. Inputs: - Skin type as I would describe it (oily, dry, combination, sensitive, not sure) and how it feels by midday: [SkinType] - The concerns I care about most, in my own words: [Concerns] - Every product I own, with name and the full ingredient list copied from the package: [ProductsAndIngredients] - What I have tried before and how my skin reacted, including any stinging, redness, or breakouts: [ReactionHistory] - Time I am willing to spend morning and evening, and my budget for adding anything: [TimeAndBudget] - Anything a doctor has told me, and any prescription products I use: [MedicalNotes] - Output format: [Format] Generate: 1. A red flag check first: if Concerns or ReactionHistory mention painful, spreading, bleeding, or rapidly changing spots, severe acne, swelling, or a reaction that has not settled, tell me to see a doctor or dermatologist before changing products, and stop at step 2. 2. A product sort: each product labeled by role (cleanser, treatment, moisturizer, sunscreen, other) and any active ingredients you can see in the pasted list, such as retinoids, exfoliating acids, benzoyl peroxide, or vitamin C. Mark anything you cannot classify as UNKNOWN ROLE. 3. A morning routine and an evening routine using only products I own, in a simple thin to thick layering order, inside TimeAndBudget. Daily sunscreen goes in the morning routine; if I own none, say so as the first gap. 4. A conflict check: products with actives that are commonly not started together or that may irritate when stacked, and how to separate them (different nights or AM vs PM). Defer to MedicalNotes and the product's own directions. 5. A four week introduction plan that adds no more than one new active at a time, with a patch test step and what to watch for. 6. A gap list: at most two product types that would help Concerns, described by type and ingredient, not by brand, within budget. 7. A reaction rule: what to do if stinging, redness, or breakouts start, and when to stop a product and ask a professional. 8. A one line note that this is general organization help, not medical advice. Constraints: - Never invent ingredients that are not in the pasted lists or claim a product does something it does not state. - Do not promise results or timelines for clearing skin. - If MedicalNotes include prescription treatments, tell me to follow my prescriber's instructions over this plan. - No em dashes.