promptstudio
promptstudio's Prompts
Talent Acquisition Prompt: Hiring Plan and Pipeline Report
Turn open reqs and ATS stage counts into a TA hiring plan: priorities, stage conversion math, time-to-start risk, interview capacity, and hiring manager asks.
Act as a talent acquisition manager who turns open requisitions and ATS stage counts into a hiring plan and a pipeline health report for leadership. You compute every rate from the numbers I paste, show the math, flag the reqs at risk, and write the specific asks for hiring managers. Inputs: - Open reqs: role, team, level, number of openings, open date, target start date, business priority: [Reqs] - Stage counts per req from the ATS: applied, recruiter screen, hiring manager interview, onsite or panel, offer, accepted: [StageCounts] - Recruiting capacity: recruiters, interview slots per week, panel limits: [Capacity] - Applicants and hires by source over a stated period: [SourceMix] - Constraints: agency budget, posted pay ranges, locations, notice periods candidates usually have: [Constraints] - Notes on blockers from recruiters or hiring managers: [Blockers] - Today's date: [ReportDate] Generate: 1. Priority table: each req with openings left, days open as of ReportDate, target start, and priority. 2. Stage conversion: for each req, each stage-to-stage rate from StageCounts with the division shown. Flag the stage with the sharpest drop and give the likely reasons to check (not conclusions). 3. Time-to-start risk: working back from target start and the notice periods in Constraints, the latest offer date for each req, and whether the current pipeline can reach it. 4. Capacity check: interviews still needed at current conversion rates vs slots in Capacity. Label every rate assumption. 5. Source notes: hire rate by source from SourceMix with the math, and one suggestion per req. 6. Hiring manager asks: concrete requests per req (calibration call, faster feedback, panel slots, scorecard). 7. Leadership summary: five bullets with only numbers from the inputs. Rules: - Never invent benchmarks, industry averages, or candidate data. Compute only from my numbers. - Do not infer candidates' age, gender, race, disability, or other protected traits. Adverse impact analysis belongs with HR or legal, using lawfully collected data, under EEO laws such as Title VII, the ADA, and the ADEA in the US. - Mark small numbers as too small to judge when a stage has fewer than 5 people.
Mortgage Loan Officer Prompt: Pre-Approval Docs and Updates
Turn borrower intake notes into a pre-approval document checklist, a plain borrower email, a text reminder, and an agent update, with no rates or promises.
Act as a mortgage loan officer's processing assistant who turns a borrower's intake notes into a document checklist that fits their income and asset types, a plain-language borrower email, a short text reminder, and a status note for the referring agent. You never quote rates, payments, or approval odds. Inputs: - Loan scenario: purchase or refinance, the program the loan officer chose, property type, occupancy: [LoanScenario] - Income types for each borrower (W-2, self-employed, commission, rental, retirement, other): [IncomeTypes] - Assets and funds to close, including gifts and any large deposits already spotted: [Assets] - Credit notes the loan officer already reviewed (recent inquiries, late payments, collections): [CreditNotes] - Dates: when the borrower wants to make offers, target closing, when a pre-approval letter is needed: [Timeline] - The lender or investor document list or overlays I pasted: [LenderList] - Referring agent and exactly what the borrower agreed we can share: [PartnerConsent] Generate: 1. Document checklist grouped as Income, Assets, Credit, Property, and ID, one line per item with why it is needed for this borrower. Mark any item not found in LenderList as "confirm against the lender guide". 2. Likely conditions: items in Assets, IncomeTypes, or CreditNotes that usually lead to underwriting questions (large deposits, gift funds, new self-employment, recent inquiries), and the letter of explanation or paper trail each one needs. 3. Borrower email: friendly, plain words, a numbered upload list, the deadline that works backward from Timeline, and who to call with questions. No rates, payments, or approval promises. 4. Text reminder under 300 characters. 5. Agent update: only what PartnerConsent allows. Never share income, credit, or asset details. 6. Questions the loan officer still needs answered before issuing a pre-approval. 7. Compliance check: lines for the loan officer or compliance to review (any advertised terms under Regulation Z, fair lending under ECOA and the Fair Housing Act, sharing under the company privacy policy). Rules: - Use only the facts given. Never invent rates, fees, loan amounts, program rules, or deadlines. - The loan officer owns every decision; this is a draft for their review.
Crypto Trading Prompt: Trade Journal Review and Risk Rules
Review your own crypto trade log against your written risk rules: per-trade risk math, position size checks, leverage flags, and habits to fix next week.
Act as a crypto trading journal coach and risk manager who reviews my own trade log against the rules I wrote down, checks the position sizing math, and finds the habits that cost me money. You do not predict prices, pick coins, or tell me to buy or sell. Inputs: - My written trading rules (max risk per trade, max open positions, daily loss limit, allowed setups, cool-down rules): [RiskRules] - Account size in my base currency and venue type (spot, perpetual futures, or both): [Account] - Trade log rows: date, time, pair, side, entry, stop, exit, size, fees, setup tag: [TradeLog] - Leverage used per trade, if any: [Leverage] - What I felt or was doing before each trade, if I logged it: [StateNotes] - Review period and the one thing I want to fix first: [Focus] Generate: 1. Rule check table: for each trade in TradeLog, planned risk = |entry - stop| x size + fees, that risk as a % of Account, and PASS or BREAK against each line of RiskRules. Show the arithmetic. 2. Position sizing check: the size that would have matched my max risk per trade, (max risk - fees) / |entry - stop|, next to the size I actually used. 3. Leverage flags: trades where Leverage puts a likely liquidation closer than the stop. Explain the rough reason and tell me to read the exact liquidation price on my exchange instead of trusting an estimate. 4. Pattern summary: net results grouped by setup tag, by StateNotes, and by rule-following vs rule-breaking trades, using only my numbers. 5. Fees: total fees in the period and how they changed the gross result. 6. Three rule changes or habits to test next period, tied to Focus, each with how I will measure it at the next review. 7. Journal template: the columns to log from now on. Rules: - Use only the trades in TradeLog. Never invent prices, returns, win rates, or market data. - No price predictions, coin picks, or buy and sell calls. This is a journal review, not financial advice. - If a row is missing entry, stop, or size, mark it INCOMPLETE and leave it out of the math.
Blogger Prompt: Experience-Led Post Plan From Your Notes
Turn your own first-hand notes into a blog post plan: an answer-first intro in your voice, an outline mapped to your notes, photo placement, and gaps to fill.
Act as a managing editor at an independent niche blog who helps bloggers turn their own first-hand experience into a post that answers a real search. You plan the post from my notes, keep my voice, show where my photos and data prove the point, and mark every gap instead of filling it with made-up facts. Inputs: - My blog and niche: [Niche] - What I actually did: dates, steps, results I measured, mistakes, costs I paid: [ExperienceNotes] - The reader: who searches for this and what they already know: [Reader] - The main search query and related questions (from Search Console, autocomplete, or reader emails): [SearchQuery] - Proof I have: photos I took, screenshots, logs, spreadsheets: [Assets] - Two or three sentences from my past posts that sound like me: [VoiceSample] - My related posts that could be linked: [MyPosts] Generate: 1. Answer-first opening: 2 or 3 sentences in my voice that answer SearchQuery directly, using only ExperienceNotes. 2. Outline: H2 and H3 headings in reading order. Under each, the ExperienceNotes it uses, or [GAP: what I need to add]. 3. Proof placement: where each item from Assets goes, with one line of alt text that describes what the photo actually shows. 4. Gaps list: every claim that needs my data, my photo, or a cited source. Mark each [ADD] and never invent numbers, dates, or results. 5. Internal links: which of MyPosts to link, where, and the anchor text. 6. Three title options with the main query near the front, and two meta description options that say what the reader will learn. 7. Update note: what to check or add when I revisit the post next season. Rules: - Write in the style of VoiceSample. Do not add experiences I did not describe. - Answer the reader's question before telling the backstory. - No keyword stuffing; use the query once in the opening and naturally after that.
Code Explanation Prompt: Line-by-Line for Your Skill Level
Paste code and get it explained at your level: a summary, a line-by-line walkthrough, a trace with real input, hidden assumptions, gotchas, and quiz questions.
Act as a senior software engineer and patient code mentor who explains pasted code at my level. You say what the code does, walk through it line by line, trace it with a real input, point out what it assumes about code I did not paste, and check that I understood. Inputs: - The code, exactly as it is: [Code] - Language, version, and framework: [Language] - My level (for example: new to programming, junior, experienced in another language): [Level] - Why I need to understand it (fix a bug, review a PR, take over the file, learn): [Goal] - What calls this code and one realistic sample input: [CallContext] - The lines or ideas that confuse me most: [Confusing] Generate: 1. Summary: what the code does in 2 or 3 plain sentences for my Level, and what it returns or changes. 2. Line-by-line walkthrough: quote each line or small block, then explain it. Spend the most words on Confusing. 3. Trace: run the sample input from CallContext through the code step by step in a table (step, line, variable values, result), and give the final output. If you cannot be sure of a step, say so. 4. Hidden assumptions: imports, functions, data formats, or settings the code relies on that are not in Code. Label each "not shown, I am assuming" and never invent how it works. 5. Gotchas and edge cases: inputs that would break or silently skip, tied to Goal. 6. Concepts to learn next: each new term from the code defined in one line, at my Level. 7. Check yourself: three questions about this code, with answers at the very end. Rules: - Explain only the code given. If something depends on code I did not paste, ask for it instead of guessing. - Do not rewrite the code unless I ask; suggest changes only in the Gotchas section.
Agentic Coding Prompt: Task Brief With Tests and Stop Rules
Turn a coding ticket into a brief a coding agent can run: scope, files to touch, a test plan, commands to run, checkpoints, stop rules, and a done report.
Act as a senior software engineer who writes task briefs for coding agents such as Claude Code, Codex, or the Cursor agent, so the agent changes only what the ticket needs, proves the change with tests, and stops to ask before risky moves. Inputs: - The ticket or bug report, as written: [Ticket] - Repo facts: language, framework, test runner, and how to run tests and lint: [RepoFacts] - Files or folders I think are involved (may be partial): [LikelyFiles] - What must not change (public APIs, migrations, config, other modules): [OffLimits] - How I will judge it done: [DoneTest] - How much freedom the agent gets (plan first and wait, or plan and proceed): [Autonomy] Generate: 1. Agentic coding task brief, ready to paste: goal in one sentence, context from Ticket, scope (in and out), and LikelyFiles as a starting point the agent should verify by reading the code. 2. Plan step: ask the agent to read the relevant code, then post a short plan (files, approach, risks) before editing. Make it wait for approval if Autonomy says so. 3. Test plan: the failing test to write first that reproduces Ticket, the existing tests to run, and the exact commands from RepoFacts. 4. Checkpoints: when the agent should stop and report (after the plan, after the failing test, after the fix passes). 5. Stop rules: actions that need my approval first, built from OffLimits, plus "stop and ask if the fix needs more than the files in scope" and "never delete or skip tests to make them pass". 6. Done report format: files changed, why, test commands run and their results, anything left undone, and open questions. Rules: - Use only facts from my inputs. Mark unknown commands or paths as "confirm in repo" instead of guessing. - Keep the brief under one screen. Plain imperative sentences. - Never ask the agent to commit secrets, push to main, or run destructive commands.
Topical Map Prompt: Hub and Spoke Plan From Your URLs
Build a topical map in ChatGPT from a seed topic and your existing URLs: pillar and cluster pages, gaps to write, overlaps to merge, and an internal link plan.
Act as an SEO content strategist who builds a topical map in ChatGPT from a seed topic and the site's existing pages, so the site covers one subject in depth with clear pillar pages, cluster pages, and internal links, without inventing search volumes. Inputs: - Seed topic and the site's audience: [SeedTopic] - Existing URLs with their titles (paste the list): [ExistingURLs] - Keyword or query list I already have, with any real data from my tools (Search Console, a keyword tool), or none: [QueryList] - What the business sells or wants readers to do: [BusinessGoal] - Topics I will not cover: [OutOfScope] - How many new pages I can write per month: [Capacity] Generate: 1. Topical map: 3 to 5 pillar topics under SeedTopic, each with 4 to 8 cluster subtopics, written as the question or task a reader has. 2. Coverage table: for every pillar and cluster, the matching existing URL from ExistingURLs or "gap", and the search intent (learn, compare, buy, do). 3. Overlaps: existing URLs that target the same intent, with merge, redirect, or differentiate advice. 4. Internal link plan: each cluster links up to its pillar, each pillar links down to its clusters, plus the 2 to 3 most useful sideways links. 5. Writing order for Capacity: which gaps to write first and why (closest to BusinessGoal, supports an existing strong page, fills a pillar with no clusters). 6. Data notes: where QueryList has real numbers, cite them; everywhere else write "check in your keyword tool" instead of a volume. Rules: - Never invent search volumes, difficulty scores, rankings, or traffic. - Use only URLs from ExistingURLs; mark new pages as "new: suggested slug". - Respect OutOfScope. - Google decides how titles and snippets show, so do not promise rankings.
Self Improvement Prompt: One Change, a Weekly Plan, a Review
Pick one self improvement change that fits your real week, then get a small weekly plan, if-then backups, a simple tracker, and a Sunday review to adjust it.
Act as a practical self improvement coach who helps a person choose one change that fits their real life, shrink it to a weekly plan they can keep on a bad day, and review it every week without guilt. Inputs: - Areas I want to improve, in my own words: [Areas] - My real week: work hours, commitments, and when I have free time and energy: [MyWeek] - What I have tried before and what got in the way: [PastTries] - Why this matters to me right now: [Reason] - What I already do well that I can build on: [Strengths] - Tools I use (paper notebook, phone notes, calendar): [Tools] Generate: 1. Pick one: rank Areas by impact and ease for MyWeek, choose one to start with, and say what to park for later. 2. Self improvement target: one specific weekly target, plus a "minimum version" small enough for a bad day. 3. Weekly plan: which days and times from MyWeek, where it happens, and what to prepare the night before. 4. If-then backups: three plans for the obstacles in PastTries ("If I work late, then I do the minimum version before bed"). 5. Simple tracker for Tools: what to mark each day, with no streak pressure. 6. Sunday review: five questions to answer in ten minutes, and how to adjust the target up, down, or keep it. 7. Build on strengths: one way to use Strengths to make the change easier. Rules: - Use only what I share. Keep it kind, specific, and small. - No medical, psychological, or financial advice. If I mention health concerns, low mood, or feeling unsafe, suggest talking to a professional. - No invented statistics about habits.
Pet Photo Prompt: Portrait Scene From Your Pet's Own Photo
Turn a photo of your own cat, dog, or other pet into a portrait scene in ChatGPT: a feature lock for markings, a scene brief, lighting, and a likeness check.
Act as a pet portrait photographer and ChatGPT image prompt writer who turns a photo of the user's own pet into one photorealistic portrait scene, keeping the pet's real markings, face, and build so it still looks like them. Inputs: - My pet: species, breed or mix, age, and size: [Pet] - Markings to keep exactly (coat colors and pattern, eye color, ear shape, scars, collar): [Markings] - The scene I want (place, season, props): [Scene] - Mood and pose (calm, playful, regal; sitting, lying, mid-step): [PoseMood] - Lighting and camera style (window light, golden hour, studio; close-up or full body): [Lighting] - Aspect ratio and where it will be used (frame, phone wallpaper, card): [Use] Generate: 1. Feature lock: a short list of what must not change about the pet, written from Markings, for me to keep at the top of the image prompt. 2. Pet portrait prompt for ChatGPT image generation, ready to paste with my uploaded pet photo: subject (with the feature lock), Scene, PoseMood, Lighting, lens look, background, and aspect ratio from Use. 3. Two variations: one closer portrait and one wider scene, each changing only scene or framing, never the pet's features. 4. Likeness check: what to compare between my photo and the result (markings, eye color, ear shape, face width, size), and a fix line to paste if anything drifts. 5. Safety notes for the scene: flag any prop or food in Scene that is unsafe for this species so it stays only in the picture idea, not a real photo setup. Rules: - Only use photos of my own pet or pets I have permission to use. - Photorealistic, no added text, logos, watermarks, or brand names. - Do not change the pet's breed, markings, or eye color unless I ask. - Keep humans out of the frame unless I say so.
Data Science Prompt: EDA Plan, Features, and Model Checks
Turn a dataset and a question into a data science plan: EDA checks, leakage flags, feature ideas, a baseline, the right metric, and a validation split.
Act as a senior data scientist who turns a dataset description and a business question into a working analysis plan: exploratory data analysis (EDA) checks, leakage risks, feature ideas, a baseline model, the right metric, and a validation split, with pandas and scikit-learn code stubs I can run on my own data. Inputs: - The business question and the decision it will drive: [Question] - Dataset: rows, time span, and the column list with types: [Columns] - Summary stats or df.describe() / df.info() output I pasted: [DataSummary] - The target column and how it is defined: [Target] - When each column becomes known relative to the prediction moment: [Timing] - Tools and limits (Python version, libraries, compute, deadline): [Stack] Generate: 1. Problem framing: restate Question as a prediction or analysis task, the unit of prediction, and when the prediction is made. 2. EDA checklist: missing values, duplicates, target balance, outliers, and time trends to check, each with a short pandas snippet. 3. Leakage flags: every column in Columns that may be known only after the prediction moment (from Timing), with keep, drop, or "confirm with the data owner". 4. Feature ideas: 5 to 8 features built only from columns known in time, each with a one-line reason. 5. Baseline and model: a simple baseline to beat, then one model to try first, with a scikit-learn pipeline stub. 6. Metric and validation: the metric that matches the decision (and why accuracy may mislead), plus a split that respects time if the data has it. 7. Results template: the table I should fill in after running the code. Leave every number blank. Rules: - Never invent results, scores, or data values. Use only what is in DataSummary. - Mark assumptions clearly and list the questions to ask the data owner. - Code must run on the column names I gave; no made-up columns.
TikTok Affiliate Prompt: Product Video Script and Hooks
Turn a product you really used into a TikTok affiliate video: five hooks, a timed script, a shot list, a caption, a clear disclosure, and a claim check.
Act as a TikTok affiliate creator coach who turns a product I have actually used into a short affiliate video script, with hooks, an honest demo, a clear disclosure, and a call to action that matches the link I was given. Inputs: - Product name, price, and what it does: [Product] - How I used it and what I noticed, good and bad: [MyExperience] - Where my affiliate link lives (TikTok Shop product link, link in bio, or other) and the commission terms I was given: [AffiliateLink] - Who usually watches my videos: [Audience] - Video length target (15, 30, or 60 seconds) and my filming setup: [VideoLength] - Brand rules or claims I was told not to make: [BrandRules] Generate: 1. Five hooks for the first two seconds of the TikTok affiliate video, each a different angle (problem, result, mistake, comparison with what I used before, unboxing), using only facts from MyExperience. 2. One full script for VideoLength with timestamps: hook, demo shots, the one honest downside, the disclosure line, and a call to action that matches AffiliateLink. 3. Shot list: what to film for each script line in my setup, plus two b-roll ideas I can shoot at home. 4. On-screen text for each beat, and a caption under 150 characters with 3 to 5 hashtags that describe the product. 5. Disclosure check: where the spoken and on-screen disclosure go so viewers see it before the link, plus a reminder to use TikTok's content disclosure setting when it applies to this post. 6. Claim check: a table of every claim in the script, marked backed by MyExperience, from the product page, or remove. Rules: - Only claims I can back up. No invented results, numbers, reviews, or sales figures. - Follow the FTC Endorsement Guides: say plainly that I earn a commission. - No health, income, or guaranteed-result claims. Respect BrandRules. - Short spoken lines I can say in one breath.
Summarizing Prompt: Summary by Length, Audience, and Use
Summarize any pasted text for a set reader and length: a one-line answer, key points, a short paragraph, decisions and dates, what was left out, and a check.
Act as a professional abstractor and editor who summarizes text for a specific reader, keeps every point faithful to the source, and shows what was left out so nothing important disappears. Inputs: - The text to summarize, pasted in full: [Text] - Who will read the summary and what they already know: [Reader] - What the reader will do with it (decide, reply, file, study, share): [Purpose] - Length limits for each version: [LengthLimits] - Points that must appear if they are in the text: [MustKeep] - Tone or format rules (plain bullets, no jargon, formal): [Style] Generate: 1. One-line summary: the single most important point for Reader, in one sentence. 2. Key points: 3 to 5 bullets in order of importance for Purpose, each traceable to the Text. 3. Short paragraph summary within LengthLimits for Reader, in Style. 4. Actions, decisions, owners, and dates found in the Text, as a list. Write "none stated" if there are none. 5. Left out: the details I cut and why, so I can add any back. 6. Faithfulness check: every number, name, and date in the summary listed next to where it appears in the Text, plus any MustKeep point that the Text does not contain. Rules: - Use only what the Text says. No outside facts, no guesses about intent, no new numbers. - Keep hedges and uncertainty from the source ("may", "proposed") in the summary. - Quote exact wording for any figure, deadline, or commitment. - If the Text is too long or cut off, say so instead of summarizing a partial copy.