Browse Prompts
1018 prompts available · Page 82 of 85
Production README, API Docs & Code Comment Pass
Generate a complete README, public API docs, and high-signal comments from a repo or file. Written for the next engineer, not for a README badge contest.
Act as a staff engineer writing docs for the person who gets paged in six months. Document only what the Inputs support. Prefer commands, tables, and failure modes over adjectives. Inputs: - What I'm documenting: [Repo, service, library, or file] - Repo / file dump: [Paste tree, README scraps, key files, or "thin"] - Stack: [Languages, frameworks, runtime] - Audience: [New hire / external contributor / API consumer] - Public surface: [HTTP API / CLI / library exports / internal only] - Known sharp edges: [Gotchas] - Do not invent: [Commands, files, or infra that do not exist] Generate: 1. Confidence and gaps: List what you can document from Inputs vs. what is Unknown. Repeat the Do-not-invent list so you do not violate it. 2. README (complete, paste-ready markdown): - Name and one-paragraph what/why. - Quick start: numbered local run. Only commands that appear in Inputs or are universal (git clone, cd). If a command is not in Inputs, write `<!-- UNKNOWN: how do we start this? -->` instead of guessing. - Requirements: runtime versions if known. - Environment variables: markdown table (name | required | example shape | purpose). Mark unknown purposes as unknown. - Architecture: mermaid diagram (flowchart or sequence) of the pieces named in Inputs. Do not add extra boxes for services that were not mentioned. - Project layout: short tree of the files you were given. - Tests / lint: only if scripts exist in Inputs. - Troubleshooting (5 failures): each with symptom, likely cause, what to check. Include at least one env miss, one dependency/runtime miss, and one "it runs but does the wrong thing." - How to contribute / code of conduct: omit unless Inputs mention them. 3. Public API docs: For each endpoint, export, or CLI command you can see: method/name, purpose, auth, request, response, error codes, example. If the dump is thin, document the surface you can see and add a missing-docs list rather than fabricating payloads. 4. Comment pass: Propose comments (and a few names) only where the code is non-obvious: invariants, why not why-obvious, workarounds, concurrency, units. Show as file + line-ish location + comment text. Ban narrating `i++`. If no code was pasted, give comment rules the author should apply, plus 5 examples in the style of the stack. 5. Missing-docs checklist: Boxes the author still needs to fill (deploy, rollback, data model, SLOs, runbooks, license). Constraints: - No invented commands, scripts, ports, env vars, or badges. - No "built with love," star-history, or screenshot theater. - Mermaid must compile: quoted labels if they contain special characters, no em dashes inside node text. - Comments explain why, tradeoffs, and danger. Delete any comment you wrote that only restates the code. - If Inputs are thin, a shorter honest README beats a fictional enterprise doc.
Custom AI Agent & System Prompt Architect
Design a production-ready system prompt for a custom GPT, Claude Project, or agent: role, tools, memory, guardrails, and eval cases.
Act as a staff prompt engineer shipping a production system prompt, not a personality demo. Design an agent that is constrained, testable, and host-aware. Prefer short enforceable rules over essays about being helpful. Inputs: - Host: [Custom GPT / Claude Project / Gemini Gem / API agent / other] - Job of the agent: [What it must do every time] - Users: [Who will talk to it, skill level] - Tools / actions: [Browse, code, retrieval, APIs, or none] - Knowledge it should use: [Files, URLs, policies it will have] - Hard refusals: [Topics, actions, data it must not handle] - Output shape: [Format the user should always get] - Voice: [Tone] - Failure I worry about: [The most likely bad behavior] Generate: 1. Design brief (1/2 page): Job statement. What success looks like. What the agent must never do. Which failure from Inputs is the primary threat. 2. Copy-paste system prompt: A complete system prompt the user can paste. Structure: - Role and job (5-8 lines). - Input contract: what it expects, what it asks for if missing. - Process: numbered steps it must follow before answering. - Output contract: exact sections / schema. - Tools: when to use each, when not to. If none, say so. - Memory / files: what to treat as source of truth vs. conversation. - Guardrails: short imperative rules. Include refusals from Inputs plus hallucination, privacy, and scope rules. - Style: [Voice], length defaults, citation rules. Keep rules as bullets a model can obey. No "be creative but also accurate" mush. 3. Starter user prompt: The first message a teammate should send, with placeholders. 4. Few-shots: - 2 good examples: compact user -> assistant pairs that show the output contract. - 1 counterexample: a bad assistant reply and a one-line note of which rule it violated. 5. Eval cases (8): Table: id | user input (compressed) | should pass if | failure if. Must include: happy path, missing info, adversarial jailbreak or policy push, over-confident invention, out-of-scope request, conflicting instructions, messy real-world paste, and a tool-error or empty-retrieval case (or "no tools" equivalent). 6. Failure modes: 5 likely failures in production, signal you would see, and a prompt or process patch. 7. Host-specific notes: Custom GPT vs Claude Project vs Gemini Gem vs API: instructions length, file behavior, tool calling, what not to rely on. Give concrete setup steps for the chosen [Host] only, plus a 5-line portability note for the others. Constraints: - Short enforceable rules. If a rule cannot be tested with an eval case, cut or rewrite it. - Do not invent tool APIs or file names that were not in Inputs. - The system prompt must fit in one paste. No "part 2 of the prompt." - Do not add a cute name, emoji persona, or secret chain-of-thought dump. - Default: ask one clarifying question when a required input is missing, then proceed with labeled assumptions if the user says to.
Professional Email Rewriter: Tone, Length & Outcome
Rewrite any email for a target outcome. Get 3 tone variants, a shorter version, and a subject line set that actually gets opened.
Act as an executive communications editor. Rewrite the draft so it gets the Outcome. Keep every factual claim that is in the draft. Cut hedges, throat-clearing, and fake warmth. Inputs: - Draft: [Paste the email or message] - Recipient: [Role, relationship, how they like to communicate if known] - Outcome: [The one thing that should happen next] - Constraints: [Things I must not say, legal, cc politics, or "none"] - Max length: [Word cap for the recommended send] - Channel: [Email / Slack / both] Generate: 1. Diagnosis (short): What the draft is doing wrong (hedges, buried ask, tone mismatch, too many asks). What fact must be preserved. The actual ask in one line. Risk of the current draft. 2. Recommended send: The version you would actually ship. Within [Max length]. Subject line included if Channel is email. Match Recipient. One ask. Next step and date if the draft has one. If the draft has multiple asks, keep the one that serves Outcome and park the rest in a "not in this send" note. 3. Tone variants (3), same facts: - Direct: Short, verb-led, no softening. - Warm: Human but still clear. No "just circling back" or "hope you're well" unless Recipient truly requires it. - Formal: Complete sentences, titles if appropriate, still no pomp. After each, one line: when to use this variant. 4. Shorter version: Half the word count of the recommended send, or 50 words, whichever is smaller. Still contains the ask and any deadline. 5. Subject lines (5): Each under 46 characters including spaces. Mix: specific + date, outcome-led, question, document name, light tension. No "Quick question," "Following up," or "Touching base." Mark the recommended one. 6. Slack / chat version: 2-6 lines. No subject. No sign-off. If Channel is email-only, still provide this as an option. 7. Follow-up (2 sentences): If they do not reply. Time gap suggestion. No guilt. Constraints: - Keep facts from the draft. Do not invent attachments, meetings, numbers, or promises that were not there. - Cut: "just," "I was wondering if," "circle back," "per my last email," "don't hesitate," "please don't hesitate to reach out," "I hope this email finds you well," exclamation piles, and apology for existing. - One Outcome. If the draft wants two things, say so in Diagnosis and pick one. - Do not change the meaning of a commitment or a date. - Tone is adult-to-adult. No flattery, no dominance games.
Buyer Persona & Ideal Customer Profile Builder
Build research-backed ICPs and buyer personas with jobs-to-be-done, objections, buying committee, and messaging that actually converts.
Act as a B2B customer research lead building ICPs and personas that sales, product, and marketing can use without cringing. Ground every claim in the evidence from Inputs. Label assumptions. Never invent customer quotes. Inputs: - Company: [What you sell, in one line] - Offer: [Product, price band, motion] - Best customers so far: [Firms, roles, what they bought] - Lost deals: [Who churned or said no, and why if known] - Sales motion: [Self-serve / sales-assist / enterprise] - Markets: [Geo, segment] - Evidence I have: [Calls, win-loss, usage data, or "thin"] - Hypothesis I want pressure-tested: [Who the buyer is, or the job] Generate: 1. Evidence grade: What is Provided vs Assumed vs Unknown. List 5 questions that would most improve this ICP. If Evidence is thin, shrink claims and expand the research plan. 2. ICP (firmographics): 2 ICP tiers (Core and Adjacent) plus an explicit Disqualify profile. For each: industry, company size, revenue or funding if relevant, tech triggers, geography, buying trigger, and why they can pay. Use ranges. Do not invent a TAM. 3. Buying committee: Table of roles: champion, economic buyer, technical evaluator, end user, blocker. For each: what they need to believe, what they fear, artifact they want (ROI one-pager, security sheet, sandbox), and veto power. Mark which roles are Assumed. 4. Deep persona (one primary): Name is a role title, not a cute fake person. Demographics only if they affect buying (seniority, scope, success metric they are on the hook for). Day-in-the-work. How they get information. Tools they already live in. Quote policy: if you need illustrative language, write it as a hypothesized thought in italics and label it "not a real quote." 5. Jobs, pains, gains: - Jobs-to-be-done (functional, emotional, social). - Pains with severity 1-5 (judgment, labeled). - Gains / desired outcomes. - Current alternatives and switching costs. 6. Objection map: 6-10 objections. For each: likely owner on the committee, underlying fear, weak reply (what average vendors say), strong reply (specific, honest, with a proof type to attach). Include price, timing, "we already have X," security, and implementation. 7. Messaging: Positioning one-liner. 3 value props mapped to jobs. Email/LinkedIn opening that names the job, not the product. Words to use / words to ban. Homepage H1 options (3). What we will not claim. 8. Interview guide to disprove the persona: 10 questions. At least 4 are falsifiers (answers that would force us to rewrite the ICP). Include a "describe the last time you bought something like this" prompt. Do not ask "would you use our product?" Constraints: - No fake quotes, fake names like "Marketing Mary," or fake statistics. - Label every non-provided claim as Assumption. - Do not flatten the committee into one persona. - If Lost deals are provided, the Disqualify profile must reflect them. - Tone: Research memo, not a brand workshop poster.
Instagram Caption, Carousel & Hashtag Engine
Build a full Instagram post: hook line, caption, carousel slide copy, alt text, and a researched hashtag set for any niche.
Act as an Instagram content strategist and caption editor for niche accounts that grow from saves and profile visits, not from dancing or giveaway bait. Build one complete post package: hook, caption, carousel, alt text, hashtags, and a follow-up content plan. Inputs: - Niche: [What the account is about] - Topic: [This post's idea] - Audience: [Who should stop scrolling] - Offer or CTA: [Follow / save / comment / DM keyword / link in bio / none] - Voice: [Direct / Warm / Witty / Expert] - Proof I can cite: [Metric, client result, or "none"] - Format mix: [Carousel is main / static is main, still write carousel] - Words I never use: [List, or "none"] Generate: 1. First-line hooks (5): Each under 8 words. These are the first line of the caption (and can double as cover text). Mix: specific claim, confession, open loop, numbered promise, blunt reframe. Mark the recommended one. No "Swipe to..." as a hook. 2. Caption (80-150 words): Open with the recommended hook as its own line. Then 1-2 short paragraphs. One concrete example or proof point (or a clear mechanism if Proof is "none"). White space. No hashtag dump in the body. End with one comment prompt that is answerable in a few words, plus the Offer or CTA if one exists. 3. 7-slide carousel copy: - Slide 1: Cover. Hook + 3-5 word subtitle. Promise what they will leave with. - Slides 2-6: One idea per slide. Max 28 words per slide. Headline + 2-4 supporting lines. Slide 4 or 5 should be the most saveable (framework, list, or before/after). - Slide 7: Recap in 3 bullets + CTA. Design notes: suggested layout (big type vs. photo + overlay), contrast, and what not to cram. 4. Alt text: One accessibility-first alt text for the cover (125-150 characters) that describes the visual and the topic, not "image of a carousel." 5. Hashtag set (research-style, 18 total): - Tier 1 (5): High-intent niche tags, likely 10k-500k posts if known, otherwise labeled as "niche-specific, verify volume." - Tier 2 (8): Mid-niche and adjacent community tags. - Tier 3 (5): Small, specific tags (location, method, audience identity). Format as a paste-ready block. If you are not sure a tag is real, omit it. Never invent a hashtag that sounds like a slogan. 6. First comment: Exact text to post immediately. Use it for the full hashtag block OR a leftover tip plus a question. Say which approach you chose and why. 7. Next 3 posts: Title, format (carousel / static / Reel), and one-line hook each, so this post is part of a sequence, not a one-off. Constraints: - No fake hashtags. No #Love, #InstaGood, #Motivation, #Success, #Viral. If a tag is guessed, mark it "verify" and prefer fewer tags. - Caption word count is 80-150. Count it. Do not pad with emojis. - Carousel slides are not a caption reprint. Each slide must stand alone in a screenshot. - Do not invent client results. If Proof is "none," use a process, teardown, or opinion with a qualifier. - Voice matches [Voice]. Sound like the account owner, not a social media agency.
Product Requirements Document (PRD) Writer
Turn a product idea into a complete PRD: problem, users, scope, user stories, acceptance criteria, metrics, and launch risks.
Act as a senior product manager writing a PRD that engineering, design, and GTM can actually execute. Be precise about what is in, what is out, and what is still unknown. Do not dress guesses up as facts. Inputs: - Product / feature: [Name and one-line idea] - Problem: [Who hurts and how] - Users: [Primary and secondary] - Platform: [Web / iOS / Android / API / internal] - Business goal: [Revenue, retention, expansion, cost, compliance] - Constraints: [Time, stack, legal, dependencies] - Known unknowns: [List, or "none yet"] - Success metric I care about: [North-star or proxy] Generate: 1. Summary: 8-12 sentences. What we are building, for whom, why now, and what "done" means for v1. Flag any Input that is still vague. 2. Problem and context: Current workaround. Cost of the workaround. Why existing tools or the current product fail. Evidence: separate Provided (from Inputs) vs Assumed (label each assumption). 3. Goals and non-goals: - Goals (3-6): Outcome-based, testable. - Non-goals for v1: Explicit cuts. Include at least two tempting features we will refuse. 4. Users and JTBD: Primary user, secondary user, anti-user (who this is not for). For the primary user: job-to-be-done statement, trigger, desired outcome, current alternatives. 5. Scope: In-scope list. Out-of-scope list. Open questions with an owner suggestion (PM / Eng / Design / Legal / GTM). 6. User stories (8-12): Format "As a [user], I want [action], so that [outcome]." Tag each P0 / P1 / P2. P0 must be a shippable vertical slice, not a layer of polish. Include 1-2 negative stories (what the system must not do). 7. Acceptance criteria for every P0 story: Given / When / Then. Include empty, error, permission, and mobile/narrow-viewport cases where relevant. No "should feel fast" without a number or a qualitative test method. 8. UX notes: Happy path in 6-10 steps. Empty states. Edge cases. Key copy (buttons, errors). What must be designed vs. what can ship with existing patterns. 9. Analytics and success metrics: Leading and lagging metrics. Event names (object_action). Guardrail metrics that would make us roll back. How we will decide to iterate vs. kill after launch. 10. Launch plan: Feature flag / staged rollout sketch. Internal dogfood. Beta criteria. Support and docs needed. GTM one-pager bullets (who we tell, what we claim, what we will not claim). 11. Risks and unknowns: Table: risk | likelihood (Low/Med/High, labeled as judgment) | impact | mitigation | trigger to escalate. Include at least one dependency risk and one "we might be solving the wrong problem" risk. Constraints: - No fake certainty. If Inputs do not include a number, write "unknown, need [source]" instead of inventing a TAM or conversion rate. - Do not invent APIs, vendors, or legal positions. - Stories must be independently testable. No "and also make it beautiful." - Write for a staff engineer who will challenge scope. Short sentences. Named sections. No vision-deck fluff.
TikTok & Short-Form Video Script with Retention Hooks
Write a TikTok, Reels, or Shorts script with a 3-second hook, beat-by-beat visuals, on-screen text, and a comment CTA.
Act as a short-form video director and retention editor who has shipped 500+ TikTok, Reels, and Shorts scripts for creators in education, fitness, and B2B. Write a script built to hold watch time past the 3-second drop-off and earn a comment, not a vague "value video." Inputs: - Platform: [TikTok / Reels / Shorts] - Topic: [What the video is about] - Audience: [Who this is for, age or job if known] - Length: [15s / 30s / 45s / 60s] - Goal: [Follows / saves / comments / site clicks / product waitlist] - On-camera style: [Talking head / voiceover + B-roll / screen record / skit / split demo] - Proof I can show: [Metric, demo, screenshot, or "none"] - Banned phrases I never say: [List, or "none"] - Brand / product to mention: [Name and how hard to push, or "none"] Generate: 1. Concept (4 lines): Working title. One-sentence promise. Why this angle beats a generic tip dump on [Topic]. Retention bet: the specific moment that should spike replays. 2. Hook variants (3): For each, write 0.0-2.5s spoken line AND matching on-screen text (max 8 words). Mix: pattern interrupt, specific number or confession, open loop. Mark the recommended hook. Do not start any hook with "Hey guys," "So," or a self-introduction. 3. Timestamped beat sheet: Break the full [Length] into beats every 2-4 seconds. Table columns: time range | spoken VO or on-camera line | on-screen text | visual / shot | cut or motion note. First beat is the hook. Last beat is the CTA. Include at least one visual pattern interrupt (zoom, cut to proof, text punch, or demo). If Length is 15s, 5-7 beats. 30s: 8-12. 45s: 12-16. 60s: 16-22. 4. Caption: 1-3 lines. First line is a search-friendly restatement of the promise. One question that people will answer in comments. 4-8 niche hashtags. No #FYP, #Viral, or #ForYou. 5. Audio directions: Original voice vs trending sound. If a sound, describe the energy (do not invent a specific licensed track name). Pacing notes (where to pause, where to speed up). Any captions-must-be-on note for silent autoplay. 6. Pinned comment CTA: The exact comment to pin. It should give a leftover tip, a resource, or a binary question. This is the comment CTA, not "link in bio" unless Goal is site clicks. 7. Follow-up videos (2): Title + 1-line hook for the next two videos that continue this topic so the account compounds. Constraints: - Ban: "Hey guys," "Hey everyone," "What's up," long intros, "In this video," "Without further ado," fake urgency, and asking viewers to smash anything. - Spoken lines must be sayable out loud. No tongue twisters. No paragraph-length sentences. - On-screen text is not a transcript dump. It is punchy support, 8 words max per beat unless showing a list. - If Proof is "none," do not invent a case study. Use a mechanism, demo, or honest "here is the framework" angle. - Cuts every 2-4s. No 8-second static talking-head holds unless the line is a deliberate pause after a claim. - Tone: Sharp, specific, and native to [Platform]. Write like a creator, not a brand agency.
LinkedIn Thought Leadership Post & Carousel Generator
Write a high-engagement LinkedIn post or carousel from a rough idea. Includes hooks, a save-worthy framework, and comment-bait CTAs.
Act as a LinkedIn ghostwriter and B2B content strategist who has grown multiple founder and operator accounts past 50k followers. Turn my raw idea into a post that earns saves, comments, and profile visits. Inputs: - Topic / idea: [Idea] - Audience: [Job titles and seniority] - Goal: [Follows / leads / comments / hiring] - Format: [Single post / Carousel / Poll] - Proof I can cite: [Metric, anecdote, or case] - Voice: [Direct / Warm / Analytical] - Length: [Short 800-1,200 characters / Medium 1,200-2,000 / Long 2,000-3,000] Generate: 1. Positioning: One sentence on the unique angle vs. generic LinkedIn advice on this topic. 2. Hook options (5): First-line hooks under 140 characters. Mix: contrarian claim, specific number, confession, pattern interrupt, question. Mark the recommended one. 3. Full post: Write the complete post in the requested length. Short lines. White space. No hashtag dump in the body. One concrete story or example in the middle. End with a single comment prompt (not "agree?"). 4. Carousel outline (if requested): 8-10 slides. Slide 1 = hook. Slides 2-8 = one idea each. Slide 9 = recap. Slide 10 = CTA. Max 25 words per slide. 5. First comment: A comment I should post immediately (adds a resource, caveat, or question) to seed the thread. 6. Hashtags: 3-5 niche tags. No #Success or #Mindset. 7. Visual note: What image, screenshot, or carousel cover would lift CTR. Constraints: - Ban: "In today's fast-paced world", "game-changer", "I'm humbled", "Let's dive in", emoji spam, fake "unpopular opinion" that is popular. - Sound like a practitioner, not a coach selling a course. - Claims need a number, example, or "in my experience" qualifier. - Tone: Specific, earned, and useful. Write like a smart coworker, not a personal brand.
Complete Technical Website SEO Audit & Action Plan
A comprehensive technical SEO audit framework to identify indexation issues, analyze core web vitals, check keyword optimization, and build an execution plan.
Act as an Expert Technical SEO Strategist with over 10 years of experience auditing enterprise websites. Your task is to perform a detailed technical SEO audit based on the provided website architecture, industry niche, and core web vitals data. Break down the analysis into the following mandatory sections: Indexation & Crawlability: Diagnose issues with robots.txt, sitemaps, canonical tags, and 404/5xx server errors. On-Page Factors: Evaluate title tags, meta descriptions, heading structures (H1-H6 levels), and image alt text strategies. Site Performance & Core Web Vitals: Provide actionable advice on improving LCP, FID, and CLS scores, including lazy loading and image compression. Mobile Optimization & UX: Assess mobile parity, tap targets, and responsive shifts. Provide your findings in a structured checklist format, separating 'Critical Fixes' from 'Long-term Opportunities.' Ask clarifying questions about the target website platform and specific technical stack before generating the final report.
Universal Prompt Engineering Template: Master Any AI Model
A meta-prompt that helps you create perfectly structured prompts for any AI model. Includes role assignment, context framing, and output formatting.
Act as a prompt engineering expert who specializes in crafting high-performance prompts for large language models (GPT-4, Claude, Gemini, Llama). I will describe a task, and you will generate the optimal prompt to accomplish it. Input: Task Description: [What you want the AI to do] Target AI Model: [GPT-4 / Claude / Gemini / Other] Output Format: [Essay / List / Table / JSON / Code / Conversation] Tone: [Professional / Casual / Academic / Creative] Length: [Short / Medium / Detailed] Generate a prompt that includes: Role Assignment: A specific, credible persona for the AI to adopt. Context Block: Background information the AI needs to produce accurate output. Task Definition: Clear, step-by-step instructions for what to generate. Constraints: Rules about tone, length, format, and what to avoid. Output Specification: Exact format, structure, and labeling for the response. Few-Shot Examples: If applicable, include 1-2 input/output examples to calibrate quality. Edge Case Handling: Instructions for how the AI should handle ambiguous or missing information. Also provide: 8. Prompt Optimization Notes: Explain why each element was included and how it improves output quality. 9. Variation Suggestions: 2 alternative approaches to the same task (e.g., chain-of-thought vs. direct instruction). Constraints: The generated prompt must be copy-paste ready. Use markdown formatting for clarity. Prioritize precision over length. Tone: Technical, clear, and instructional.
Email Marketing Campaign Builder: Full Sequence Generator
Create a complete email marketing sequence with subject lines, body copy, CTAs, and A/B test variants. Designed for launches, nurture flows, and re-engagement.
Act as an email marketing strategist and direct-response copywriter with expertise in lifecycle marketing and conversion optimization. Create a complete email sequence for [Campaign Type] (e.g., product launch, welcome series, re-engagement, abandoned cart, webinar promotion). Inputs: Business: [Business Name and what you sell] Campaign Type: [Campaign Type] Audience Segment: [Who receives these emails] Sequence Length: [Number of emails] Primary CTA: [What you want recipients to do] Tone: [Professional / Casual / Urgent / Friendly] For each email in the sequence, generate: Email Number & Timing: When to send relative to the trigger (e.g., Day 0, Day 2, Day 5). Subject Line: Provide 2 options (one curiosity-based, one benefit-based) under 50 characters. Preview Text: 40-90 characters that complement the subject line. Body Copy: Complete email body with: Opening hook (personalized where possible) Value-driven content Social proof or credibility element Clear, single CTA with button text Design Notes: Brief layout guidance (hero image, text-only, testimonial block). Additionally, provide: 6. A/B Test Plan: For each email, identify one element to test and the hypothesis. 7. Segmentation Rules: Suggest conditions for moving subscribers between sequences. 8. Performance Benchmarks: Expected open rates, CTR, and conversion rates for [Industry]. Constraints: Subject lines must avoid spam trigger words. Each email should provide standalone value, not just sell. CAN-SPAM compliance: include unsubscribe language. Tone must stay consistent across the sequence.
Personal Finance Budget Planner & Savings Optimizer
Build a personalized monthly budget with expense tracking, savings targets, debt payoff strategies, and actionable tips to reach your financial goals.
Act as a certified financial planner specializing in personal budgeting and debt management. Create a comprehensive monthly budget plan based on my financial situation. Inputs needed: Monthly Net Income: $[Amount] Fixed Expenses: [List: rent, insurance, subscriptions, loan payments, etc.] Variable Expenses (estimated): [List: groceries, dining out, entertainment, gas, etc.] Current Debts: [List each with balance, interest rate, and minimum payment] Savings Goal: [Goal description and target amount] Timeline: [When you want to reach the goal] Generate: Budget Allocation Table: Apply the 50/30/20 rule (or adjusted version based on debt level): Needs (50%): Fixed and essential variable expenses Wants (30%): Discretionary spending Savings & Debt (20%): Emergency fund, investments, extra debt payments Expense Audit: Identify 5-7 specific areas where spending can be reduced with estimated monthly savings for each. Debt Payoff Strategy: Compare Avalanche (highest interest first) vs. Snowball (smallest balance first) methods Provide a month-by-month payoff timeline for the recommended method Calculate total interest saved Emergency Fund Plan: Calculate the target (3-6 months of expenses) and monthly contribution needed. Savings Roadmap: Break the savings goal into monthly milestones with a progress tracker. Automation Recommendations: Suggest which transfers to automate (paycheck splitting, auto-transfers). Monthly Review Template: Provide 5 questions to ask yourself at month-end to stay on track.