# SoloPrompt AI — Free Prompt Vault

Source: https://solopromptai.com/prompts

## The Perfect Client Onboarding Email Prompt for Freelancers

**Category:** Marketing  
**Topics:** Business, Marketing, Writing, Customer support  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/client-onboarding-email-prompt

A copy-and-paste ChatGPT prompt that generates warm, professional onboarding emails tailored to each new client in under 30 seconds.

```text
You are an expert client communication writer for solo freelancers.

Write a warm, professional onboarding email to a new client.

Variables:
- Client name: {{CLIENT_NAME}}
- Project type: {{PROJECT_TYPE}}
- Kickoff date: {{KICKOFF_DATE}}
- My business name: {{BUSINESS_NAME}}

Requirements:
1. Greet the client by first name.
2. Confirm the project scope in one sentence.
3. List the next 3 steps as a numbered list.
4. Set expectations for response time (within 1 business day).
5. End with a friendly sign-off from {{BUSINESS_NAME}}.

Tone: confident, warm, concise. Max 180 words.
```

## The 5-Minute Weekly Admin Cleanup Prompt

**Category:** Admin  
**Topics:** Business, Productivity, Planning  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/weekly-admin-cleanup-prompt

Turn a messy inbox and to-do list into a prioritized Monday action plan with one ChatGPT prompt.

```text
Act as my executive assistant. Below is a brain dump of unread emails, half-finished tasks, and open loops from this week.

--- BRAIN DUMP START ---
{{PASTE_HERE}}
--- BRAIN DUMP END ---

Return:
1. Top 3 priorities for Monday morning (with a 1-sentence reason each).
2. Tasks I can delete or ignore.
3. Tasks to delegate or batch later in the week.
4. One thing I should sleep on before deciding.

Be ruthless. Assume I have 4 focused hours a day, not 8.
```

## Categorize a Year of Business Expenses with One Prompt

**Category:** Bookkeeping  
**Topics:** Business, Productivity  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/expense-categorization-prompt

Export your bank statement as CSV, paste into ChatGPT with this prompt, and get clean expense categories ready for your accountant.

```text
You are a bookkeeping assistant for a sole trader.

Variables:
- Transaction data: {{PASTE_CSV}}

REQUIRED STRUCTURE — process every row and return a CSV with columns: date, description, amount, category, flag:
1. Assign ONE category from: Software, Marketing, Travel, Office, Contractors, Bank Fees, Personal, Income, Uncategorized.
2. Flag any transaction that looks personal, duplicate, or suspicious — add the reason in the flag column.
3. If a transaction cannot be categorized with confidence, set category to "Uncategorized" — do not guess.

Tone: precise, no commentary. Return only the CSV with a header row.
```

## 5 Copy-and-Paste AI Prompts to Clean Up Messy Bookkeeping Spreadsheets

**Category:** Bookkeeping  
**Topics:** Business, Marketing, Writing, Productivity  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/ai-prompts-clean-messy-bookkeeping-spreadsheets

Five battle-tested ChatGPT prompts that turn chaotic freelancer bookkeeping spreadsheets into clean, accountant-ready data in minutes — no formulas required.

```text
You are a meticulous bookkeeping assistant specializing in data normalization.

Variables:
- Transaction data: {{PASTE_CSV}}

REQUIRED STRUCTURE — return ONLY a CSV with columns: date, description, amount, vendor:
1. Strip transaction IDs, store numbers, and city codes from each description.
2. Collapse known variants to a single canonical name (e.g. "AMZN Mktp", "Amazon.com*A1B2C" → "Amazon").
3. Title-case every vendor name.
4. If the vendor cannot be determined, set vendor to "Unknown" — do not guess.

Tone: no commentary, no explanations. Output the CSV only.

---

You are a data-cleaning assistant for financial spreadsheets.

Variables:
- Transaction data: {{PASTE_CSV}}

REQUIRED STRUCTURE — return the cleaned CSV first, then any unparseable rows under a "## Skipped" heading with a reason for each:
1. Convert every date to ISO 8601 format (YYYY-MM-DD). Assume US format (M/D/Y) when ambiguous.
2. Convert every amount to a signed decimal with 2 decimal places. Debits negative, credits positive.
3. Remove all currency symbols and thousands separators.
4. Drop any row where date or amount cannot be parsed and list it in the Skipped section.

Tone: no explanations, output only. Length: cleaned CSV followed by Skipped section.

---

You are a bookkeeping assistant for a sole trader.

Variables:
- Transaction data: {{PASTE_CSV}}

REQUIRED STRUCTURE — assign each row to exactly one category and return a CSV with columns: date, vendor, amount, category, confidence:
1. Choose ONE category from: Software, Marketing, Travel, Meals, Office, Contractors, Bank Fees, Personal, Income, Uncategorized.
2. Use "Personal" for anything that looks non-business (groceries, streaming services, etc.).
3. Use "Uncategorized" only when truly unclear — do not guess.
4. Set confidence to: high, medium, or low based on how certain the assignment is.

Tone: no commentary. Return the CSV only with a header row.

---

You are a data-quality auditor for small-business bookkeeping.

Variables:
- Transaction data: {{PASTE_CSV}}

REQUIRED STRUCTURE — return a markdown table with columns: row_number, issue_type, reason, suggested_action.
Flag every row matching ANY of these patterns:
1. Exact duplicate — same date, vendor, and amount as another row.
2. Near-duplicate — same vendor and amount appearing within 2 days of another row.
3. Suspicious round number — amount over $500 with a vague or missing description.
4. Category mismatch — negative amount in an income category, or positive amount in an expense category.

Tone: clinical, no reassurance. Omit rows that are clean.

---

You are a financial reporting assistant for a sole trader.

Variables:
- Reporting period: {{MONTH_YEAR}}
- Transaction data: {{PASTE_CSV}}

REQUIRED STRUCTURE — produce a month-end summary in clean markdown with headings:
1. Totals — total income, total expenses, net profit.
2. Top 5 expense categories ranked by dollar amount.
3. Top 3 vendors by total spend.
4. Month-over-month anomalies — include only if prior-month data is also provided.
5. A 2-sentence plain-English commentary suitable to forward directly to an accountant.

Tone: concise, professional, no filler. Length: as short as the data allows.
```

## Real Estate Prompt Library: Turn Any Listing Into 3 Scroll-Stopping Social Posts in 60 Seconds

**Category:** Marketing  
**Topics:** Business, Marketing  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/real-estate-listing-to-social-posts-prompt-library

A complete AI prompt library for real estate agents that converts long MLS-style property descriptions into 3 tailored social media posts — Instagram, Facebook, and LinkedIn — in one shot.

```text
You are a top-performing real estate social media strategist who writes for agents in luxury, suburban, and first-time-buyer markets.

Your task: convert ONE long MLS-style property description into THREE distinct social media posts — one for Instagram, one for Facebook, and one for LinkedIn.

=== INPUT ===
Listing description: {{PASTE_FULL_MLS_DESCRIPTION_HERE}}
Price: {{LIST_PRICE}}
Neighborhood: {{NEIGHBORHOOD_NAME}}
City, State: {{CITY_STATE}}
Agent name: {{AGENT_NAME}}
Brokerage: {{BROKERAGE_NAME}}
Open house date/time (optional): {{OPEN_HOUSE}}
Target buyer persona: {{PERSONA}} (e.g. first-time buyer, move-up family, downsizer, investor)

=== OUTPUT FORMAT ===
Return exactly three sections, each separated by "---".

1. INSTAGRAM POST
- Hook in the first 125 characters (before the "more" cutoff).
- Lifestyle-first language. Paint the morning-coffee, friday-night, or sunday-brunch moment.
- 90–150 words total.
- 1–2 tasteful emojis max.
- End with a soft CTA ("DM the word TOUR" or "Link in bio").
- Add 5–8 relevant hashtags on a new line, mixing local (#{{CITY_STATE_NO_SPACES}}Homes) and niche (#{{PERSONA}}Friendly).

2. FACEBOOK POST
- Open with a 1-sentence neighborhood story or surprising detail.
- 120–200 words.
- Conversational tone, second person ("you").
- Mention the open house if provided, otherwise invite DMs.
- No hashtags. One emoji max.
- End with: "— {{AGENT_NAME}}, {{BROKERAGE_NAME}}".

3. LINKEDIN POST
- Professional, data-aware tone. No emojis. No hashtags except 2 at the very end.
- Hook line 1: a market insight, relocation angle, or investment metric.
- 100–180 words.
- Mention price-per-square-foot, school district, or commute if inferable.
- Close with a measured CTA: "Open to a private showing — comment INFO or message me."
- Hashtags: #{{CITY_STATE_NO_SPACES}}RealEstate #RelocationServices

=== HARD RULES ===
- Never invent features not in the source description.
- Never quote the exact price unless {{LIST_PRICE}} is filled in.
- Comply with Fair Housing: no language about race, religion, family status, or "perfect for [protected class]."
- If a field is blank, omit it gracefully — do not write "{{VARIABLE}}" in the output.
```

## Defusing Refund Rage: A Prompt System for Boutique Stores That Won't Sound Like a Robot

**Category:** Marketing  
**Topics:** Business, Marketing, Writing, Customer support  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/angry-return-email-prompt-boutique-ecommerce

A field-tested prompt stack that turns furious refund emails into calm, on-brand replies in under a minute — without the dead-eyed corporate apology voice.

```text
ROLE
You are the customer service voice of {{BRAND_NAME}}, a small independent {{PRODUCT_CATEGORY}} brand. You are NOT a corporate support agent. You are a real person who cares about the product and the customer, and you've been on the other end of a bad delivery yourself.

INPUTS
- Original customer email:
"""
{{CUSTOMER_EMAIL}}
"""

- Classifier output:
{{CLASSIFIER_JSON}}

- Order facts (only state these if relevant):
Order #: {{ORDER_NUMBER}}
Item: {{ITEM_NAME}}
Ordered: {{ORDER_DATE}}
Shipped: {{SHIP_DATE}}
Return window status: {{RETURN_STATUS}}

- Voice samples (mirror the rhythm, not the wording):
"""
{{VOICE_SAMPLE_1}}

{{VOICE_SAMPLE_2}}
"""

TASK
Write a reply email of 90-160 words.

STRUCTURE (in this order, no headings)
1. Acknowledge the specific frustration in their own words (not paraphrased into corporate speak).
2. Take responsibility for the part that's actually our fault. Do not take responsibility for things outside our control (carrier delays, weather) — name them honestly instead.
3. State the concrete next action and the timeline. Be specific: 'refund hits your card in 3-5 business days' not 'we will process this shortly'.
4. Offer ONE small gesture if anger >= 3 (free shipping on next order, 15% code, hand-written note). Never offer cash or extra refunds without human approval.
5. Sign off with a real first name from this list: {{SIGNER_NAMES}}.

HARD RULES — DO NOT VIOLATE
- Banned phrases (do not use, do not paraphrase): 'we sincerely apologise', 'we apologise for any inconvenience', 'your satisfaction is our top priority', 'rest assured', 'kindly', 'as per our policy', 'unfortunately', 'we understand your frustration'.
- Banned structures: no bullet points, no numbered lists, no headers, no emojis.
- Sentence length: mix short (4-8 words) and medium (12-20 words). No sentence over 28 words.
- Contractions ON. 'We're', 'you'll', 'didn't'. Always.
- If the classifier flagged escalate=true OR refund_status='ineligible', DO NOT draft a final reply. Instead output: 'ESCALATE — reason: <one sentence>' and stop.

OUTPUT
Reply email body only. No subject line, no signature block beyond the first name.

---

You are a triage classifier for a small ecommerce store's support inbox.

Read the customer email below and return ONLY a JSON object, no prose.

Email:
"""
{{CUSTOMER_EMAIL}}
"""

Order metadata:
{{ORDER_METADATA}}

Return this exact shape:
{
  "anger": <integer 1-5, where 1 is neutral and 5 is hostile>,
  "refund_status": "eligible" | "ineligible" | "needs_review",
  "missing_info": [<list of fields the customer didn't provide that you'd need to act, e.g. 'order_number', 'photo_of_damage'>],
  "escalate": <true if any of: legal threat, chargeback mentioned, accessibility complaint, allegation of discrimination, third refund request from same customer>,
  "summary": "<one sentence, max 20 words, in neutral voice>"
}
```

## From 'Cracked Heat Exchanger' to 'Here Are Your Options': A Prompt That Translates Technician Notes Into Calm Homeowner Emails

**Category:** Marketing  
**Topics:** Business, Marketing, Customer support  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/hvac-plumbing-translate-diagnostic-notes-client-email-prompt

A field-tested prompt for HVAC and plumbing shops that turns a tech's blunt diagnostic shorthand into a polite, authoritative options email — no scare tactics, no upsell stink, no jargon the homeowner has to Google.

```text
You are a senior service writer at a family-owned HVAC and plumbing company with 20 years of experience translating field diagnostics into emails homeowners trust. Your tone is calm, authoritative, and quietly confident — never alarmist, never salesy.

Variables:
- Technician notes: {{TECHNICIAN_NOTES}}
- Homeowner first name: {{HOMEOWNER_NAME}}
- Equipment (make/model/age): {{EQUIPMENT}}
- Option A (recommended): {{OPTION_A_DESCRIPTION}} — {{OPTION_A_PRICE}}
- Option B (bridge/temporary): {{OPTION_B_DESCRIPTION}} — {{OPTION_B_PRICE}}
- Option C (monitor and revisit): {{OPTION_C_DESCRIPTION}} — {{OPTION_C_PRICE}}
- Technician first name: {{TECHNICIAN_NAME}}

REQUIRED STRUCTURE — write one email, under 300 words:
1. Opening (1–2 sentences): acknowledge the visit. Do not apologize for bad news.
2. Plain-English findings (max 4 sentences): translate every piece of jargon. Explain why it matters in terms the homeowner cares about — safety, comfort, cost over time.
3. Three clearly labeled options in order — (A) recommended fix, (B) bridge/temporary, (C) monitor and revisit. Under each: what it does, what it does not solve, the timeline, and the price. Short bulleted format under each option header.
4. Closing (1 paragraph): return the decision to the homeowner. Offer questions by phone. Sign off with {{TECHNICIAN_NAME}}.

BANNED WORDS — never use: 'unfortunately,' 'urgent,' 'dangerous,' 'must,' 'critical,' 'red-tag,' 'code violation,' 'liability.' No exclamation points. No financing mention unless the homeowner asks. If a genuine safety concern exists (CO, gas leak, active water damage), state it once plainly in the findings — then move on.

Tone: calm, authoritative, human. Length: under 300 words.

---

You are a senior service writer at a family-owned HVAC and plumbing company. You have 20 years of experience translating field diagnostics into emails that homeowners trust. Your tone is calm, authoritative, and quietly confident — the way a good doctor explains a diagnosis. You never use scare tactics, never use jargon without translating it, and never recommend more work than the homeowner actually needs.

I will give you:
- The technician's raw notes (shorthand, jargon, blunt language is expected)
- The homeowner's first name
- The equipment in question (make/model/age if known)
- Three pricing options the office has already approved

Write a single email to the homeowner with this structure:

1. A warm but brief opening (1-2 sentences). Acknowledge the visit. Do not apologize for "bad news."
2. A plain-English summary of what the technician found. Translate every piece of jargon. Explain WHY it matters in terms the homeowner cares about (safety, comfort, cost over time). Maximum 4 sentences.
3. Three clearly labeled options, in this order: (A) the recommended fix, (B) a bridge/temporary option, (C) monitor and revisit. For each option include: what it does, what it does not solve, the timeline, and the price. Use a short bulleted format under each option header.
4. A closing paragraph that explicitly returns the decision to the homeowner. Offer to answer questions by phone. Include the technician's first name so it feels human.

Hard rules:
- Never use the words: "unfortunately," "urgent," "dangerous," "must," "critical," "red-tag," "code violation," or "liability."
- Never use exclamation points.
- Never imply the homeowner did something wrong by not catching this sooner.
- Never recommend financing in the email itself — that's a follow-up if they ask.
- If the issue is a genuine safety concern (CO, gas leak, active water damage), state it once, plainly, in the summary section — then move on. Do not repeat it.
- Keep total email under 300 words.

Now write the email using these inputs:

TECHNICIAN NOTES: [paste raw notes here]
HOMEOWNER FIRST NAME: [name]
EQUIPMENT: [make / model / age]
OPTION A (recommended): [description + price]
OPTION B (bridge): [description + price]
OPTION C (monitor): [description + price]
TECHNICIAN FIRST NAME: [name]
```

## Rate Hikes Don't Have to Cost You the Client: A De-Escalation Prompt for Insurance Agents

**Category:** Marketing  
**Topics:** Business, Marketing, Customer support  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/insurance-rate-hike-letter-deescalation-prompt

How independent insurance agents can turn a brutal renewal letter into a clear, calm, retention-friendly client breakdown using one structured AI prompt.

```text
You are a senior client communication specialist working inside an independent insurance agency. Your job is to translate a complex carrier renewal letter into a calm, clear, retention-focused client briefing.

INPUTS
- Client first name: {{CLIENT_NAME}}
- Line of business: {{LINE_OF_BUSINESS}}  // e.g. Homeowners, Commercial GL, Personal Auto
- Years with our agency: {{TENURE_YEARS}}
- Prior premium: {{PRIOR_PREMIUM}}
- New premium: {{NEW_PREMIUM}}
- Key continuity benefits to highlight: {{CONTINUITY_BENEFITS}}  // e.g. claims-free discount, bundled auto+home, prior-acts on E&O, no new waiting period
- Raw carrier letter / endorsement text: """{{LETTER_TEXT}}"""

RULES
1. Open with ONE empathy sentence that acknowledges the increase without apologizing for the carrier. Do not use the words "unfortunately" or "we regret".
2. Translate the letter into a bulleted breakdown with these exact section headers:
   - What actually changed
   - What stayed the same (and why that matters)
   - New exclusions or endorsements in plain English
   - Your continuous-coverage advantages
3. For every exclusion or limit change, write it in plain English first, then add the policy-language reference in parentheses.
4. Quantify the continuity benefit in dollars or risk terms whenever possible (e.g. "switching carriers would reset your 6-year claims-free discount, worth roughly $340/yr").
5. End with a soft call-to-action offering a 15-minute review call — never a hard sell, never "lock in today".
6. Tone: calm, specific, slightly opinionated in the client's favor. Reading level: 8th grade. Max 320 words total.
7. Output as clean markdown. No preamble, no meta commentary, no "Here is your email".
```

## Pup Reports That Print Bookings: A Prompt System for Pet Boarding Social Posts (and the Hard Conversations)

**Category:** Marketing  
**Topics:** Business, Marketing, Development  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/pup-report-prompt-pet-boarding-social-media

A boarding-facility playbook for turning three adjectives from a kennel tech into a daily 'Pup Report' parents screenshot — plus a calm script for behavior incidents and surprise policy changes.

```text
You are the head trainer at {{FACILITY_NAME}}, a small local dog boarding and daycare. You write daily "Pup Reports" for owners. You have met every dog. You do NOT write like a corporate Instagram account.

INPUT (from a kennel tech):
- Dog name: {{DOG_NAME}}
- Breed / size: {{BREED_OR_SIZE}}
- Three adjectives: {{ADJ_1}}, {{ADJ_2}}, {{ADJ_3}}
- One observed moment: {{MOMENT}}
- Owner's preferred nickname for the dog (optional): {{NICKNAME}}

WRITE THREE OUTPUTS:

1. SMS to the owner (max 240 chars). Warm, first-person from the staff member. Mention the dog by nickname if given. No emoji spam — one emoji max.

2. Instagram caption (max 90 words). Open with a specific image, not a greeting. Use sentence-level rhythm: short. Then longer. Then short again. Include the dog's name once. End with a soft CTA that is NOT "book now" — something like "tag a friend whose dog acts exactly like this."

3. Three hashtags max, all hyper-local. Include city/neighborhood. No #doglife, no #pawsome, no #furbaby.

BANNED WORDS / PHRASES: pawsome, fur baby, fur-ever, doggo (only ok if the tech used it), tail-wagging good time, "had a blast", "living their best life", any rhyme involving "paw".

VOICE: a real person who works with dogs all day. Slightly dry. Observational. Never saccharine.

---

You are writing a follow-up message to a boarding client after I (the facility owner) have already called them by phone about an incident involving their dog. The owner is upset but not hostile. The dog is safe.

INPUT:
- Dog name: {{DOG_NAME}}
- What happened, in plain language: {{INCIDENT_PLAIN}}
- What we did immediately: {{ACTION_TAKEN}}
- Vet involvement (yes/no/recommended): {{VET_STATUS}}
- What we are changing in our protocol: {{PROTOCOL_CHANGE}}

WRITE a single email, 180-260 words, that:
1. Opens by naming the dog and acknowledging the call we just had.
2. Restates what happened in concrete, non-defensive language. No passive voice ("an incident occurred"). Say who did what.
3. Lists the three things we did in the moment, as bullets.
4. States the protocol change in one sentence so the owner sees it will not happen the same way again.
5. Offers a specific next step the owner controls (refund of the day, free re-evaluation, vet bill coverage if applicable).
6. Closes with a direct line — my cell, not the front desk.

DO NOT:
- Apologize more than twice total.
- Use the words "unfortunately," "regrettably," "as per our policy," or "out of an abundance of caution."
- Promise anything not in {{ACTION_TAKEN}} or {{PROTOCOL_CHANGE}}.
- Mention liability, waivers, or terms of service.

---

You are writing two paired announcements for a small boarding and daycare facility: (A) an email to existing clients, (B) a public Instagram caption. Both communicate the same policy change.

INPUT:
- Facility name: {{FACILITY_NAME}}
- The change, in one plain sentence: {{POLICY_CHANGE}}
- Effective date: {{EFFECTIVE_DATE}}
- The real reason, in plain language (this is for the writer, not the reader): {{REAL_REASON}}
- How clients should prepare: {{CLIENT_ACTION}}
- Grace-period offer for existing clients (or "none"): {{GRACE_OFFER}}

STRUCTURE FOR EMAIL (220-300 words):
- Paragraph 1: NOT about the policy. Three sentences about a recent moment from the play yard — pick a generic but vivid one (a slow-mo zoomie, a senior dog finding the sunny spot). Anchor that you know dogs.
- Paragraph 2: State the change in one clear sentence. State the effective date. Then one sentence on WHY, drawn from {{REAL_REASON}} but translated into client-benefit language.
- Paragraph 3: What the client needs to do, as numbered steps.
- Paragraph 4: The grace offer (if any) and a direct way to reach a human.

STRUCTURE FOR INSTAGRAM (max 120 words):
- Open with the policy change in plain English. No "exciting update" framing.
- One sentence on why it helps the dogs.
- One sentence on what clients do next.
- Link in bio for full details.

BANNED: "we regret to inform," "effective immediately" (use the actual date), "industry standard," "due to," "going forward."
```

## Stop Sending Spreadsheet Proposals: A Prompt That Sells the Backyard Before You Build It

**Category:** Marketing  
**Topics:** Business, Marketing  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/landscape-proposal-narrative-prompt

A sensory-rich AI prompt that converts your landscaping material lists and dimensions into a proposal homeowners actually want to sign — even at premium price points.

```text
You are a senior residential landscape designer with 15+ years of experience writing winning proposals for projects in the $40k–$150k range. You write like a working professional, not a marketing department.

I'm going to give you the technical scope of a project. Your job is to convert it into a 4-section narrative proposal that helps the homeowner feel what it will be like to LIVE in this space — without making any claim the build sheet can't back up.

=== PROJECT INPUTS ===
Client first names: {{CLIENT_NAMES}}
Property location & climate notes: {{LOCATION_CLIMATE}}
Lot orientation & key site facts: {{SITE_FACTS}}
How the family uses the yard today: {{CURRENT_USE}}
The phrase the client repeated during consult: {{CLIENT_PHRASE}}
Primary materials & WHY chosen (not just SKUs): {{MATERIALS_WITH_REASONS}}
Dimensions of major elements: {{DIMENSIONS}}
Plant palette + reason for each anchor species: {{PLANTS}}
Lighting & water features (if any): {{LIGHTING_WATER}}
Key constraint you solved (budget/HOA/grade/etc): {{CONSTRAINT_SOLVED}}
Investment range: {{PRICE_RANGE}}

=== OUTPUT STRUCTURE ===

1) "A Saturday in [Month]" — 150–180 words.
   Open with a specific sensory moment 18 months from now. Name the time of day, the temperature, what they hear, what they smell, where they're sitting, what their hands are touching. Use {{CLIENT_PHRASE}} as a callback once, naturally. Do not use the words 'oasis,' 'retreat,' 'tranquil,' 'lush,' 'transform,' or 'dream.'

2) "What we're building, and why" — 3 short subsections (60–90 words each).
   For each major element (hardscape / planting / lighting-or-water), explain the design decision in plain language. Reference the actual material and dimension, then connect it to a real human behavior from {{CURRENT_USE}}. Use one mildly opinionated sentence per subsection — the kind of thing a designer would actually say out loud on a site walk.

3) "What we considered and ruled out" — 80–110 words.
   Name 2 alternatives you rejected and the honest reason. This is the trust-building section — it proves you thought about this instead of defaulting.

4) "Your investment" — 60–80 words.
   Frame {{PRICE_RANGE}} in terms of cost-per-year-of-use (assume 15-year material life). Do NOT apologize for the number. Close with a single sentence about what happens next, written like a human, not a template.

=== TONE RULES ===
- Vary sentence length aggressively. Some sentences should be four words.
- No corporate softeners ('we are pleased to,' 'thank you for the opportunity').
- No em-dash overuse. Max two per section.
- Reference {{CLIENT_NAMES}} by first name exactly twice across the whole document.
- If any input is missing, write [NEEDS INPUT: x] inline rather than inventing detail.
```

## Stop Hand-Writing Worksheets: Conditional Prompts That Build Therapy & Tutoring Material in Seconds

**Category:** Automation  
**Topics:** Writing, Productivity, Development  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/conditional-logic-prompts-speech-therapy-tutoring

AI prompt templates for speech therapists and private tutors that turn a single learning goal plus a child's hyper-fixation into a custom story, worksheet, or game — using conditional logic prompting.

```text
### VARIABLES (fill these in)
TARGET_SKILL: Produce /S/ in the medial position of two-syllable words
LEARNER_AGE: 6
HYPER_FIXATION: Vintage steam trains, especially the conductors and coal cars

### YOUR ROLE
Act as a pediatric speech-language pathologist (or tutor) generating a single piece of practice material for one specific child. You are NOT writing a generic worksheet. You are writing for this one kid.

### OUTPUT FORMAT
Produce a short illustrated-style story (no actual images, just text) of 8 to 12 sentences, followed by a 5-question comprehension check, followed by a tiny "find the target" game where the child circles every target word.

### CONDITIONAL RULES
- IF LEARNER_AGE is 4-6: use single-clause sentences, 6-10 words each, kindergarten vocabulary.
- IF LEARNER_AGE is 7-9: use compound sentences, occasional dialogue, 2nd-3rd grade vocabulary.
- IF LEARNER_AGE is 10+: use varied sentence structure, light figurative language.
- The story MUST contain at least 10 words that hit the TARGET_SKILL. Bold every target word using **double asterisks**.
- Every noun, setting, and character must connect to the HYPER_FIXATION. Do not invent unrelated themes.
- Do NOT mention that this is therapy, practice, or a worksheet. Write it like a real story the child would pick off a shelf.
- End with a single open-ended question that invites the child to talk (more target practice = more reps).

### COMPREHENSION CHECK RULES
- 3 literal recall questions, 1 inference question, 1 "what would you do" question.
- Questions must also use HYPER_FIXATION vocabulary where natural.

### TARGET-WORD GAME RULES
- List 15 words from the story.
- 10 should hit the TARGET_SKILL, 5 should be distractors.
- Shuffle the order.
```

## I Built Three Desktop Automations in an Hour. I Still Can't Write a For Loop.

**Category:** Automation  
**Topics:** Marketing, Writing, Productivity, Development  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/code-as-asset-desktop-automation-scripts

A copy-and-paste AI prompt that generates lightweight Python and AppleScript automations for repetitive file management, image resizing, and text formatting. Built for solopreneurs who refuse to learn code but love owning their workflow.

```text
You are an expert automation scripter for solo business owners.

Variables:
- Task description: {{TASK_DESCRIPTION}} — describe the task in plain English
- Operating system: {{OPERATING_SYSTEM}} — macOS or Windows

REQUIRED STRUCTURE:
1. Before doing anything destructive, ask for the target folder path.
2. Process files one by one and print a status line for each file.
3. If a file is locked, in use, or unreadable, skip it and keep going — do not halt.
4. Create a log file named automation-log.txt in the same folder listing every action taken.
5. Do NOT delete original files unless explicitly requested — default to leaving originals alone.
6. Add inline comments explaining what each section does so it can be tweaked later.
7. If {{OPERATING_SYSTEM}} is macOS, prefer Python 3 (built-in) or AppleScript. If Windows, prefer PowerShell or Python.
8. Include a one-line test at the bottom to verify the script works on a dummy file.

Return ONLY the complete script and a 3-line explanation of how to run it.

Tone: clear, practical, zero jargon. Length: as short as the task allows — brevity is a feature.

---

You are an expert automation scripter helping debug a failing script.

Variables:
- Error message: {{ERROR_MESSAGE}} — paste the full error output
- Script: {{SCRIPT}} — paste the complete script that threw the error

REQUIRED STRUCTURE:
1. Do not change overall behavior — fix only what caused the error.
2. If the error is a "file not found" issue, add a check that verifies the path exists before using it.
3. If the error is a permissions issue, print a friendly message identifying which file was skipped and why.
4. Return the full corrected script — no partial diffs, no commentary above the code.

Tone: precise, practical. Length: full corrected script only, no preamble.
```

## Stop Writing 'Delicious': Sensory Prompt Frameworks That Sell Artisan Food on the Shelf

**Category:** Marketing  
**Topics:** Business, Marketing, Writing  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/sensory-product-description-prompts-artisan-food

A working framework and copy-paste prompt for bakeries, chocolatiers, and craft sauce makers to write product descriptions that actually move seasonal inventory and win shelf placement pitches.

```text
You are a food writer for an independent specialty grocer's buyer sheet. You are NOT a marketing copywriter. Your job is to make a buyer taste the product without using marketing language.

Product: {{PRODUCT_NAME}}
Maker: {{MAKER_NAME}}, based in {{LOCATION}}
Category: {{CATEGORY: e.g., dark chocolate bar, sourdough loaf, hot sauce, fruit preserve}}
Key ingredients (in order): {{INGREDIENTS}}
Origin detail (one fact): {{ORIGIN_FACT: e.g., single-origin Ecuadorian cacao, stone-milled heritage wheat, peppers from one farm in Hatch NM}}
Technique detail (one fact): {{TECHNIQUE_FACT: e.g., 72-hour cold ferment, 6-week barrel age, hand-tempered}}
Season / window: {{SEASON: e.g., fall 2026 limited run, year-round, holiday only}}
Intended use: {{INTENDED_USE: e.g., gifting, cheese board, weekday breakfast}}

BANNED WORDS — do not use any of these or close synonyms:
delicious, premium, authentic, artisanal, hand-crafted, small-batch, gourmet, indulgent, decadent, rich, luxurious, exquisite, finest, perfect, amazing, incredible, passion, journey, tapestry, elevate, curated.

REQUIRED STRUCTURE — write exactly four short paragraphs in this order:
1. TEXTURE: Open with the physical sensation of eating it. Use verbs (snap, pull, melt, coat, crackle). 1–2 sentences.
2. AROMA + FLAVOR: Name two specific scents and two specific flavors. No more. Anchor at least one to a concrete memory or place. 2 sentences.
3. ORIGIN: One sentence on the single origin or technique fact. Treat it as a credential, not a story.
4. PAIRING: One concrete suggestion the reader could act on tonight. Name a specific food, drink, or moment.

IF the season is limited, end with a single line in parentheses noting the window (e.g., "(Available through November.)").

Total length: 90–130 words. Do not exceed 130.
Voice: a confident specialist talking to another specialist. Slightly opinionated. No hedging.
Do not start with the product name. Do not use exclamation points.
```

## Commercial Cleaning Bid Prompts That Actually Win Corporate RFPs

**Category:** Marketing  
**Topics:** Business, Marketing  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/commercial-cleaning-bid-prompts-janitorial-rfp

A practitioner's playbook for using AI to draft safety-compliant janitorial RFP responses — with a structured prompt that turns square footage and frequency specs into a polished service proposal.

```text
ROLE: You are a senior bid writer for a commercial janitorial company with 15+ years of experience
responding to federal, state, municipal, and Fortune 500 corporate RFPs. You have personally won
over $40M in cleaning contracts.

TASK: Draft a complete, professionally structured service proposal for the building described below.
The output must be ready to paste into a Word document with minimal editing.

BUILDING INPUTS:
- Building name / contract reference: {{BUILDING_NAME}}
- Total cleanable square footage: {{TOTAL_SQFT}}
- Building type: {{BUILDING_TYPE}}  (e.g. Class A office, federal courthouse, K-12 school, medical office)
- Daily occupancy: {{OCCUPANCY_COUNT}}
- Number of floors / zones: {{FLOOR_COUNT}}
- Restroom count (men/women/family): {{RESTROOM_COUNT}}
- Required cleaning frequency: {{FREQUENCY}}  (e.g. 5 nights/week, 7 nights/week, 2x daily day-porter)
- Contract term: {{CONTRACT_TERM}}
- Special requirements: {{SPECIAL_REQS}}  (e.g. SCIF areas, biohazard rooms, LEED compliance, union labor)

COMPANY INPUTS:
- Our company name: {{COMPANY_NAME}}
- Years in business: {{YEARS}}
- Total sqft currently serviced: {{PORTFOLIO_SQFT}}
- Two comparable accounts (name, sqft, years): {{REFERENCES}}
- General liability limit: {{GL_LIMIT}}
- Workers comp carrier: {{WC_CARRIER}}

REQUIRED OUTPUT STRUCTURE (use these exact H2 headings):

1. Executive Summary  (3 paragraphs max, references building name + contract term)
2. Company Qualifications  (named references, portfolio scale, certifications)
3. Scope of Work Matrix  (markdown table: Zone | Task | Frequency | Method/Chemical)
4. Staffing & Supervision Plan  (crew size, shift schedule, named supervisor escalation)
5. Safety & Compliance Program  (must reference: OSHA 29 CFR 1910.1030 bloodborne pathogens,
   SDS binder on-site, GHS-compliant chemical labeling, lockout/tagout for equipment,
   COVID-era disinfection protocols per CDC guidance)
6. Quality Assurance & Reporting  (inspection cadence, KPI dashboard, complaint SLA in hours)
7. Pricing Schedule  (monthly base + itemized periodic services + emergency hourly rate)

HARD RULES:
- Use formal, third-person corporate voice. No 'we're excited' or 'thrilled to partner'.
- Every claim must be specific. Replace 'experienced team' with 'crew of 6 with avg 4.2 years tenure'.
- The scope matrix must contain at least 25 line items broken down by zone (restrooms, lobby,
  open office, private offices, kitchen/break rooms, conference rooms, elevators, stairwells,
  data closets, exterior entry, loading dock).
- Pricing section must list monthly recurring, then a separate periodic services table
  (carpet extraction, hard-floor strip & wax, window cleaning, pressure washing) priced per occurrence.
- Do NOT invent insurance limits, certifications, or references. Use the inputs verbatim.
- Do NOT use the words: 'delve', 'leverage', 'synergy', 'cutting-edge', 'world-class', 'tapestry'.
- If any input is missing, output [REVIEW: missing {{FIELD}}] inline instead of guessing.

OUTPUT FORMAT: Clean markdown, ready to paste into Microsoft Word via paste-special.
```

## Your Meetings Are Bleeding Money: The Transcript Deconstruction Method That Forces Accountability

**Category:** Automation  
**Topics:** Productivity, Development  
**Models:** ChatGPT, Claude, Gemini  
**URL:** https://solopromptai.com/prompts/transcript-deconstruction-meeting-extraction-prompt

Stop summarizing meetings and start deconstructing them. A senior-PM-grade prompt that turns any raw transcript into a Who-What-When matrix in one shot.

```text
# ROLE
Act as a Senior Project Manager and Data Extraction Specialist. I am providing you with a raw, unedited transcript from a recent meeting or discussion.

# YOUR MISSION
Perform a deep DECONSTRUCTION of this text. Do not provide a summary. Do not describe the tone of the meeting. Your sole objective is to identify every hidden obligation, specific deadline, and project milestone mentioned or implied within the dialogue.

# REQUIRED OUTPUT FORMAT
You must output the findings strictly as a WHO-WHAT-WHEN MATRIX. Use the following structure for every identified task:

- **OWNER:** The person responsible for the action.
- **ACTION:** A clear, verb-driven description of the task.
- **DEADLINE:** The specific date or timeframe mentioned. If no date is mentioned, write `TBD` based on context.

If an owner or deadline is not explicitly stated but can be reasonably inferred from the conversation, include your inference but label it as `INFERRED`.

Flag any decision made without an owner as a `CRITICAL UNASSIGNED TASK`.

# TRANSCRIPT CONTENT
<TRANSCRIPT>
{{PASTE_TRANSCRIPT_HERE}}
</TRANSCRIPT>

Begin extraction.
```