Prompts that specify the answer

You are a paid search copywriter working to strict Google Ads character limits.

Product or service: {{PRODUCT}}
Target keyword or ad group theme: {{AD_GROUP_THEME}}

Act as a Google Ads specialist building one responsive search ad.

Ad group: {{AD_GROUP_NAME}}
Top 5 keywords in the ad group: {{KEYWORDS}}

You are a PPC analyst cleaning up wasted spend.

Here is my search terms data as rows of: search term, impressions, clicks, cost, conversions.
{{SEARCH_TERMS_DATA}}

You are a conversion copywriter. Your job is to write a landing page that continues the exact promise of the ad that sent the visitor.

The ad they clicked (headlines and descriptions): {{AD_COPY}}
The keyword that triggered it: {{KEYWORD}}

Act as a paid media auditor. Compare an ad against the page it points to and find the mismatches.

Ad copy: {{AD_COPY}}
Keywords in the ad group: {{KEYWORDS}}

You are a landing page copywriter rewriting one hero section.

Current hero headline: {{CURRENT_HEADLINE}}
Current subhead: {{CURRENT_SUBHEAD}}

You are a conversion copywriter building the objection handling section of a landing page.

Product: {{PRODUCT}}
Price and commitment: {{PRICE_AND_COMMITMENT}}

Act as a paid social strategist writing a creative brief that a designer or video editor can execute without asking you questions.

Brand: {{BRAND}}
Platform and placement: {{PLATFORM_AND_PLACEMENT}}

You are a conversion copywriter working only on calls to action.

Page or ad: {{PAGE_OR_AD}}
Current CTA labels and where each sits: {{CURRENT_CTAS}}

You are a conversion strategist choosing which testimonials to put on a landing page and where.

Raw testimonials and reviews, verbatim: {{TESTIMONIALS}}
Page sections in order: {{PAGE_SECTIONS}}

You are a paid media analyst deciding how to reallocate budget. Be conservative and say when the data cannot support a decision.

Campaign data as rows of: campaign, spend, impressions, clicks, conversions, conversion value, date range.
{{CAMPAIGN_DATA}}

You are a direct response strategist. Build ad angles only from the language of real customers, not from marketing imagination.

Raw customer language (reviews, survey answers, sales call notes, support tickets): {{CUSTOMER_LANGUAGE}}
Product: {{PRODUCT}}

You are a Google Ads specialist writing extension assets to spec.

Business: {{BUSINESS}}
Campaign or ad group theme: {{CAMPAIGN_THEME}}

You are a competitive analyst pulling apart rival ads to find an unclaimed position.

Competitor ads, verbatim, labeled by advertiser: {{COMPETITOR_ADS}}
My product: {{MY_PRODUCT}}

You are a conversion specialist auditing a lead capture form.

Form fields as they currently are, in order: {{CURRENT_FIELDS}}
What happens to a lead after submission: {{LEAD_PROCESS}}

You are a compliance reviewer checking ad copy before it goes live. Be strict and flag anything doubtful.

Ad copy to review: {{AD_COPY}}
Sector and regulator or platform policy that applies: {{SECTOR_AND_POLICY}}

You are a conversion optimization lead writing a test plan that will produce a decision, not a debate.

Page and its job: {{PAGE_AND_JOB}}
Current conversion rate and monthly conversions: {{CURRENT_PERFORMANCE}}

You are a paid media diagnostician. Traffic is arriving and not converting. Work out where it is going wrong and in what order to check things.

Ad copy and keywords or audience: {{AD_AND_TARGETING}}
Landing page text as a visitor reads it: {{PAGE_TEXT}}

You are a paid search specialist filling one Performance Max asset group. You are not planning campaign structure and you are not setting budgets.

Product or service in this asset group: {{ASSET_GROUP_PRODUCT}}
Landing page text, as a visitor reads it: {{LANDING_PAGE_TEXT}}

You are a paid media analyst planning a bid strategy change. You are not writing ad copy or restructuring the account.

Campaign, current bid strategy and current target: {{CURRENT_STRATEGY}}
Eight weeks of data as rows of week, spend, conversions, conversion value, average CPA, impression share lost to budget and to rank: {{WEEKLY_DATA}}

You are a paid social strategist building a retargeting ladder. You are not writing the prospecting campaign.

Actions I can actually track on the site: {{TRACKED_ACTIONS}}
Typical time from first visit to purchase: {{SALES_CYCLE}}

You are a paid social analyst reading creative decay. You are not redesigning ads or changing targeting.

Performance rows as creative name, days live, spend, impressions, frequency, weekly CTR, weekly CPA: {{CREATIVE_DATA}}
What each creative shows and says: {{CREATIVE_DESCRIPTIONS}}

You are an analytics lead writing a UTM convention. You are not implementing tags or auditing conversion tracking.

Channels and platforms currently running: {{CHANNELS}}
Tagged URLs as they appear in reports today: {{CURRENT_UTMS}}

You are a direct response strategist working on the offer itself. Do not rewrite ads or headlines.

The current offer, copied exactly as the page states it: {{CURRENT_OFFER}}
Price, margin room and what I can genuinely give away: {{MARGIN_ROOM}}

You are a conversion copywriter writing one page for people searching for an alternative to a named competitor. You are not writing the ads that point at it.

Competitor named in the search: {{COMPETITOR}}
What their own site, pricing page and documentation state, pasted: {{COMPETITOR_PUBLIC_FACTS}}

You are a paid media analyst joining CRM outcomes back to campaign data. You are not rewriting ads.

Campaign rows as name, spend, leads, cost per lead: {{CAMPAIGN_LEADS}}
CRM outcomes for the same period as lead source, qualified, disqualified with reason, opportunities, closed won, value: {{CRM_OUTCOMES}}

You are a paid media lead running the final check before a campaign goes live. You are not reviewing creative quality.

Campaign as configured, covering objective, budget, bid strategy, locations, schedule, devices and audiences: {{CAMPAIGN_SETUP}}
Landing page URLs with their tracking parameters attached: {{DESTINATION_URLS}}

You are a copywriter adapting paid ads for another market. You are not translating literally and you are not inventing local claims.

Source ad copy, line by line: {{SOURCE_COPY}}
Target market, language and regional variety: {{TARGET_MARKET}}

You are a search analyst. I will paste a Google Search Console query export.

Data:
{{GSC_QUERY_EXPORT}}

You are writing the narrative section of a monthly performance report for {{CLIENT_OR_TEAM}}.

Numbers for {{MONTH}}:
{{METRICS_WITH_COMPARISONS}}

Act as a skeptical analyst investigating a traffic drop. Your job is to find the cause, not to reassure me.

Drop: {{METRIC}} fell from {{BEFORE}} to {{AFTER}} between {{DATE_A}} and {{DATE_B}}.
Segment breakdown available: {{SEGMENT_DATA}}

You are a GA4 practitioner. Turn my question into a build spec I can follow in the GA4 Explore interface.

Question I need answered: {{BUSINESS_QUESTION}}
Events and parameters available: {{EVENTS_AND_PARAMS}}

You are reading a cohort retention table for {{PRODUCT_OR_SITE}}.

Cohort table (rows are cohorts by {{COHORT_BASIS}}, columns are periods since acquisition):
{{COHORT_TABLE}}

You are explaining attribution limits to {{AUDIENCE}}, who are not analysts and will act on these numbers.

Setup:
Attribution model in use: {{MODEL}}

You are writing the executive summary that sits on top of a performance dashboard.

Reader: {{READER_ROLE}}, cares most about {{READER_PRIORITY}}, will spend about 90 seconds on this.
Dashboard data: {{DASHBOARD_DUMP}}

You are producing a forecast for {{METRIC}} for {{FORECAST_PERIOD}}.

Historical data: {{HISTORICAL_SERIES}}
Known upcoming events: {{PLANNED_EVENTS}}

You are triaging a set of analytics anomalies. Treat this like an on-call queue.

Anomalies detected:
{{ANOMALY_LIST}}

You are specifying a dashboard before it gets built. Write the spec, not the dashboard.

Who uses it: {{USERS_AND_ROLES}}
Decisions it must support: {{DECISIONS}}

You are turning a data dump into decisions. Nothing else.

Data:
{{DATA_DUMP}}

You are auditing landing page performance from analytics data.

Page data (URL, sessions, entrances, bounce or engagement rate, conversions, conversion rate, revenue if available):
{{PAGE_DATA}}

Compare channel performance for {{BUSINESS}} without pretending attribution is settled.

Channel data: {{CHANNEL_DATA}}
Costs by channel: {{COSTS}}

You are reviewing an A/B test result critically before anyone ships the winner.

Test: {{TEST_DESCRIPTION}}
Hypothesis as written before the test: {{HYPOTHESIS}}

Two sources disagree about the same metric. Explain the gap before anyone picks a favorite.

Metric: {{METRIC_NAME}}
Source A: {{SOURCE_A}} reports {{VALUE_A}}

You are checking whether a change in {{METRIC}} is real performance or seasonality.

Current period: {{CURRENT_PERIOD}} value {{CURRENT_VALUE}}
Comparison period: {{COMPARISON_PERIOD}} value {{COMPARISON_VALUE}}

A stakeholder has asked a data question. Answer it honestly, including the part where the question itself is off.

Question as asked: {{QUESTION}}
Who asked and what they are trying to decide: {{ASKER_AND_GOAL}}

Outline a quarterly performance review for {{AUDIENCE}}. Structure only, plus the content brief for each slide.

Quarter: {{QUARTER}}
Results against targets: {{RESULTS_VS_TARGETS}}

You are examining the shape of a metric, not its average. You are not recommending product changes.

Metric and how it is calculated: {{METRIC_DEFINITION}}
Raw values, percentile summary, or bucketed counts: {{DISTRIBUTION_DATA}}

You are a measurement engineer writing a tracking plan. You are not writing implementation code, only specifying what gets sent and why.

Feature or launch: {{FEATURE_DESCRIPTION}}
Questions we must be able to answer after launch: {{QUESTIONS_TO_ANSWER}}

You are auditing campaign tagging. You are not judging campaign performance, only working out which rows in the report misstate where traffic came from.

Tagged URLs or a source and medium export: {{TAGGING_EXPORT}}
The convention we are meant to follow: {{TAGGING_CONVENTION}}

You are estimating what consent and tracking loss does to reported numbers. You are not giving legal advice and you are not redesigning the banner.

Consent setup, banner behaviour and defaults: {{CONSENT_SETUP}}
Consent rates by region or device where known: {{CONSENT_RATES}}

You are designing a holdout test to measure incremental effect. You are not evaluating a finished test and you are not defending the current attribution model.

Activity to test: {{ACTIVITY_TO_TEST}}
Current reported performance and spend: {{CURRENT_PERFORMANCE}}

You are reviewing a query before its output reaches a report. You are not optimising it for speed, you are checking whether it answers the question asked.

The question it is meant to answer: {{QUESTION}}
The query: {{QUERY_SQL}}

You are profiling segments to find where value concentrates. You are not writing personas and you are not describing anyone in personality terms.

Segment data with counts and value: {{SEGMENT_DATA}}
How value is defined here: {{VALUE_DEFINITION}}

You are setting alert thresholds so that an alert firing means something. You are not diagnosing a live incident.

Metrics we want to alert on: {{METRICS_TO_ALERT}}
Historical variation for each, by day of week where available: {{HISTORICAL_VARIATION}}

You are checking whether a dataset can support an analysis before anyone runs it. You are not doing the analysis.

The analysis planned: {{PLANNED_ANALYSIS}}
Dataset description, including row count, date range and columns: {{DATASET_DESCRIPTION}}

You are reading acquisition economics. You are not producing a valuation and you are not projecting beyond the data.

Spend and new customers by channel and month: {{SPEND_AND_ACQUISITION}}
Revenue or margin per customer by month since acquisition: {{REVENUE_CURVE}}

You are a content strategist producing a brief for a staff writer. You are not writing the article.

Target keyword: {{TARGET_KEYWORD}}
Search intent as I read it: {{INTENT_NOTE}}

You are an editor turning raw research into a structure. Work only from the material I give you.

Working title: {{WORKING_TITLE}}
Audience and what they already know: {{AUDIENCE}}

You are writing a first draft for publication under a named human byline. Follow the brief exactly.

Brief and outline:
{{BRIEF}}

You are a line editor. The draft below was written by a language model. Your job is to make it read as if a knowledgeable person wrote it quickly and carefully, without changing the facts.

Draft:
{{DRAFT}}

You are a ruthless subeditor. Cut the copy below to {{TARGET_WORDS}} words or fewer while keeping every load-bearing claim.

Copy:
{{COPY}}

You are adapting an existing piece for a different reader. Do not lose accuracy while changing the level.

Original: {{ORIGINAL_TEXT}}
Current reader: {{CURRENT_READER}}

You are a fact-checker reviewing a draft before publication. You are not editing style.

Draft:
{{DRAFT}}

You are a headline editor. Generate options for the piece below and rank them against a stated rule.

Piece summary: {{SUMMARY}}
Single most useful thing the reader gets: {{PAYOFF}}

You are rewriting the opening of an article. The reader arrived from search with a specific problem and will leave if the first 40 words do not show they are in the right place.

Article body: {{ARTICLE_BODY}}
What the reader searched or was thinking: {{READER_PROBLEM}}

You are building an FAQ section from real questions, not from keyword tools.

Page topic: {{PAGE_TOPIC}}
Real questions collected from support, sales or search console:

You are auditing an existing article that has lost traffic, and producing an update plan. Do not rewrite the whole thing.

Article: {{ARTICLE_TEXT}}
Published: {{PUBLISH_DATE}}. Last updated: {{LAST_UPDATED}}

You are turning a spoken transcript into a written article. Spoken structure does not survive the transfer, so restructure it.

Transcript: {{TRANSCRIPT}}
Speakers and roles: {{SPEAKERS}}

You are enforcing a house style guide on a draft. Report before you fix.

Style guide:
{{STYLE_GUIDE}}

One section of an article is thin. Diagnose whether it needs more substance or should be cut, then fix it.

Full article for context: {{ARTICLE}}
The thin section: {{THIN_SECTION}}

You are repurposing a published article. Each output format must stand alone and be worth reading on its own.

Article: {{ARTICLE}}
Formats wanted: {{FORMATS}}

You are writing meta titles and descriptions. Each must be an accurate promise the page keeps.

For each page below I give the URL, the primary query, the H1, and a summary of the content:
{{PAGE_DATA}}

You are rewriting a product page around the reasons people do not buy, not around the feature list.

Product: {{PRODUCT}}
Who buys it and what they are comparing it against: {{BUYER_AND_ALTERNATIVES}}

You are a demanding editor giving a final read. You are not fixing the draft. You are deciding whether it earns publication.

Draft: {{DRAFT}}
Where it will be published and who reads it: {{PUBLICATION_AND_AUDIENCE}}

You are drafting a customer case study from interview material. You are not writing testimonial copy and you are not inventing outcomes.

Customer, what they bought and when: {{CUSTOMER_CONTEXT}}
Interview notes and quotes: {{INTERVIEW_NOTES}}

You are preparing to interview a subject expert so a writer can produce something competing pages do not contain. You are not writing the article.

Topic and the angle we are taking: {{TOPIC_AND_ANGLE}}
The expert, their role and what they have actually done: {{EXPERT_BACKGROUND}}

You are diagnosing the structure of a piece that reads well sentence by sentence and badly as a whole. You are not line editing.

Draft: {{DRAFT}}
The claim the piece is meant to land: {{CENTRAL_CLAIM}}

You are adapting marketing copy for a different market. You are not translating it and you are not changing the offer.

Source copy: {{SOURCE_COPY}}
Target market, language and variety: {{TARGET_MARKET}}

You are writing a comparison page that names a competitor. Accuracy is the whole value of the page, so an unverified row is worse than a missing one.

Our product, pricing and limits: {{OUR_PRODUCT}}
Competitor facts, each with where it came from and when: {{COMPETITOR_FACTS}}

You are reviewing page copy for accessibility. You are reviewing the words and their structure, not the code.

Page copy with heading levels marked: {{PAGE_COPY}}
Image list, each with what it shows and why it is on the page: {{IMAGE_LIST}}

You are writing a revision request to a commissioned writer. You are not rewriting the draft and you are not softening the asks.

The brief they were given: {{BRIEF_GIVEN}}
The draft they delivered: {{DELIVERED_DRAFT}}

You are recommending what happens to each post in a content library. You are not rewriting anything and you are not removing anything, only deciding.

Inventory rows with URL, title, publish date, traffic, conversions and referring domains: {{INVENTORY_ROWS}}
What the site is for now: {{SITE_PURPOSE}}

You are assembling a curated newsletter issue. The value is the judgement between the links, not the links.

Saved items, each with title, source and my note: {{SAVED_ITEMS}}
Who subscribes and what they do for a living: {{SUBSCRIBERS}}

You are planning a long asset assembled from published posts. You are not writing it and you are not stitching the posts together in publication order.

Published posts with title, summary and main sections: {{PUBLISHED_POSTS}}
What the asset is and who downloads it: {{ASSET_AND_AUDIENCE}}

You are a conversion analyst reviewing a landing page. Work only from the material I give you. Do not invent page elements you cannot see.

PAGE CONTENT:
{{PAGE_COPY_OR_SCREENSHOT_DESCRIPTION}}

You are auditing a form for unnecessary friction.

FORM PURPOSE: {{FORM_PURPOSE}}
FIELDS (name, type, required or optional): {{FIELD_LIST}}

You are reviewing a pricing page for comprehension problems, not for aesthetics.

PLAN STRUCTURE: {{PLAN_NAMES_PRICES_AND_FEATURES}}
BILLING MODEL: {{BILLING_MODEL}}

You are auditing the trust and proof elements on a page. Assume the visitor is skeptical and has not heard of us.

PAGE: {{PAGE_URL_OR_DESCRIPTION}}
TRUST ELEMENTS PRESENT: {{LIST_OF_LOGOS_TESTIMONIALS_BADGES_STATS_GUARANTEES}}

You are helping write a testable hypothesis. Do not accept a vague idea - force it into a falsifiable statement.

THE IDEA: {{IDEA}}
EVIDENCE THAT PROMPTED IT: {{EVIDENCE}}

You are synthesising raw notes from session recordings into patterns. Be conservative: a pattern needs repetition, not one memorable session.

RAW NOTES (one session per block): {{SESSION_NOTES}}
NUMBER OF SESSIONS WATCHED: {{SESSION_COUNT}}

You are auditing a checkout flow step by step.

FLOW STEPS IN ORDER: {{STEP_LIST}}
DROP-OFF BY STEP (if known): {{STEP_DROPOFF_DATA}}

You are rewriting interface microcopy. Every rewrite must have a stated reason.

ELEMENTS TO REWRITE (current text, element type, where it appears): {{CURRENT_MICROCOPY}}
WHAT THE USER IS TRYING TO DO AT THIS POINT: {{USER_GOAL}}

You are diagnosing why a page converts worse on mobile than desktop. Only report issues that are genuinely mobile specific.

PAGE OR FLOW: {{PAGE}}
MOBILE CONVERSION RATE: {{MOBILE_RATE}}

You are extracting buyer objections from sales conversations and mapping them to the website.

CALL TRANSCRIPTS OR NOTES: {{TRANSCRIPTS}}
NUMBER OF CALLS: {{CALL_COUNT}}

You are writing the readout for a completed experiment. Honesty about a null result is the point of this document.

TEST NAME: {{TEST_NAME}}
HYPOTHESIS AS WRITTEN BEFORE THE TEST: {{ORIGINAL_HYPOTHESIS}}

You are reviewing the calls to action on a page for competition and placement.

PAGE CONTENT IN ORDER: {{PAGE_SECTIONS_IN_ORDER}}
EVERY CTA ON THE PAGE (text, type, position): {{CTA_LIST}}

You are running a comprehension test on the first screen of a page. Behave like a first-time visitor with no context.

WHAT IS VISIBLE BEFORE SCROLLING: {{HERO_CONTENT}}
DEVICE: {{DEVICE}}

You are diagnosing a conversion funnel from step data. Be careful to separate the biggest drop from the most fixable drop.

FUNNEL STEPS AND VOLUMES: {{STEP_VOLUMES}}
TIME PERIOD: {{PERIOD}}

You are designing a short on-site survey for visitors who are about to leave without converting.

PAGE OR STEP WHERE IT TRIGGERS: {{TRIGGER_LOCATION}}
WHAT I WANT TO LEARN: {{RESEARCH_QUESTION}}

You are prioritizing a backlog of conversion test ideas. Score consistently and show your reasoning.

BACKLOG (one idea per line, with any supporting evidence): {{BACKLOG}}
PAGE TRAFFIC FOR EACH LOCATION: {{TRAFFIC_BY_PAGE}}

You are auditing every route off a conversion focused page.

PAGE: {{PAGE}}
PURPOSE OF THE PAGE: {{PAGE_PURPOSE}}

You are reviewing the page a user sees immediately after converting. Most of these pages waste the highest attention moment in the journey.

CONVERSION ACTION JUST COMPLETED: {{ACTION_COMPLETED}}
CURRENT CONFIRMATION PAGE CONTENT: {{CURRENT_CONTENT}}

You are sequencing a multi step form. You are not deciding which fields exist, only what order they appear in and where the step breaks fall.

FIELDS ALREADY AGREED: {{FIELD_LIST}}
WHAT THE VISITOR CAME TO DO: {{VISITOR_GOAL}}

You are reviewing how a form behaves when the visitor gets something wrong. You are not redesigning the form or cutting fields.

FIELDS AND THEIR VALIDATION RULES: {{FIELD_RULES}}
ERROR MESSAGES EXACTLY AS THEY APPEAR: {{CURRENT_ERROR_TEXT}}

You are mapping the path from account creation to the first moment the product is useful. You are not writing onboarding copy or proposing new features.

SIGNUP AND SETUP STEPS IN ORDER: {{SETUP_STEPS}}
WHAT COUNTS AS FIRST VALUE FOR THIS PRODUCT: {{FIRST_VALUE_EVENT}}

You are checking an experiment before it goes live. You are not judging whether the idea is good, only whether the test will produce a result anyone can trust.

VARIANT DESCRIPTIONS AND WHAT CHANGES IN CODE: {{VARIANT_SPEC}}
TARGETING AND TRAFFIC ALLOCATION: {{TARGETING_RULES}}

You are checking urgency and scarcity claims for truth first and effect second. You are not writing new urgency copy unless a claim is genuinely true.

URGENCY AND SCARCITY ELEMENTS PRESENT: {{URGENCY_ELEMENTS}}
WHAT IS ACTUALLY TRUE ABOUT STOCK, DEADLINES AND CAPACITY: {{UNDERLYING_FACTS}}

You are finding accessibility failures that also stop people converting. You are not producing a full WCAG audit or a legal opinion.

PAGE OR FLOW AND ITS CONVERSION ACTION: {{FLOW_AND_ACTION}}
MARKUP, COMPONENT LIST OR SCREENSHOT DESCRIPTION: {{PAGE_STRUCTURE}}

You are designing the risk reversal for an offer. You are not drafting legal terms, and you must not invent a policy we do not operate.

WHAT WE SELL AND THE PRICE: {{OFFER_AND_PRICE}}
THE REFUND, CANCELLATION AND TRIAL TERMS WE ACTUALLY OPERATE: {{ACTUAL_TERMS}}

You are reviewing the path from a demo request to a confirmed meeting in the calendar. You are not rewriting the sales pitch.

THE STEPS FROM CLICK TO CONFIRMED MEETING: {{BOOKING_STEPS}}
FORM FIELDS AND ANY QUALIFICATION LOGIC: {{FORM_AND_QUALIFICATION}}

You are checking the order of the sections on a long page. You are not rewriting the copy inside them.

SECTIONS IN CURRENT ORDER, ONE LINE ON EACH: {{SECTION_ORDER}}
WHAT THE VISITOR ALREADY KNOWS ON ARRIVAL: {{PRIOR_KNOWLEDGE}}

You are choosing the cheapest research method that would genuinely answer a conversion question. You are not running the research or designing a test.

THE QUESTION I NEED ANSWERED: {{RESEARCH_QUESTION}}
WHAT I ALREADY KNOW AND WHERE IT CAME FROM: {{EXISTING_EVIDENCE}}

You are writing product descriptions for {{BRAND_NAME}}, which sells {{PRODUCT_CATEGORY}}.

Here are the products, one per line, with their attributes:
{{PRODUCT_LIST_WITH_ATTRIBUTES}}

You are writing on-page copy for the category page "{{CATEGORY_NAME}}" on {{SITE_NAME}}.

Context:
- Products in the category: {{PRODUCT_TYPES_AND_PRICE_RANGE}}

Write a buying guide titled "{{GUIDE_TITLE}}" for {{SITE_NAME}}.

Range available:
{{PRODUCT_LIST_WITH_KEY_SPECS_AND_PRICES}}

Write a comparison page for {{PRODUCT_A}} versus {{PRODUCT_B}}, both sold by {{SITE_NAME}}.

Specs and prices:
{{SPECS_FOR_BOTH}}

You are analyzing customer reviews for {{PRODUCT_NAME}} and turning them into copy.

Reviews:
{{PASTED_REVIEWS}}

Write size and fit copy for {{PRODUCT_NAME}} sold by {{BRAND_NAME}}.

Inputs:
- Size chart: {{SIZE_CHART}}

Write out of stock messaging for {{PRODUCT_NAME}} on {{SITE_NAME}}.

Situation:
- Reason unavailable: {{REASON}}

Generate JSON-LD Product structured data for this page.

Page data:
- Product name: {{PRODUCT_NAME}}

You are converting a supplier spec sheet into structured attributes for a product feed.

Target attribute schema (use these field names exactly):
{{ATTRIBUTE_SCHEMA}}

Build a campaign copy set for {{BRAND_NAME}}.

Campaign: {{CAMPAIGN_NAME}}
Offer, exactly as it will run: {{OFFER_TERMS}}

Rewrite this returns policy so a customer can act on it without contacting support.

Current policy:
{{CURRENT_POLICY_TEXT}}

Write positioning and copy for a bundle sold by {{BRAND_NAME}}.

Bundle contents and individual prices:
{{BUNDLE_CONTENTS_WITH_PRICES}}

I have one product sold as multiple variants, each on its own URL. They currently share identical copy.

Base product: {{PRODUCT_NAME}}
Shared description: {{SHARED_DESCRIPTION}}

Rewrite the above the fold block on this product page.

Product: {{PRODUCT_NAME}}
Current title, price, and copy: {{CURRENT_ABOVE_FOLD}}

Write consistent delivery copy for {{BRAND_NAME}} across all touchpoints.

Actual delivery options, costs, cut off times and carriers:
{{DELIVERY_MATRIX}}

Optimize shopping feed titles for {{RETAILER_OR_CHANNEL}}.

Products with current titles and attributes:
{{PRODUCT_TITLES_AND_ATTRIBUTES}}

Build a gift guide for {{SITE_NAME}}, titled "{{GUIDE_TITLE}}".

Available products with prices and a one line note each:
{{PRODUCT_LIST}}

Audit this product page for missing information.

Full page content as it stands:
{{PAGE_CONTENT}}

You are a merchandising lead restructuring a category tree. You are not writing page copy and you are not choosing which products go where.

Current tree, one node per line with depth shown by indentation:
{{CURRENT_CATEGORY_TREE}}

You are writing alt text for product imagery. You are not writing captions and you are not describing anything the image does not show.

Images, one per line with filename, shot type and the product they belong to:
{{IMAGE_LIST}}

You are rewriting checkout interface strings. You are not redesigning the flow and you are not adding steps.

Current strings, one per line with the field or state they belong to:
{{CURRENT_STRINGS}}

You are building a synonym and redirect ruleset for a site search engine. You are not writing product copy.

Failed or low-result queries with their frequency:
{{ZERO_RESULT_QUERIES}}

You are adapting an existing product page into a marketplace listing. You are not inventing product facts.

Our current page copy: {{SOURCE_PAGE_COPY}}
Marketplace listing rules as published: {{MARKETPLACE_RULES}}

You are renaming filters on a listing page so shoppers understand them. You are not changing which products match.

Facets and their values exactly as they render now:
{{CURRENT_FACETS}}

You are writing copy for a subscription option on products currently sold one at a time. You are not designing the pricing.

Products and how often they are actually reordered: {{PRODUCT_AND_REORDER_DATA}}
Subscription terms exactly as they will run: {{SUBSCRIPTION_TERMS}}

You are turning supplier care and use information into instructions a customer can follow. You are not writing marketing copy.

Supplier documentation: {{SUPPLIER_CARE_TEXT}}
Materials and components in this specific product: {{MATERIALS}}

You are writing the copy around product recommendation slots. You are not choosing the recommendation algorithm.

Slots and where they appear: {{SLOT_LOCATIONS}} (for example product page, basket, order confirmation)
Anchor products and what is currently shown alongside them: {{PAIRING_DATA}}

You are reviewing product copy for claims that need evidence. You are not a lawyer and you are not approving anything for publication.

Copy under review: {{DRAFT_COPY}}
Evidence we hold, with dates and who produced it: {{EVIDENCE_PACK}}

You are a lifecycle email strategist. Design a five-email welcome sequence.

Business: {{BUSINESS_DESCRIPTION}}
What the person just did to join the list: {{SIGNUP_TRIGGER}}

You are an email copywriter. Write 12 subject lines for the email below.

Email body: {{EMAIL_BODY}}
Audience: {{AUDIENCE}}

You are an email deliverability and inbox copy reviewer. Audit the inbox preview for the sends below.

For each send I will give: from name, subject, preheader, first line of body.
Sends:

You are a lifecycle email strategist. Write a three-email win-back sequence for subscribers who have not opened or clicked in {{INACTIVE_PERIOD}}.

Business: {{BUSINESS_DESCRIPTION}}
What has actually changed since they were last active: {{WHAT_CHANGED}}

You are an ecommerce email copywriter. Write a three-email abandoned cart sequence.

Product or category: {{PRODUCT}}
Average order value: {{AOV}}

You are a retention email copywriter. Write a two-email review request flow.

Product or service: {{PRODUCT}}
Time until a customer can fairly judge it: {{TIME_TO_VALUE}}

You are a demanding newsletter editor. Edit the draft below. Keep my voice and my argument. Do not replace my writing with your own.

Draft:
{{NEWSLETTER_DRAFT}}

You are an email copywriter. Rewrite the designed email below as a plain-text email that could plausibly have been typed by one person.

Original email including button labels and image alt text: {{ORIGINAL_EMAIL}}
Who it appears to come from: {{SENDER_PERSON}}

You are an email copywriter working on segmentation. Take the base email and produce one variant per segment.

Base email: {{BASE_EMAIL}}
Offer or announcement: {{OFFER}}

You are a B2B outreach writer. Write one cold email to a specific person.

My company and what it does: {{MY_COMPANY}}
Recipient name and role: {{RECIPIENT}}

You are a B2B outreach writer. Write a four-step follow-up ladder for a cold email that got no reply.

First email sent: {{FIRST_EMAIL}}
Recipient and role: {{RECIPIENT}}

You are a product marketing copywriter. Write a launch announcement email.

Product: {{PRODUCT_NAME}}
What it does, in plain terms: {{WHAT_IT_DOES}}

You are a product communications writer. Write a release note email for existing customers.

Product: {{PRODUCT_NAME}}
What changed: {{CHANGES}}

You are a retention email writer. Write a renewal reminder sequence.

Product and plan: {{PRODUCT_AND_PLAN}}
Renewal amount and date logic: {{RENEWAL_TERMS}}

You are a billing communications writer. Write a dunning sequence for failed payments.

Product: {{PRODUCT}}
Retry schedule the billing system uses: {{RETRY_SCHEDULE}}

You are an email program analyst. Work out what is driving unsubscribes and what to change.

Send data, one row per send with subject, segment, send date, list size, open rate, click rate, unsubscribe rate, spam complaint rate:
{{SEND_DATA}}

You are an email deliverability reviewer. Review the email below for content and structure risks that affect inbox placement. Judge only what is in the copy and the send setup I describe. Do not comment on authentication records you cannot see.

Email, including subject, preheader, body, links and footer: {{EMAIL}}
Send type, such as broadcast, automation or transactional: {{SEND_TYPE}}

You are a customer communications writer. Write a price increase notice.

Product and plan affected: {{PRODUCT_AND_PLAN}}
Old price, new price, effective date: {{PRICE_CHANGE_DETAILS}}

You are an email experimentation analyst. You are designing and reading one test, not writing email copy.

What I want to test, and the two versions: {{TEST_VARIANTS}}
Metric I will judge it on: {{PRIMARY_METRIC}}

You are a lifecycle email strategist planning the sends around one live session. You are not writing the session content.

Topic, and what an attendee will be able to do afterwards: {{SESSION_PROMISE}}
Date, time, and the time zones the audience sits in: {{SESSION_DATETIME}}

You are a product lifecycle email strategist. You are designing behaviour triggered sends, not a fixed drip.

Product and what the trial includes: {{PRODUCT_AND_TRIAL}}
Trial length and what happens at the end: {{TRIAL_TERMS}}

You are a customer communications editor reviewing transactional mail. You are not adding marketing to it.

The messages, each with its trigger, subject and full body: {{TRANSACTIONAL_MESSAGES}}
Product, and what the customer has just done: {{PRODUCT_CONTEXT}}

You are a B2B sales writer. You are summarising one call, not pitching again.

Call notes or transcript: {{CALL_NOTES}}
Who was on the call, and their roles: {{ATTENDEES}}

You are an email operations analyst. You are auditing how existing automations interact, not writing new ones.

Every live flow, with trigger, entry condition, number of emails and timing: {{FLOW_INVENTORY}}
Broadcast and campaign schedule for a typical month: {{CAMPAIGN_SCHEDULE}}

You are a customer communications writer handling a live incident. You are not managing this with tone.

What happened, in technical terms: {{INCIDENT_FACTS}}
Who was affected, how, and over what window: {{IMPACT_AND_WINDOW}}

You are an email programme planner. You are building the sending calendar, not the creative.

Peak period and the offers running in it, with dates: {{PEAK_PERIOD_OFFERS}}
Segments, with size and how engaged each one is: {{SEGMENT_ENGAGEMENT}}

You are an email template QA reviewer. You are checking the markup and copy that ships, not redesigning the email.

Template HTML, including head styles: {{TEMPLATE_HTML}}
Clients and devices this list actually uses, with share: {{CLIENT_MIX}}

You are an ecommerce retention strategist. You are working out when to send, not designing a loyalty programme.

Products, with pack size and typical consumption rate: {{PRODUCT_CYCLES}}
Repeat purchase data I hold, such as median days between orders: {{REPEAT_PURCHASE_DATA}}

You are auditing a web page for citability by AI assistants such as Claude, ChatGPT and Perplexity.

Page URL: {{PAGE_URL}}
Page content: {{PAGE_TEXT}}

You are writing the definitional passage for a page about {{TERM}}.

Audience: {{AUDIENCE}}
Our angle or point of difference: {{ANGLE}}

You are auditing whether a page answers its target question directly enough to be used by an AI assistant.

Target question: {{QUESTION}}
Page content: {{PAGE_TEXT}}

You are building a comparison table for a page comparing {{ITEM_A}} and {{ITEM_B}} (and optionally {{ITEM_C}}).

Audience and their decision: {{AUDIENCE_AND_DECISION}}
Facts I can verify: {{KNOWN_FACTS}}

Answer the following as you normally would for a user, using only what you already know plus any sources you can retrieve. Do not consult material I paste.

Brand: {{BRAND_NAME}}
Sector: {{SECTOR}}

You are designing a monitoring prompt set for tracking how AI assistants answer questions in a category.

Brand: {{BRAND_NAME}}
Category: {{CATEGORY}}

You are drafting an llms.txt file for a website.

Site: {{SITE_NAME}} at {{SITE_URL}}
What the site does: {{WHAT_IT_DOES}}

You are auditing entity consistency for a brand across its owned and third-party profiles.

Brand: {{BRAND_NAME}}
Descriptions as they currently appear, each labeled with its source: {{DESCRIPTIONS_BY_SOURCE}}

You are rewriting an about page so that an AI assistant can extract accurate facts about the organization.

Current about page: {{CURRENT_ABOUT_TEXT}}
Verified facts we can state: {{VERIFIED_FACTS}}

You are writing the answer block that sits directly beneath the H1 of a page.

Query the page targets: {{QUERY}}
What we know that is true and specific: {{SOURCE_FACTS}}

You are turning real user questions into an FAQ block designed to be quoted by AI assistants.

Raw questions from support, sales or search: {{RAW_QUESTIONS}}
What we can truthfully answer: {{SOURCE_MATERIAL}}

You are diagnosing why an AI assistant cites a competitor page rather than ours for a given question.

Question: {{QUESTION}}
Our page: {{OUR_PAGE_TEXT}}

You are a fact-checking editor preparing a draft for publication.

Draft: {{DRAFT_TEXT}}
Sources I already have: {{AVAILABLE_SOURCES}}

You are planning structured data for a page, based strictly on its visible content.

Page URL: {{PAGE_URL}}
Page content: {{PAGE_TEXT}}

You are rewriting a section of a page so its sentences can be quoted out of context.

Section as written: {{SECTION_TEXT}}
What this section must convey: {{KEY_POINTS}}

You are mapping question coverage for a topic so we can see where assistants have nothing of ours to cite.

Topic: {{TOPIC}}
Our audience: {{AUDIENCE}}

You are comparing an AI assistant's answer against the source page it should have used.

The question asked: {{QUESTION}}
The assistant's answer: {{ASSISTANT_ANSWER}}

You are adding honest freshness signals to a page so assistants can judge how current its facts are.

Page content: {{PAGE_TEXT}}
When each fact was last verified, if known: {{VERIFICATION_DATES}}

You are advising on crawler access policy. You are not predicting traffic and you are not writing a public statement.

Site and what it publishes: {{SITE_AND_CONTENT}}
User agents seen in server logs, with hit counts: {{AGENT_LOG_SUMMARY}}

You are working out which third-party sources an assistant leans on for a category. You are not writing outreach emails.

Category: {{CATEGORY}}
Sources cited in assistant answers, with the lines quoted from each: {{CITED_SOURCES}}

You are splitting a page the way a retrieval system would, then judging each piece on its own. You are not editing for style.

Page text: {{PAGE_TEXT}}
Heading structure as published: {{HEADING_STRUCTURE}}

You are rewriting pricing content so an assistant can state what something costs without guessing. You are not designing the page.

Pricing page as it stands: {{CURRENT_PRICING_TEXT}}
Verified pricing facts: {{PRICE_FACTS}}

You are reverse engineering the criteria behind shortlist answers. You are not writing a sales argument.

Assistant answers naming a shortlist, with the reasons each gave: {{SHORTLIST_ANSWERS}}
The qualifier buyers use, for example "for small teams" or "for regulated industries": {{SEGMENT}}

You are planning the correction of an out of date fact that assistants keep repeating. You are not drafting a press release.

The claim being repeated: {{STALE_CLAIM}}
What is true now, when it changed, and where that is documented: {{CURRENT_TRUTH}}

You are planning original data that others could cite. You are not producing the numbers and you must not estimate them.

What our data covers, with row counts and date range: {{DATA_WE_HOLD}}
Questions our audience asks that a number would settle: {{AUDIENCE_QUESTIONS}}

You are running a buyer conversation and then auditing your own answers. Answer from what you already know or can retrieve, not from anything I paste.

Brand: {{BRAND_NAME}}
Category: {{CATEGORY}}

You are building a reporting frame for visibility in assistant answers. You are not forecasting traffic or revenue.

The frozen prompt set and how often each prompt is run: {{TRACKED_PROMPTS}}
Logged results, one row per run: assistant, prompt, named or not, cited or not, URL cited: {{RESULTS_LOG}}

You are drafting attributable commentary from what a named expert actually said. You are not inventing an opinion on their behalf.

Expert name and credentials: {{EXPERT_CREDENTIALS}}
Raw notes, interview transcript or written answers: {{RAW_NOTES}}

You are writing the business description field for a Google Business Profile.

Business: {{BUSINESS_NAME}}
What it does: {{SERVICES}}

Plan one month of Google Business Profile posts for a local business.

Business: {{BUSINESS_NAME}}
Services: {{SERVICES}}

You are helping me write a service area page that would survive a manual review for thin or doorway content.

Service: {{SERVICE}}
Town or area: {{AREA}}

Write owner responses to positive reviews for a local business.

Business: {{BUSINESS_NAME}}
Person signing the replies: {{SIGNER_NAME}}

Help me reply to a negative review in public.

The review: {{REVIEW_TEXT}}
Star rating: {{RATING}}

Assess whether a review is likely to be fake or policy-violating, and draft the response.

The review: {{REVIEW_TEXT}}
Reviewer profile signals I can see (other reviews, account age, photo, name pattern): {{REVIEWER_SIGNALS}}

You are auditing name, address and phone consistency for a local business.

Canonical details as they should appear everywhere:
Name: {{CANONICAL_NAME}}

Build an FAQ section for a local business page.

Business and service: {{BUSINESS_AND_SERVICE}}
Area: {{AREA}}

Generate community content ideas for a local business that are worth publishing on their own terms.

Business: {{BUSINESS_NAME}}
Sector: {{SECTOR}}

You are auditing a set of location pages that are too similar to each other.

Business: {{BUSINESS_NAME}}
Locations: {{LOCATION_LIST}}

Plan LocalBusiness structured data for one location page.

Business name: {{BUSINESS_NAME}}
Most specific business type that applies: {{BUSINESS_TYPE}}

Build a citation cleanup and building plan for a local business.

Business: {{BUSINESS_NAME}}
Sector: {{SECTOR}}

Plan a seasonal campaign for a local business whose demand rises and falls through the year.

Business and service: {{BUSINESS_AND_SERVICE}}
Area: {{AREA}}

Help me structure the categories, services and attributes on a Google Business Profile.

Business: {{BUSINESS_NAME}}
What we actually do, in my own words: {{WHAT_WE_DO}}

Compare our local presence against competitors ranking above us and find the actionable gaps.

Search term and location the comparison is based on: {{SEARCH_TERM_AND_LOCATION}}
Our profile and site details: {{OUR_DETAILS}}

Write a review request sequence for a local business.

Business: {{BUSINESS_NAME}}
Service and typical job length: {{SERVICE_AND_JOB_LENGTH}}

Plan the questions and answers section on a Google Business Profile.

Business and service: {{BUSINESS_AND_SERVICE}}
Location: {{LOCATION}}

Audit a local landing page for whether it converts a nearby visitor into an enquiry.

Page URL: {{PAGE_URL}}
Page content, pasted: {{PAGE_CONTENT}}

You are planning the photo and video library for a Google Business Profile. You are not editing images and you are not claiming what any upload does to rankings.

Business and trade: {{BUSINESS_AND_TRADE}}
Photos already on the profile, with subject and date: {{CURRENT_PHOTOS}}

You are mining review text for themes. You are not writing replies and you are not summarising the business.

Our reviews, pasted with star rating and date: {{OUR_REVIEWS}}
Reviews of nearby competitors, pasted the same way: {{COMPETITOR_REVIEWS}}

You are working out why a Google Business Profile was suspended, before anything is appealed. You are not the reviewer and you cannot see the profile.

The suspension notice, copied exactly: {{SUSPENSION_NOTICE}}
Profile as it stood: name, address, categories, hours, website: {{PROFILE_DETAILS}}

You are specifying how to measure map results across a service area. You are not running the scans and you hold no ranking data of your own.

Address the grid centres on: {{BUSINESS_ADDRESS}}
Area we serve and how far out it goes: {{SERVICE_RADIUS}}

You are planning listings on the map platforms that are not Google. You cannot see any of them and you must not assert what a platform currently requires.

Canonical name, address, phone, hours and website: {{CANONICAL_DETAILS}}
Country we trade in: {{COUNTRY}}

You are sequencing an address change for a local business. You are not deciding whether to move and you cannot check any listing yourself.

Old address: {{OLD_ADDRESS}}
New address: {{NEW_ADDRESS}}

You are deciding which named people at a local business deserve a page of their own. You are not writing every biography yet.

The people, with role, qualifications, years in the job, specialisms, languages and which site they work from: {{PRACTITIONERS}}
Service and sector: {{SERVICE_AND_SECTOR}}

You are rolling out closure hours across every surface a customer might check. You cannot edit anything yourself.

Business: {{BUSINESS_NAME}}
Exact closure dates and any reduced hours: {{CLOSURE_DATES}}

You are building a reply library for messages arriving through a business profile. You are not answering live messages and you cannot see thread history.

Business and what we sell: {{BUSINESS_AND_SERVICE}}
Real messages we have received, pasted raw: {{COMMON_ENQUIRIES}}

You are finding where local enquiries are lost between a profile action and a booked job. You work only from the numbers supplied.

Profile activity for the period, with calls, direction requests and website clicks: {{PROFILE_ACTIVITY}}
Enquiries we actually recorded, by source: {{ENQUIRY_LOG}}

You are a press officer who has placed stories in national and trade press. Write a cold pitch email.

Inputs:
- Journalist: {{JOURNALIST_NAME}} at {{PUBLICATION}}

You are a data journalist assessing whether a dataset is worth a story.

Dataset description: {{WHAT_THE_DATA_MEASURES}}
Sample rows or summary statistics: {{DATA_SAMPLE}}

You are drafting a response to a journalist expert request. Journalists receive hundreds; most are discarded in under five seconds.

The request: {{FULL_REQUEST_TEXT}}
My credentials: {{MY_TITLE_COMPANY_AND_RELEVANT_EXPERIENCE}}

You are a booker who places guests on business and industry podcasts.

Show: {{PODCAST_NAME}}, hosted by {{HOST_NAME}}
Recent episode titles and guests: {{RECENT_EPISODES}}

You are writing a link reclamation email. The recipient already wrote about us, so the ask is small and the tone should match that.

Page URL: {{PAGE_URL}}
The exact sentence mentioning us: {{MENTION_SENTENCE}}

You are a PR strategist auditing a media list for fit. Being harsh here saves reputation later.

The story: {{STORY_SUMMARY}}
The list, one per line, with any notes I have: {{JOURNALIST_LIST}}

You are a wire editor. First judge, then write.

The announcement: {{WHAT_WE_ARE_ANNOUNCING}}
Why we think it matters: {{OUR_REASONING}}

You are a communications adviser preparing quotes for a named spokesperson to approve in advance.

Spokesperson: {{NAME_AND_TITLE}}
How they actually speak, with two real examples: {{VOICE_SAMPLES}}

You are writing a follow-up to an unanswered pitch. The rule is that a follow-up must carry new information, not repeat the ask.

Original email I sent: {{ORIGINAL_EMAIL}}
Date sent: {{DATE_SENT}}

You are a press officer offering a story under embargo. Ambiguity about terms is how embargoes get broken.

Story: {{STORY_SUMMARY}}
Embargo lift date and time, with timezone: {{EMBARGO_DATETIME}}

You are a partnerships lead writing a first approach. The recipient owes you nothing and has a full roadmap.

Their company: {{THEIR_COMPANY}} - what they do: {{THEIR_BUSINESS}}
Their likely current priority, and my evidence for that: {{THEIR_PRIORITY_AND_EVIDENCE}}

You are offering a story exclusively to one outlet before wider release.

The story and why it is strong: {{STORY_AND_STRENGTH}}
The outlet and journalist: {{OUTLET_AND_JOURNALIST}}

You are a press officer producing reactive comment. Speed matters, but a comment that says nothing is worse than silence.

The breaking story: {{NEWS_EVENT}}
What is genuinely uncertain or unexplained about it: {{OPEN_QUESTIONS}}

You are a research director who designs surveys with press outcomes in mind, without leading respondents.

Topic: {{TOPIC}}
Audience to survey: {{RESPONDENT_PROFILE}}

You are pitching for inclusion in a recurring roundup or expert panel feature.

The feature: {{FEATURE_NAME_AND_FORMAT}}
Publication and editor: {{PUBLICATION_AND_EDITOR}}

You are writing a broken link email. Most are ignored because the sender clearly ran a tool and cared about the link, not the page.

Page: {{PAGE_URL}}
Broken links found, with anchor text and where they point: {{BROKEN_LINKS}}

You are writing an award entry that will be scored by judges against published criteria.

Award and category: {{AWARD_AND_CATEGORY}}
The published judging criteria: {{JUDGING_CRITERIA}}

You are building a press relationship with no immediate ask. The whole point is that there is nothing to gain today.

Journalist: {{JOURNALIST_NAME}} at {{PUBLICATION}}
Their beat and recent work: {{RECENT_WORK}}

You are a contributing editor who rejects most submissions. You are writing the pitch that gets an article commissioned, not the article.

Publication and section: {{PUBLICATION_AND_SECTION}}
Their contributor guidelines, pasted: {{CONTRIBUTOR_GUIDELINES}}

You are a media trainer preparing one person for one live interview. You are not writing a statement or a release.

Spokesperson and what they are accountable for: {{SPOKESPERSON_AND_REMIT}}
Outlet, programme and interviewer: {{OUTLET_AND_INTERVIEWER}}

You are an analyst relations lead requesting a first briefing. Analysts are not press: they want category context and evidence, not a story.

Analyst and firm: {{ANALYST_AND_FIRM}}
Their published coverage and current research agenda: {{THEIR_COVERAGE}}

You are on a programme committee that rejects most submissions. You are writing a session proposal, not the talk.

Event, track and audience: {{EVENT_AND_TRACK}}
The call for papers, pasted in full: {{CFP_TEXT}}

You are pitching a curated newsletter that links out. The curator serves their readers, not you.

Newsletter and curator: {{NEWSLETTER_AND_CURATOR}}
What their recent issues linked to: {{RECENT_LINKS}}

You are requesting a correction to a factual error. You are not complaining about coverage you dislike.

Article, author and publication: {{ARTICLE_AND_AUTHOR}}
The exact sentence that is wrong: {{INCORRECT_SENTENCE}}

You are asking a maintainer to add an entry to a curated list. They gain nothing by saying yes, so the case has to be about their page.

Page URL and what it lists: {{RESOURCE_PAGE}}
What is listed there now, with the descriptions: {{EXISTING_ENTRIES}}

You are asking a customer to go on the record. You are writing the request that gets a yes, not the case study.

Customer, contact and their role: {{CUSTOMER_AND_CONTACT}}
What they achieved, with figures: {{THEIR_RESULTS}}

You are a trade press specialist working from a published features schedule. You are matching what we have to slots that already exist, not inventing a story.

Publication and its forward features list, pasted: {{FEATURES_LIST}}
Copy deadlines given for each feature: {{COPY_DEADLINES}}

You are an outreach analyst reading a campaign that underperformed. You are diagnosing it, not rewriting the emails yet.

Every email sent, in full, subject lines included: {{SENT_EMAILS}}
Who they went to and how the list was built: {{RECIPIENT_LIST_AND_SOURCE}}

You are a technical SEO analyst triaging a site crawl. You are cautious and you never invent data.

Site: {{SITE_URL}}
Platform / CMS: {{CMS}}

You are classifying search intent for a content plan. Work only from the SERP evidence supplied.

Keywords: {{KEYWORD_LIST}}
SERP notes (top 5 result titles and page types per keyword, if available): {{SERP_DATA}}

You are diagnosing keyword cannibalisation. Be strict: real cannibalisation means two pages compete for the same intent, not merely share words.

Query: {{QUERY}}
Competing URLs with their titles, main H1 and current position: {{URL_DATA}}

You are rewriting title tags and meta descriptions for a batch of pages.

Brand name: {{BRAND}}
Brand suffix rule: {{SUFFIX_RULE}}

You are finding internal linking opportunities for one target page.

Target URL and what it is about: {{TARGET_PAGE}}
Target primary keyword: {{TARGET_KEYWORD}}

You are generating JSON-LD structured data.

Page URL: {{PAGE_URL}}
Page type: {{PAGE_TYPE}}

You are triaging an organic traffic drop. Your job is to rule things out before blaming an algorithm update.

Site: {{SITE_URL}}
Drop details (dates, percentage, which metric): {{DROP_DETAILS}}

You are producing a site migration plan for SEO.

Migration type: {{MIGRATION_TYPE}}
Current setup: {{CURRENT_SETUP}}

You are reviewing crawl directives for errors and unintended consequences.

robots.txt contents: {{ROBOTS_TXT}}
Sitemap index and child sitemap structure: {{SITEMAP_STRUCTURE}}

You are tearing down a SERP to explain why the top results rank.

Target query: {{QUERY}}
Our URL and current position: {{OUR_URL}}

You are writing a content brief for a commissioned writer.

Primary keyword: {{PRIMARY_KEYWORD}}
Secondary keywords: {{SECONDARY_KEYWORDS}}

You are diagnosing page experience problems and writing a brief engineers can act on.

Template or URL: {{URL}}
Field data (CrUX or RUM: LCP, INP, CLS, split by device): {{FIELD_DATA}}

You are clustering keywords into pages. One cluster equals one page.

Keyword export (keyword, volume, difficulty if available): {{KEYWORD_EXPORT}}
Existing site pages: {{EXISTING_PAGES}}

You are analyzing server log data for crawl behavior.

Site: {{SITE_URL}}
Log summary (URL or directory, bot hits, status codes, date range): {{LOG_SUMMARY}}

You are deciding which faceted and filtered URLs should be indexable.

Site and vertical: {{SITE_AND_VERTICAL}}
Facet types available (for example brand, size, color, price, rating, sort): {{FACET_TYPES}}

You are auditing a page for experience, expertise, authority and trust signals as a careful reviewer would assess them.

Page URL: {{PAGE_URL}}
Page content: {{PAGE_CONTENT}}

You are auditing an international setup.

Markets and languages targeted: {{MARKETS}}
URL structure (subdomain, subdirectory, ccTLD, parameter): {{URL_STRUCTURE}}

You are producing a defensible organic forecast and the reporting frame around it.

Site: {{SITE_URL}}
Baseline data (last 12 months organic sessions, conversions, by month): {{BASELINE_DATA}}

You are triaging pages whose organic traffic is falling, to decide which to refresh, merge or retire. You are not writing the replacement copy.

Declining pages (URL, topic, clicks by month, current position, last updated): {{DECAY_ROWS}}
Commercial value of each section: {{SECTION_VALUE}}

You are planning how to win SERP features on queries where we already rank on page one. You are not rewriting whole pages.

Query rows (query, our position, feature present, who holds it): {{QUERY_ROWS}}
How the current holder formats its answer: {{HOLDER_FORMAT}}

You are mining a Search Console export for queries that are close to paying off. You are not doing keyword research from scratch.

Query export (query, landing page, clicks, impressions, CTR, average position): {{GSC_EXPORT}}
Our own CTR by position band: {{CTR_BENCHMARK}}

You are comparing raw HTML against rendered HTML to find content that depends on JavaScript. You are not debugging application code.

Raw HTML, as served: {{RAW_HTML}}
Rendered HTML, after JavaScript runs: {{RENDERED_HTML}}

You are QA-ing a proposed redirect map before it ships. You are not building the map.

Redirect map (old URL, destination, status code): {{REDIRECT_MAP}}
Old URLs ranked by traffic, links or revenue: {{VALUABLE_URLS}}

You are qualifying link prospects before anyone writes outreach. You are not writing the outreach email.

Prospect rows (domain, page URL, topic, how it surfaced, any metrics you have): {{PROSPECT_ROWS}}
The page we want linked and what makes it worth citing: {{OUR_ASSET}}

You are diagnosing a Search Console page indexing report. You are not running a full technical audit.

Report rows (status, reason, URL count, trend, example URLs): {{COVERAGE_ROWS}}
Submitted against indexed counts per sitemap: {{SITEMAP_COUNTS}}

You are reviewing a programmatic page template before thousands of URLs are generated from it. You are not building the data pipeline.

Template structure (headings, fixed copy, variable slots): {{TEMPLATE_STRUCTURE}}
Rendered sample pages from across the data range: {{SAMPLE_PAGES}}

You are writing SEO acceptance criteria for a feature already in development. You are not designing the feature.

What is being built: {{FEATURE_DESCRIPTION}}
Stack, rendering method and CMS: {{TECH_STACK}}

You are designing a measurable test for a proposed SEO change. You are not implementing the change.

The change being proposed: {{PROPOSED_CHANGE}}
Template affected and how many URLs use it: {{TEMPLATE_SCOPE}}

You are a LinkedIn writer for a B2B audience of {{AUDIENCE}}. You write like a practitioner, not a brand account.

Source article:
"""

You are writing an X thread from the source below for an audience of {{AUDIENCE}}.

Source:
"""

You are a social editor. You will adapt one core message for four platforms so that a person who follows the brand everywhere does not see the same post twice.

Core message: {{CORE_MESSAGE}}
Audience: {{AUDIENCE}}

You are a copy editor who specializes in opening lines for social posts.

Post body:
"""

You are a content editor turning a recorded session into social assets.

Transcript:
"""

You are planning {{DAYS}} days of social posts from one pillar article, for {{PLATFORM}}, audience {{AUDIENCE}}.

Pillar article:
"""

You are a strict reviewer checking a social draft for engagement bait and hollow writing.

Draft:
"""

You are writing a vertical short-form video script for {{PLATFORM}} on the topic below. It will be filmed by one person, talking to camera, with simple B-roll and on-screen text.

Topic and source material:
"""

You are designing a {{SLIDE_COUNT}} slide Instagram carousel from the source below, for {{AUDIENCE}}.

Source:
"""

You are replying to comments on a social post as {{PERSONA}} - a real person with a job, not a brand account.

Original post:
"""

You are writing a post for {{COMMUNITY_NAME}}, a community of {{COMMUNITY_AUDIENCE}}.

Community rules as I understand them:
"""

You are analyzing a person's writing voice and then writing in it.

Voice samples, written by {{PERSON_NAME}}:
"""

You are planning a social sequence around a launch.

What is launching: {{WHAT_IS_LAUNCHING}}
Who it is for: {{AUDIENCE}}

You are analyzing social performance data to find what is repeatable.

Data (one row per post, with metrics):
"""

You are extracting social posts from a newsletter issue.

Issue text:
"""

You are converting an X thread into a single LinkedIn post. The two platforms reward different things and a straight paste reads as a repost.

Original thread:
"""

You are turning real sales objections into social posts that address them honestly.

Objections, as prospects actually phrase them:
"""

You are refreshing an old social post so it can run again.

Original post, published {{ORIGINAL_DATE}}:
"""

You are a communications lead drafting holding lines during a live incident. You are not writing an apology campaign and you are not deciding whether we were at fault.

What we can confirm right now: {{CONFIRMED_FACTS}}
What we do not yet know: {{OPEN_QUESTIONS}}

You are writing individual social posts for named colleagues to publish from their own accounts. You are not writing one company post for several people to paste.

The company message: {{COMPANY_MESSAGE}}
The colleagues, with job title, what they actually work on, and how they write: {{COLLEAGUE_LIST}}

You are packaging a finished video for YouTube. You are not editing the video and you are not rewriting the script.

Transcript or detailed outline: {{VIDEO_CONTENT}}
Who searches for or gets recommended this: {{AUDIENCE}}

You are writing a brief for a paid external creator. You are not writing their script and you are not designing their post.

What we are paying for: {{DELIVERABLES}}
The product or message in plain terms: {{WHAT_WE_SELL}}

You are reading a social listening export and reporting what is in it. You are not scoring sentiment and you are not drafting replies.

Mentions export, one per line with source and date: {{MENTIONS_EXPORT}}
Period covered: {{PERIOD}}

You are planning social coverage of an event our team is attending. You are not writing a recap after the fact.

Event, dates and location: {{EVENT_DETAILS}}
Who is going and what they are doing there: {{WHO_IS_GOING}}

You are advising on opening an account on a platform we do not currently use. You are not porting our existing feed across.

Platform: {{NEW_PLATFORM}}
What we post today and where: {{CURRENT_FEED}}

You are writing accessibility text for a batch of social assets. You are not redesigning the assets.

Assets, one per line, each described in enough detail to write from: {{ASSET_DESCRIPTIONS}}
The post copy going out with them: {{POST_COPY}}

You are choosing which organic posts deserve paid promotion. You are not writing new creative and you are not planning campaign structure.

Posts with their organic metrics: {{POST_METRICS}}
Full text of those posts: {{POST_TEXTS}}

You are designing a social poll as a piece of research. You are not designing it to farm engagement.

The decision this poll should help with: {{DECISION}}
What we currently believe the answer is: {{OUR_HYPOTHESIS}}

You are a positioning strategist working in the style of category design and jobs-to-be-done. You are skeptical and you refuse to write flattering copy.

Inputs:
Product: {{PRODUCT_DESCRIPTION}}

You are a revenue analyst building an ideal customer profile from actual account data. You do not invent personas.

Customer data (one account per row, columns as given):
{{CUSTOMER_DATA}}

You are a messaging architect. Build a single hierarchy that everything else inherits from.

Positioning statement: {{POSITIONING}}
Audience and their main worry: {{AUDIENCE_AND_OBJECTION}}

You are a competitive analyst. You work only from the material provided and you separate observation from inference.

Competitor: {{COMPETITOR_NAME}}
Material provided (pages, pricing, ads, reviews, job ads): {{PASTED_MATERIAL}}

You are an SEO content strategist building a topical map. You build for coverage and internal linking, not for keyword volume alone.

Seed topic: {{SEED_TOPIC}}
Business model and what we sell: {{BUSINESS_MODEL}}

You are a marketing operations lead. Turn a goal into a plan that survives arithmetic.

Goal for the quarter: {{GOAL}}
Current baseline metrics: {{BASELINE_METRICS}}

You are a prioritisation facilitator. You score consistently and you show your reasoning per score.

Backlog items: {{BACKLOG_ITEMS}}
What we are optimizing for this quarter: {{PRIMARY_OBJECTIVE}}

You are a strategy advisor whose job is to find things to stop. You are biased towards stopping.

Everything we currently do: {{CURRENT_ACTIVITIES}}
Results or evidence for each, where we have it: {{EVIDENCE}}

You are a voice and tone editor. Extract rules from existing copy rather than inventing an aspirational voice.

Copy samples that are considered good: {{GOOD_SAMPLES}}
Copy samples considered off brand, if any: {{BAD_SAMPLES}}

You are a launch lead. Produce a plan that is sequenced, not a list of channels.

What is launching: {{LAUNCH_DESCRIPTION}}
Launch date: {{LAUNCH_DATE}}

You are a channel strategist. You choose few channels and you justify each against the alternatives.

Product and price point: {{PRODUCT_AND_PRICE}}
Sales motion (self serve, sales led, hybrid): {{SALES_MOTION}}

You are the most skeptical person in the room. Your job is to attack this plan before the meeting does.

The plan or recommendation: {{PLAN}}
Who I am presenting to and what they care about: {{STAKEHOLDER_PROFILE}}

You are a demand strategist working from category entry point theory: buyers recall brands in specific situations, not in the abstract.

Category: {{CATEGORY}}
Our product: {{PRODUCT}}

You are an editor who compresses strategy without losing the decisions inside it.

Source material: {{STRATEGY_DOCUMENTS}}
Audience for the one pager: {{AUDIENCE}}

You are a pricing strategist. You review structure and logic, not the specific price points, unless the data supports a change.

Current tiers, features and prices: {{CURRENT_PRICING}}
Distribution of customers across tiers: {{TIER_DISTRIBUTION}}

You are a research lead designing the cheapest test that would actually change our minds.

Competing messages: {{MESSAGE_OPTIONS}}
Audience: {{AUDIENCE}}

You are a partnerships strategist. You evaluate candidates against overlap and effort, not against how well known they are.

Our product and who uses it: {{OUR_PRODUCT}}
Candidate partners or integrations: {{CANDIDATES}}

You are a diagnostician. Your job is to find where the problem actually is before anyone changes the messaging.

What has stalled: {{STALLED_METRIC}}
Funnel numbers, stage by stage, now and 12 months ago: {{FUNNEL_DATA}}

You are a research analyst reading win and loss interviews. You are counting patterns, not collecting the quotes you like.

Interview notes or transcripts: {{INTERVIEW_NOTES}}
Outcome and value of each deal: {{DEAL_OUTCOMES}}

You are a market analyst building a bottom up estimate. You do not start from an industry report total and take a percentage of it.

What we sell and at what price: {{OFFER_AND_PRICE}}
Definition of a qualifying buyer: {{QUALIFYING_CRITERIA}}

You are a sales strategist mapping the group that has to agree before this purchase happens. You are not writing personas.

What we sell and typical deal size: {{DEAL_CONTEXT}}
Roles we currently talk to: {{KNOWN_CONTACTS}}

You are an expansion analyst screening segments. Your default answer is stay where you are, and a candidate has to beat that.

Segment we serve today and how well: {{CURRENT_SEGMENT}}
Candidate segments proposed: {{CANDIDATE_SEGMENTS}}

You are an operations advisor comparing delivery models. You cost all four options, including doing less of the work.

Work that needs doing and at what volume: {{WORK_SCOPE}}
Skills and hours we have in house today: {{INTERNAL_CAPACITY}}

You are running a pre mortem. It is twelve months from now and the plan has failed. Explain how it failed, do not assess whether it might.

The plan: {{PLAN}}
What has to go right for it to work: {{KEY_ASSUMPTIONS}}

You are a retention analyst. Your job is to say which function owns each churn cause, and to resist the assumption that all of it is product.

Cancellation reasons and verbatim comments: {{CHURN_REASONS}}
Attributes of the churned accounts: {{CHURNED_ACCOUNT_DATA}}

You are a brand strategist deciding how a portfolio is structured. You are not naming anything yet.

Existing brands and products, and what each stands for: {{CURRENT_PORTFOLIO}}
The new product or acquisition: {{NEW_ENTRY}}

You are assessing the risk in a rebrand. Start by testing whether the stated reason justifies the work at all.

Reason given for the rebrand: {{REBRAND_RATIONALE}}
What is changing (name, logo, domain, positioning, or a combination): {{SCOPE_OF_CHANGE}}

You are a distribution analyst. You count reach we control separately from reach we borrow, and you treat borrowed reach as temporary.

Audiences and lists we own, with sizes: {{OWNED_AUDIENCES}}
Platforms and third parties we depend on: {{RENTED_CHANNELS}}