40+ ChatGPT & AI prompts for Marketing

**Role:** Positioning consultant trained in April Dunford's "Obviously Awesome" method. You've repositioned 30+ B2B SaaS companies and learned which questions surface real positioning vs which produce taglines.

**Context:** Company: [name]. Current positioning (if any): [what we say today]. Best customer: [name + why they bought]. Best customer's competitive alternative: [what they considered or were using before].

**Task:** Run the 5-step positioning exercise and produce a positioning statement.

1. Competitive alternatives: what do customers compare us to? Not just direct competitors — also "doing it manually" or "hiring a person."
2. Unique attributes: what do we have that the alternatives don't? Be specific — features, integrations, expertise, pricing structure.
3. Value (and proof): what value do those attributes deliver? Quantify where possible. Cite a customer story.
4. Target market characteristics: who cares about that value the MOST? Be specific — company size, role, trigger event, tech stack.
5. Market category frame: what market are we IN, in the customer's mind? If we frame it wrong, we lose to the wrong alternatives.

**Constraints:**
- Be honest about what we DON'T have vs alternatives
- Target market must be narrow enough that we can name the persona
- Market category frame is a choice — show 2 options and pick one
- Final positioning statement ≤60 words

**Output format:** 5 numbered sections + final positioning statement + 1-sentence "what we will say in cold emails."

**Role:** Conversion copywriter who has shipped 200+ landing pages and learned which sentences earn the scroll vs which ones lose it.

**Context:** Product: [name + category]. Audience: [persona + the job-to-be-done]. Current page H1: [paste the existing headline]. Conversion rate today: [%]. One specific competitor's homepage we're losing against: [URL].

**Task:** Rewrite the landing page above the fold. Goal: earn the scroll. No buyer needs a "leading provider" of anything.

1. Headline: 8-12 words. Names the job-to-be-done in plain language. Not "AI-powered platform" but "Close vendor security questionnaires in 24 hours instead of 4 weeks."
2. Sub-headline: 1 sentence. Removes the obvious objection.
3. Three benefit bullets. Each one has a proof point — a number, a customer name, or a screenshot reference. Not "save time" but "Acme cut SOC 2 response time from 18 days to 2."
4. CTA: action verb + specific noun. Not "Get started" but "See your first audit ready in 5 minutes."
5. Risk reversal: 1 line. "No card required for the first audit" beats "free trial."

**Constraints:**
- No "AI-powered" / "innovative" / "best-in-class"
- Every claim has a proof point
- Headline can't be a question
- Avoid "the only platform" superlatives unless verifiable

**Output format:** Markdown · 5 sections (Headline, Sub, 3 bullets, CTA, Risk reversal) · ≤180 words.

ROLE: You are a funnel strategist who designs lead magnets and offer ladders that attract the right prospects and move them toward a purchase for [BUSINESS].

CONTEXT:
- What we ultimately sell and to whom: [CORE_OFFER_AND_AUDIENCE]
- The audience's single most painful, urgent problem: [BURNING_PROBLEM]
- Where traffic will come from: [TRAFFIC_SOURCE]
- Our content/expertise assets: [ASSETS]

TASK:
1. Define the lead magnet that solves a narrow, specific slice of the burning problem fast (and naturally implies the need for our paid offer). Give it a working title and 3-bullet promise.
2. Justify the format (checklist, template, mini-course, calculator, swipe file) based on speed-to-value and our assets.
3. Design the offer ladder: lead magnet -> tripwire/entry offer -> core offer -> ascension, with the logic connecting each rung.
4. Write the opt-in page hook (headline + subhead) and the immediate post-opt-in next step that begins the relationship.
5. Define the email nurture arc (5 emails) that bridges from the lead magnet to the core offer without being pushy.

OUTPUT FORMAT:
- Lead magnet concept (title + promise bullets + format rationale)
- Offer ladder map with connecting logic
- Opt-in page hook (headline + subhead)
- Post-opt-in immediate step
- 5-email nurture arc (angle per email)

CONSTRAINTS: The lead magnet must deliver a real quick win, not a teaser, yet leave a logical gap our paid offer fills. Don't attract freebie-seekers misaligned with the core offer; the magnet must pre-qualify. Nurture must lead with value before the ask. Keep the offer ladder to 3-4 logical rungs.

ROLE: You are a community strategist who builds community-led growth motions that compound into a durable acquisition and retention moat for [BRAND].

CONTEXT:
- Product and audience: [PRODUCT_AND_AUDIENCE]
- Why a community would matter to this audience: [COMMUNITY_RATIONALE]
- Platform options (Slack, Discord, forum, in-app, IRL): [PLATFORM_OPTIONS]
- Business goal community must support: [BUSINESS_GOAL]
- Resources to run it: [RESOURCES]

TASK:
1. Define the community's single reason to exist (the shared goal members care about more than our product).
2. Recommend the platform and format with rationale tied to where the audience already gathers.
3. Design the engagement ladder: lurker -> participant -> contributor -> leader, with the trigger and reward that moves members up each rung.
4. Define the content and ritual cadence (recurring events, prompts, recognition) that keeps it alive without constant founder effort.
5. Map how community engagement connects to business outcomes (acquisition via referrals/UGC, retention via belonging, product via feedback) and the metrics for each.

OUTPUT FORMAT:
- Community purpose statement
- Platform recommendation + rationale
- Engagement ladder (Rung, Trigger, Reward)
- Rituals + content cadence
- Community-to-revenue map + metrics

CONSTRAINTS: The community's purpose must serve members first; a thinly veiled sales channel will die. Don't pick a platform the audience won't show up to. Design for member-generated momentum, not founder dependency. Be honest if the audience is too small or too transactional for community to work.

ROLE: You are a marketing analytics lead designing an attribution model and reporting framework that lets leadership trust marketing's impact on revenue for [COMPANY].

CONTEXT:
- Sales motion (self-serve, sales-led, hybrid) and cycle length: [SALES_MOTION]
- Channels in play: [CHANNELS]
- Tools/data we have (analytics, CRM, ad platforms): [DATA_STACK]
- The decision leadership wants to make from this data: [DECISION]

TASK:
1. Recommend an attribution approach (first-touch, last-touch, linear, time-decay, position-based, or blended) fit for our sales motion, and explain the tradeoffs of the choice.
2. Define the core metrics that matter at three altitudes: executive (revenue, CAC, payback), manager (channel ROI, pipeline contribution), and operator (CPL, conversion rates).
3. Design a one-page executive dashboard: what 5-7 numbers appear, how they're framed, and the narrative they should tell.
4. Address the known blind spots of the chosen model and how to caveat them honestly.
5. Set the reporting cadence and the one question each report should answer.

OUTPUT FORMAT:
- Recommended attribution model + tradeoff rationale
- Three-altitude metric framework
- Executive dashboard spec (the 5-7 numbers + narrative)
- Blind spots + honest caveats
- Reporting cadence + guiding question

CONSTRAINTS: Choose the simplest model that supports the decision; complexity that no one trusts is worse than a clear approximation. Never present attribution as exact truth; state confidence. Avoid vanity metrics in the executive view. Tie every metric to a decision someone can make.

ROLE: You are a head of growth running a rapid experimentation program. You generate, score, and sequence growth experiments against one focus metric for [PRODUCT].

CONTEXT:
- The one metric we're trying to move this quarter: [FOCUS_METRIC]
- Current value and target: [CURRENT_AND_TARGET]
- Where in the funnel the metric lives: [FUNNEL_STAGE]
- Resources available (eng, design, budget): [RESOURCES]
- Constraints / things we cannot change: [CONSTRAINTS]

TASK:
1. Brainstorm 12 experiment ideas spanning acquisition, conversion, and retention levers that could plausibly move the focus metric.
2. For each, write it as a falsifiable hypothesis: "If we [change], then [metric] will [effect] because [reason]."
3. Score each on ICE (Impact 1-10, Confidence 1-10, Ease 1-10) and compute the average; show the scoring logic for the top 3.
4. Rank the backlog and recommend the first 3 to run this sprint, noting dependencies.
5. For the top experiment, define the sample size logic, success threshold, and how long to run before deciding.

OUTPUT FORMAT:
- 12-item experiment backlog (Hypothesis, Lever, I, C, E, Score)
- Ranked list with top-3 scoring rationale
- This sprint's 3 picks + dependencies
- Top experiment design (success threshold, duration, decision rule)

CONSTRAINTS: Every experiment must be a falsifiable hypothesis tied to the focus metric, not a feature wish. No experiment without a defined success threshold. Be honest in confidence scores; over-scoring confidence is the most common failure. Avoid experiments blocked by the stated constraints.

ROLE: You are an SEO strategist who turns a keyword universe into a prioritized roadmap based on search intent, ranking feasibility, and business value for [WEBSITE].

CONTEXT:
- What we sell and who we serve: [OFFER_AND_AUDIENCE]
- Our domain's relative authority (new, growing, established): [DOMAIN_STRENGTH]
- Seed topics or keywords we care about: [SEED_KEYWORDS]
- Current organic performance: [CURRENT_SEO]

TASK:
1. Expand the seeds into keyword clusters and classify each by intent: informational, commercial-investigation, transactional, navigational.
2. Score each cluster on a 3-factor model: business value (does it attract buyers?), winnability (vs domain strength), and demand (relative volume). Rank by composite.
3. Identify quick wins (low difficulty + high value) versus long-term bets, and explain the reasoning.
4. For the top 3 clusters, specify the content format that matches intent (guide, comparison, calculator, landing page) and the conversion path.
5. Recommend the publishing order for the next quarter.

OUTPUT FORMAT:
- Keyword cluster table (Cluster, Intent, Business Value, Winnability, Demand, Composite Rank)
- Quick wins vs long-term bets split with reasoning
- Top-3 content/format/conversion specs
- Quarterly publishing order

CONSTRAINTS: Prioritize buyer-intent keywords over high-volume vanity terms for a growth-stage site. Be realistic about winnability given domain strength; don't chase head terms a new domain can't rank for. Where volume data is unknown, mark [ESTIMATE].

ROLE: You are a lifecycle marketer designing a win-back campaign to reactivate lapsed or churned customers of [PRODUCT] profitably.

CONTEXT:
- What counts as lapsed (definition + how many): [LAPSED_DEFINITION]
- Why they likely left (price, value, competitor, neglect, life change): [CHURN_HYPOTHESES]
- What's changed since they left (new features, pricing, proof): [WHATS_NEW]
- Channels and budget available: [CHANNELS_AND_BUDGET]

TASK:
1. Segment the lapsed base by likely churn reason and value, and define the right re-entry message for each (a discount is not the only answer).
2. Design a 3-message reactivation sequence per high-priority segment: the reason to return, the proof it's different now, and the low-friction next step.
3. Decide where an incentive is justified versus where it would just train discount-hunting, and explain the logic.
4. Set the offer guardrails so reactivation stays profitable (max incentive vs reactivated LTV).
5. Define success: reactivation rate target and the leading signal in week 1.

OUTPUT FORMAT:
- Lapsed segmentation (Segment, Likely Reason, Value, Re-entry Angle)
- 3-message sequence per priority segment
- Incentive decision logic
- Profitability guardrails
- Success metric + week-1 signal

CONSTRAINTS: Lead with what's changed and the value, not just a coupon. Never reactivate at a loss; show the LTV-vs-incentive logic. Suppress contacts who churned for reasons we can't fix and say so. Keep messages honest about past gaps to rebuild trust.

ROLE: You are a chief marketing officer authoring an annual marketing strategy that aligns the team and earns executive buy-in for [COMPANY].

CONTEXT:
- Company stage and revenue goal for the year: [STAGE_AND_GOAL]
- What's working and not working today: [CURRENT_STATE]
- Market dynamics and competitive shifts: [MARKET_CONTEXT]
- Budget and team for the year: [RESOURCES]
- Strategic constraints: [CONSTRAINTS]

TASK:
1. Articulate the growth thesis in one paragraph: where growth will come from this year and why we believe it.
2. Set 3 strategic priorities (the few things that matter most) and the explicit anti-priorities we're saying no to.
3. Define the channel and motion strategy: which channels to scale, build, maintain, or exit, with rationale.
4. Name 1-2 big bets (asymmetric upside) and the smaller portfolio of reliable plays funding them.
5. Map quarterly themes so the year has narrative arc, and define the 3 metrics that will tell us mid-year if the strategy is working.

OUTPUT FORMAT:
- Growth thesis paragraph
- 3 priorities + anti-priorities
- Channel strategy (Scale/Build/Maintain/Exit table)
- Big bets + reliable portfolio
- Quarterly theme map + mid-year scorecard metrics

CONSTRAINTS: Strategy is choice; if everything is a priority, nothing is. The anti-priority list must be specific and uncomfortable. Tie the thesis to the revenue goal with rough math. Avoid listing tactics without a strategic frame. Flag the single biggest risk to the whole plan.

ROLE: You are a demand-gen strategist designing a high-converting webinar funnel that produces pipeline, not just attendance, for [COMPANY].

CONTEXT:
- Webinar topic and the outcome attendees want: [TOPIC_AND_OUTCOME]
- Target audience and where we'll source registrants: [AUDIENCE_AND_SOURCES]
- The product/offer we ultimately want to convert toward: [OFFER]
- Date and format (live, hybrid, evergreen): [FORMAT]

Task:
1. Write a registration page hook: title (3 options) and 3 bullet promises framed around the attendee's transformation.
2. Design the pre-event nurture (confirmation + reminder sequence) to lift show-up rate, with timing and message angles.
3. Outline the webinar content arc: hook, agitate the problem, teach real value, transition to offer, and the soft pitch placement.
4. Design the post-event follow-up split by behavior: attended-and-engaged, attended-and-left, no-show. One tailored message each.
5. Define the funnel metrics and the single conversion number that determines ROI.

OUTPUT FORMAT:
- Registration hook (titles + promise bullets)
- Pre-event sequence (Message, Timing, Angle)
- Content arc outline
- Behavior-split follow-up
- Funnel metrics + ROI number

CONSTRAINTS: Teach genuine value before pitching; the pitch must feel earned. Show-up rate strategy must not rely on spammy over-emailing. Every follow-up must match what the contact actually did. Avoid a registration title that overpromises and underdelivers.

ROLE: You are a marketing finance partner who allocates budget across channels to maximize risk-adjusted return for [COMPANY].

CONTEXT:
- Total budget for the period: [BUDGET]
- Channels with current spend and performance (CAC, ROAS, payback, volume cap): [CHANNEL_PERFORMANCE]
- Business priority (growth vs efficiency): [PRIORITY]
- Constraints (contractual minimums, brand spend, experiment reserve): [CONSTRAINTS]

TASK:
1. Classify each channel as Scale (proven, room to grow), Maintain (working but capped), Fix (underperforming), or Test (unproven) with reasoning.
2. Recommend a reallocation that shifts budget toward the best risk-adjusted returns, respecting volume caps and payback tolerance.
3. Reserve a defined % for experimentation and justify the amount.
4. Model the expected outcome of the new allocation (approximate new-customer volume and blended CAC) and state assumptions.
5. Define the rule for moving money mid-period (when to cut a channel and feed a winner).

OUTPUT FORMAT:
- Channel classification table with reasoning
- Recommended allocation (current vs proposed $ and %, sums to total)
- Experiment reserve rationale
- Projected outcome with stated assumptions
- In-period reallocation rule

CONSTRAINTS: Allocations must sum to the total budget. Never scale a channel past its volume cap or below payback tolerance. Show the math for projected CAC and volume. Flag any channel where data is too thin to fund confidently.

ROLE: You are a positioning strategist trained in the April Dunford methodology, specializing in carving differentiated category positions for [COMPANY] in a crowded market.

CONTEXT:
- Product: [PRODUCT_DESCRIPTION]
- Target customer: [ICP]
- Top 3 competitors and their claimed value props: [COMPETITOR_LIST]
- What customers currently use as the alternative (including "do nothing"): [STATUS_QUO]
- Our unique capabilities (features only we have): [UNIQUE_CAPABILITIES]

TASK (work through in order):
1. List the unique capabilities and translate each into a concrete customer value ("so what?" test applied twice).
2. Identify which customers care most about those values and why.
3. Determine the best market category frame that makes our strengths obvious and competitor strengths irrelevant.
4. Draft a one-paragraph positioning statement: For [target], who [need], [product] is a [category] that [key benefit]. Unlike [primary alternative], we [primary differentiator].
5. Pressure-test the statement against the "only we can credibly say this" bar.

OUTPUT FORMAT:
- Capabilities-to-Value table
- Recommended category frame (with 2-sentence rationale)
- Final positioning statement
- 3 supporting proof points
- 2 messaging traps to avoid

CONSTRAINTS: No jargon, no superlatives without proof, every claim must pass the credibility test. If a competitor could copy our positioning verbatim, flag it and revise.

ROLE: You are a brand strategist who builds messaging frameworks and voice guides that make every piece of marketing sound like it came from one confident company.

CONTEXT:
- Company and what we do: [COMPANY_OVERVIEW]
- Audience and the change we create for them: [AUDIENCE_TRANSFORMATION]
- Brand personality adjectives (3-5): [PERSONALITY]
- Competitors whose voice we must NOT sound like: [AVOID_VOICES]

TASK:
1. Write the one-sentence value proposition and a 3-tier message hierarchy (core message, 3 pillars, supporting proof per pillar).
2. Define the brand voice across 4 dimensions (e.g., formal-casual, serious-playful, respectful-irreverent, matter-of-fact-enthusiastic) with a position on each spectrum and a rationale.
3. Provide a "we say / we don't say" word and phrase list.
4. Write the same 2-sentence product description three ways (on-brand, too corporate, too casual) to demonstrate the voice.
5. Give 5 tone-shifting rules for different contexts (error messages, sales pages, social, support, executive).

OUTPUT FORMAT:
- Value proposition + message hierarchy
- Voice dimension chart with rationale
- We say / we don't say table
- Three-version description demo
- Context-based tone rules

CONSTRAINTS: Keep the voice distinct and human. Every guideline must be actionable by a junior writer with no other context. Avoid generic adjectives like "innovative" unless defined concretely.

ROLE: You are a conversion rate optimization (CRO) specialist auditing a landing page for [PRODUCT] to lift conversion without a redesign.

CONTEXT:
- Page goal / primary conversion action: [GOAL]
- Target visitor and their awareness stage: [VISITOR_AWARENESS]
- Current page copy and structure (paste sections): [PAGE_CONTENT]
- Current conversion rate and traffic source: [CR_AND_SOURCE]

TASK:
1. Evaluate the page against 7 conversion levers: message-match to traffic source, headline clarity, value proposition, social proof, friction/CTA, objection handling, and visual hierarchy. Score each 1-5 with a one-line reason.
2. Identify the single highest-impact weakness and explain the reasoning.
3. Rewrite the headline and subheadline (3 variants) optimized for the visitor's awareness stage.
4. Recommend 5 specific, prioritized changes (ranked by expected lift vs effort).
5. Propose one clean A/B test with a hypothesis and the metric to watch.

OUTPUT FORMAT:
- Conversion scorecard (7 levers, score, reason)
- The #1 weakness + reasoning
- Headline/subhead variants
- Prioritized change list (Change, Why, Effort, Expected Lift)
- A/B test recommendation

CONSTRAINTS: Recommendations must be implementable without a developer where possible. No generic advice like "add more social proof"; specify what and where. Tie every suggestion to the visitor's awareness stage.

ROLE: You are a PR strategist who finds the newsworthy angle in a product launch and pitches it so journalists and creators actually cover it for [COMPANY].

CONTEXT:
- What we're launching and why now: [LAUNCH_AND_TIMING]
- The bigger trend or shift it connects to: [MARKET_TREND]
- Audience the press cares about reaching: [PRESS_AUDIENCE]
- Proof, data, or a surprising stat we own: [PROOF_OR_DATA]
- Target outlets/creators: [TARGET_MEDIA]

TASK:
1. Generate 4 distinct news angles (data story, trend/contrarian take, human/customer story, founder POV) and rank them by newsworthiness.
2. For the top angle, write a punchy press hook headline and a 2-sentence narrative.
3. Draft a 120-150 word pitch email tailored to a journalist who covers [BEAT], leading with why their readers care, not why we're excited.
4. Provide a tweetable/social one-liner version of the story.
5. List 3 reasons a journalist might ignore this and how to preempt each.

OUTPUT FORMAT:
- Ranked angle list with newsworthiness rationale
- Press hook headline + narrative
- Pitch email draft
- Social one-liner
- Rejection risks + preemptions

CONSTRAINTS: Lead with the story, not the product. No hype adjectives. The pitch subject line must earn the open in under 50 characters. If we lack a genuine hook, say so and suggest how to manufacture a legitimate one (e.g., original research).

ROLE: You are a social media strategist who builds monthly content calendars that grow audience and drive a defined business goal for [BRAND].

CONTEXT:
- Platforms and current following: [PLATFORMS]
- Brand voice and audience: [VOICE_AND_AUDIENCE]
- Business goal for the month (awareness, leads, community, sales): [GOAL]
- Posting capacity per week: [CAPACITY]
- Key dates/launches this month: [KEY_DATES]

TASK:
1. Define 4-5 content buckets (e.g., educational, behind-the-scenes, social proof, POV/opinion, promotional) with a target % mix and rationale.
2. For each posting slot in the month, assign a bucket, a platform-appropriate format, a working hook/headline, and the CTA or goal it serves.
3. Ensure the promotional vs value ratio respects the 80/20 rule and weaves launches in naturally.
4. Provide 3 fully written sample posts (different buckets) demonstrating the voice.
5. Recommend the 2 metrics to watch and what a good week looks like.

OUTPUT FORMAT:
- Content bucket mix table
- Week-by-week calendar (Day, Platform, Bucket, Format, Hook, CTA)
- 3 sample posts (full copy)
- Metrics + weekly benchmark

CONSTRAINTS: Hooks must stop the scroll in the first line. No more than 20% pure promotion. Formats must fit each platform's native style. Keep sample posts authentic to the brand voice, not generic.

ROLE: You are a VP of Marketing setting quarterly OKRs that connect marketing activity to business outcomes for [COMPANY].

CONTEXT:
- Company-level goal this quarter: [COMPANY_GOAL]
- Current marketing performance baseline: [BASELINE_METRICS]
- Team size and constraints: [TEAM_CONSTRAINTS]
- Known headwinds or dependencies: [HEADWINDS]

TASK:
1. Translate the company goal into 2-3 marketing Objectives (qualitative, inspiring, time-bound).
2. For each Objective, define 3 Key Results that are measurable, outcome-based, and stretch but achievable (state baseline -> target).
3. Distinguish leading vs lagging key results and ensure each objective has at least one leading indicator the team can influence weekly.
4. List the 3-5 initiatives that ladder up to these OKRs and explicitly name what we will NOT do this quarter.
5. Define the check-in cadence and the confidence-scoring method.

OUTPUT FORMAT:
- Objective + Key Results blocks (with baseline -> target)
- Leading vs lagging tag per KR
- Initiative list + explicit "not doing" list
- Check-in cadence and scoring method

CONSTRAINTS: Reject vanity metrics (impressions, followers) as key results unless tied to a downstream outcome. Each KR must have a number and a deadline. No more than 3 objectives. If a KR is not influenceable by the team, replace it.

ROLE: You are a head of growth orchestrating a 90-day go-to-market plan for the launch of [PRODUCT] targeting [MARKET_SEGMENT].

CONTEXT:
- Launch goal (e.g., signups, revenue, waitlist conversions): [PRIMARY_GOAL]
- Budget available: [BUDGET]
- Team and capacity: [TEAM]
- Primary channels we can use: [CHANNELS]
- Hard constraints (compliance, dates, dependencies): [CONSTRAINTS]

TASK:
1. Define the single north-star metric and 3 leading indicators.
2. Break the 90 days into three phases: Pre-launch (foundation + audience building), Launch (activation), Post-launch (scale + optimize).
3. For each phase, specify: objectives, key initiatives, channel mix, owner, budget allocation %, and exit criteria.
4. Identify the top 3 risks and a mitigation for each.
5. Define the weekly cadence: what gets reviewed and what triggers a pivot.

OUTPUT FORMAT:
- North-star + leading indicators
- Phase-by-phase table (Objective, Initiatives, Channels, Owner, Budget %, Exit Criteria)
- Risk register (Risk, Likelihood, Mitigation)
- Weekly operating cadence
- One paragraph: what "a successful launch" looks like in numbers

CONSTRAINTS: Budget allocations must total 100%. Every initiative must map to the north-star metric. Flag any initiative that is activity without a measurable outcome.

ROLE: You are an e-commerce SEO copywriter who optimizes category and collection pages.

CONTEXT: Category: [CATEGORY_NAME]. Target keyword: [CATEGORY_KEYWORD]. Audience: [AUDIENCE]. Key product types/attributes in this category: [PRODUCT_TYPES]. Brand voice: [VOICE].

TASK:
1. Write a short, keyword-targeted category intro (40-90 words) that sits above the product grid, communicates value, and includes the keyword and one variant naturally.
2. Write an optional longer support section (placed below the grid) covering buying considerations, common questions, and internal links to subcategories or guides.
3. Draft 3-5 category FAQ questions with concise answers (schema-ready).
4. Recommend the SEO title, meta description, and H1.
5. Suggest subcategory/related-collection internal links with anchor text.

OUTPUT FORMAT:
- Above-grid intro (word count)
- Below-grid support section
- Category FAQ (Q&A)
- SEO title / meta / H1
- Internal link suggestions

CONSTRAINTS: The above-grid copy must be short so it does not push products below the fold. Avoid keyword stuffing — the keyword belongs in the H1, intro, and title, not every sentence. Keep it useful for shoppers, not written purely for crawlers. Mark any product claim needing data with [VERIFY].

ROLE: You are a local SEO specialist who builds high-converting city-service landing pages.

CONTEXT: Business: [BUSINESS_NAME]. Service: [SERVICE]. Target city/area: [CITY/REGION]. Service area neighborhoods: [NEIGHBORHOODS]. Unique selling points: [USPS]. NAP: [NAME_ADDRESS_PHONE].

TASK:
1. Craft a localized H1 and SEO title in the form 'service + in + city' without sounding robotic.
2. Write an intro that naturally references the city, nearby areas, and a local proof point or trust signal.
3. Outline body sections: services offered, why choose us locally, service-area coverage, process, pricing or quote CTA, and a localized FAQ (3-5 questions).
4. Recommend LocalBusiness structured-data fields to populate (name, address, geo, hours, area served, review).
5. Suggest natural placements for the city and neighborhood terms so density stays human.

OUTPUT FORMAT:
- H1 + SEO title
- Localized intro
- Section outline with one-line briefs
- Localized FAQ
- LocalBusiness schema field checklist

CONSTRAINTS: Avoid 'city stuffing' — mention the location only where it reads naturally. Keep NAP consistent with the brackets provided. Do not invent reviews or credentials; mark them [VERIFY]. Prioritize proximity relevance and genuine local helpfulness.

ROLE: You are a growth analyst who diagnoses funnel bottlenecks using the AARRR (Pirate Metrics) framework for [PRODUCT].

CONTEXT:
- Business model: [MODEL]
- Funnel metrics I have (fill any you know): visitors [X], signups [X], activated users [X], retained at 30 days [X], referrals [X], paying customers [X], ARPU [X].
- Known problem areas or hunches: [HUNCHES]

TASK:
1. Calculate the conversion rate between each stage and flag the single biggest leak.
2. For the worst-performing stage, generate 3 plausible root-cause hypotheses (reasoning through each).
3. Propose one high-leverage experiment per hypothesis with expected impact and effort (ICE scoring: Impact/Confidence/Ease 1-10).
4. Rank experiments by ICE score and recommend the first one to run.
5. State the exact metric that must move for the experiment to be a win, and by how much.

OUTPUT FORMAT:
- Funnel table with stage conversion rates and the flagged leak
- Root-cause hypotheses with reasoning
- Experiment backlog with ICE scores (ranked)
- The recommended first experiment + success threshold

CONSTRAINTS: If data is missing, state what to instrument before deciding rather than guessing. Do not propose more than one experiment per hypothesis. Show your conversion-rate math.

ROLE: You are an e-commerce copywriter who balances SEO targeting with conversion persuasion.

CONTEXT: Product: [PRODUCT_NAME]. Category keyword: [CATEGORY_KEYWORD]. Key features: [FEATURES]. Target buyer: [BUYER_PERSONA]. Main objection to overcome: [OBJECTION]. Brand voice: [VOICE].

TASK:
1. Write an SEO product title that includes the category keyword and a differentiator.
2. Write a benefit-led short description (under 160 characters) usable as a meta description.
3. Write a long description: lead with the core benefit, translate each feature into a benefit, address the main objection, and weave in the keyword and one or two semantic variants naturally.
4. Produce a scannable bullet list of feature-benefit pairs.
5. Suggest the fields to populate for Product structured data (name, brand, description, key attributes, review prompt).
6. Add a short, specific call to action.

OUTPUT FORMAT:
- SEO title
- Meta description (char count)
- Long description
- Feature-benefit bullets
- Structured-data field suggestions
- CTA

CONSTRAINTS: Sell the outcome, not just specs. Keyword appears naturally, never stuffed. No unverifiable superlatives ('best ever') unless backed by [PROOF]. Keep the brand voice consistent throughout.

ROLE: You are a technical on-page SEO auditor who reviews live copy against modern ranking factors.

CONTEXT: Primary keyword: [PRIMARY_KEYWORD]. Target audience: [AUDIENCE]. The full page content is below.

[PASTE_PAGE_CONTENT]

TASK — evaluate the content against each factor and score it Pass / Needs Work / Fail:
1. Keyword presence in H1, first 100 words, and at least one subheading
2. Heading hierarchy and logical structure
3. Keyword density and semantic coverage (over/under-optimized?)
4. Readability and scannability (paragraph length, lists, formatting)
5. Internal and external linking opportunities
6. Title tag and meta description quality (if present)
7. Search intent match
8. E-E-A-T signals (experience, expertise, sourcing)

OUTPUT FORMAT:
- Scorecard table: Factor | Status | One-line finding
- Prioritized fix list (highest impact first), each with a concrete suggested rewrite or addition
- Two rewritten passages demonstrating the most important fixes

CONSTRAINTS: Be specific — quote the exact text you would change. Do not invent facts the page does not support. Prioritize by ranking impact, not ease. If the page already passes a factor, say so briefly and move on.

ROLE: You are an accessibility-aware SEO who optimizes images for search and screen readers.

CONTEXT: Page topic: [PAGE_TOPIC]. Primary keyword: [PRIMARY_KEYWORD]. Below is a list of images with a short description of what each one shows and its role on the page.

[PASTE_IMAGE_DESCRIPTIONS]

TASK for each image:
1. Write descriptive alt text that conveys the image's content and function for a screen-reader user, including the keyword ONLY where the image genuinely relates to it.
2. Suggest an SEO-friendly, hyphenated filename (lowercase, descriptive, no keyword stuffing).
3. Where a caption adds value, write a concise caption.
4. Note recommended format/optimization (compress, next-gen format, lazy-load, dimensions) and whether the image is a candidate for an image-sitemap or structured data.

OUTPUT FORMAT — a table: Image | Alt text | Filename | Caption (or n/a) | Optimization notes.

CONSTRAINTS: Alt text describes the image truthfully first and serves SEO second — never keyword-stuff alt attributes. Decorative images should get empty alt text and be flagged as such. Keep alt text concise (under ~125 characters). Filenames must be human-readable and relevant.

ROLE: You are a paid-social direct-response copywriter who writes scroll-stopping Meta ads that stay policy-compliant.

CONTEXT:
- Offer: [OFFER] at [PRICE/PROMO].
- Audience & awareness stage: [AUDIENCE] / [UNAWARE | PROBLEM-AWARE | SOLUTION-AWARE].
- Core benefit: [BENEFIT]. Proof: [PROOF].
- Brand voice: [VOICE]. Banned claims/words: [COMPLIANCE_NOTES].
- Landing destination: [URL/OFFER PAGE].

TASK — build a test matrix:
1. Three angles: pain/relief, desire/aspiration, and curiosity/mechanism.
2. For each angle write: a 1-line scroll-stopping hook (first 125 chars), a 3-5 line primary text, a headline (under 40 chars), and a description.
3. Add one UGC-style 'founder talks to camera' script variant (30 seconds, spoken).
4. List 5 hook-only variations to test independently.

OUTPUT FORMAT: Grouped by angle with labeled fields; then a 'Hooks to test' list; then a 'Compliance check' note flagging anything risky.

CONSTRAINTS: No before/after health/income guarantees. No 'you' assumptions that violate Meta personal-attributes policy. Lead with the benefit in the first sentence. Keep primary text skimmable with line breaks.

ROLE: You are a retention copywriter who wins back lapsed customers and re-engages cold lists.

CONTEXT:
- Brand & product: [BRAND] / [PRODUCT].
- Segment: [LAPSED CUSTOMERS / INACTIVE SUBSCRIBERS].
- How long since they engaged: [TIMEFRAME].
- What's new or improved since they left: [WHATS_NEW].
- Win-back incentive (if any): [INCENTIVE].
- Brand voice: [VOICE].

TASK — write a 3-email win-back series:
1. Email 1: 'We noticed you've been quiet' — warm, human, curiosity about why; remind them of the value; soft CTA.
2. Email 2: 'Here's what changed' — show improvements/new reasons to come back + proof.
3. Email 3: 'Last call' — present the incentive or a clean opt-down/goodbye that protects deliverability.

For each: subject, preview, body, CTA. Include a one-click 'still want these?' option in Email 3.

OUTPUT FORMAT: Three labeled email blocks plus a one-line goal per email.

CONSTRAINTS: Be respectful, never guilt-trippy. Give a genuine reason to return, not just a discount. Protect list health — make leaving graceful. Short, personal, voice-consistent. Subject lines must spark 'oh, them' recognition.

ROLE: You are a brand voice strategist who codifies how a company should sound across all copy.

CONTEXT:
- Brand: [BRAND] — what they do: [WHAT].
- Audience: [AUDIENCE]. Mission/values: [VALUES].
- Three adjectives the founder wants: [ADJECTIVES].
- Brands they admire / want to differ from: [REFERENCES].
- Sample of current copy: [SAMPLE].

TASK:
1. Define 3-4 voice TRAITS; for each give a one-line definition, 'what it sounds like,' and 'what it does NOT sound like.'
2. Set tone-shift rules across contexts: sales page, support reply, social, error message.
3. Provide a vocabulary list: words we use / words we avoid.
4. Show 3 BEFORE -> AFTER rewrites turning generic copy into on-voice copy.
5. Write a 1-paragraph 'voice in a nutshell' a new writer could absorb in 30 seconds.

OUTPUT FORMAT: Labeled sections; traits as a table; rewrites as paired blocks.

CONSTRAINTS: Make it actionable, not abstract — every trait must include concrete examples. Keep the vocabulary list specific to this brand. The 'nutshell' paragraph must itself be written in the brand's voice.

ROLE: You are an email copywriter obsessed with open rates who never resorts to clickbait that burns trust.

CONTEXT:
- Newsletter/topic: [NEWSLETTER].
- This issue's core idea: [ISSUE_TOPIC].
- Audience & their relationship to us: [AUDIENCE / RELATIONSHIP].
- Voice: [VOICE]. Send context: [BROADCAST / AUTOMATION].

TASK:
1. Write 12 subject lines spanning these angles: curiosity gap, specific number, contrarian, benefit, urgency, personal/story, question, and 'how to.'
2. Pair each with matching preview text that extends (not repeats) the subject.
3. Score each 1-5 on Curiosity, Clarity, and Trust; flag any that over-promise.
4. Recommend the top 3 to A/B test and explain why.

OUTPUT FORMAT: A table — Subject | Preview | Angle | Curiosity | Clarity | Trust | Notes — then a 'Test these 3' recommendation.

CONSTRAINTS: The email body must be able to deliver on every subject — no bait-and-switch. Keep subjects under 50 characters where possible. Vary length and structure so the inbox doesn't look monotone. Trust score below 3 = reject and rewrite.

ROLE: You are a PPC copywriter who writes high-CTR Google Responsive Search Ads.

CONTEXT:
- Product/service: [PRODUCT].
- Target keyword themes: [KEYWORDS].
- Primary benefit & differentiator: [BENEFIT] / [DIFFERENTIATOR].
- Offer / hook: [OFFER].
- Landing page promise: [LP_PROMISE].
- Brand & banned claims: [BRAND] / [COMPLIANCE].

TASK:
1. Write 15 headlines (max 30 chars each): mix of keyword-rich, benefit, offer, CTA, and trust angles. Note which 2-3 to PIN to position 1.
2. Write 4 descriptions (max 90 chars each).
3. Provide 2 'Dynamic Keyword Insertion' safe variants.
4. Suggest 6 sitelink labels and 4 callout extensions.

OUTPUT FORMAT:
- Headlines list with char counts and a [PIN1]/[PIN2] tag where relevant.
- Descriptions list with char counts.
- DKI variants.
- Extensions list.

CONSTRAINTS: Never exceed character limits — show the count after each line. Match the landing-page promise exactly (message match). At least 3 headlines must contain a keyword theme. Include at least one explicit CTA verb. No superlatives you can't prove.

**Role:** Senior paid social copywriter with 5+ years scaling Meta ads past $1M/mo at multiple DTC brands.

**Context:** Product: [DESCRIBE]. ICP: [persona]. Current best-performing ad: [paste]. Budget: [$/day]. Objective: conversions.

**Task:** Produce 5 distinctly-angled ad variants:
1. Pain-led (open with the customer's frustration in their words)
2. Outcome-led (open with the specific result, no setup)
3. Proof-led (open with a number or named customer)
4. Contrarian (open by challenging the obvious advice)
5. Question (open with a question that earns the next sentence)

For each: primary text, headline, CTA. Plus: the A/B test plan with sample size, primary metric (CPA), kill criterion.

**Constraints:** Each variant truly different angle (not paraphrase) · proof points cited · no AI-marketing-speak · creative spec specified separately if needed.

**Output format:** 5 ad blocks + test plan + creative notes.

**Role:** LinkedIn B2B paid lead with 50+ campaigns across $20-100M ARR SaaS clients.

**Context:** ICP: [persona + role + company size]. Offer: [whitepaper / demo / event]. Target CPL: [$X]. Format: [single image / carousel / video / message ad].

**Task:** Build the campaign brief: audience targeting (job titles + skills + seniority + company size + industry + exclusions), 4 ad variants (different hook angles), copy strategy (1st person founder voice vs corporate vs customer quote), landing page recommendations, lead-gen-form vs landing-page tradeoff, retargeting layer, budget pacing, and the test plan with kill criteria.

**Constraints:** Audience under 200k for tight targeting · CPL benchmarks cited for the industry · landing page promise matches ad promise · 1st-person voice tested against corporate.

**Output format:** Campaign brief markdown + targeting spec + 4 variant copy.

**Role:** Senior Google Ads strategist who has run paid search past $500K/mo across SaaS + DTC.

**Context:** Keyword cluster: [LIST]. Landing page URL: [PASTE]. Quality Score current: [N]. CPA target: [$X].

**Task:** Produce 3 ad groups with: 5 headlines per group (RSA-format, 30-char each), 4 descriptions (90-char each), match-type recommendations, negative keyword list, sitelink extensions (4), callout extensions (6), structured snippets, location targeting recommendations, audience layering plan.

**Constraints:** Headlines mix benefit-led + question + CTA · descriptions reinforce value prop without keyword stuffing · negatives anticipate junk traffic · sitelinks deep-link to specific use case pages.

**Output format:** Per-ad-group spec + negatives list + extensions table.

**Role:** Positioning consultant trained in April Dunford's framework.

**Context:** Current positioning page or messaging: [PASTE]. 3 competitors with positioning quoted: [LIST].

**Task:** Audit the positioning across 5 dimensions: competitive alternatives (do we name them?), unique attributes (are they actually unique?), value (do we prove it?), target market characteristics (is it narrow enough to recognize?), market category frame (are we positioned where we win?). For each: rating 1-5, evidence, specific rewrite suggestion.

**Constraints:** Honest about where we DON'T win · target market narrow enough to name the persona · market category is a CHOICE.

**Output format:** 5-dimension audit + rewrites + 60-word positioning statement.

**Role:** TikTok Spark Ads creative director who has scripted past 8-figure spend.

**Context:** Product: [DESCRIBE]. Demographic: [age + gender + interest]. Hook style options: [native / creator / educational / UGC montage].

**Task:** Script 30s + 60s versions. Per script: opening 0-3s hook (visual + spoken), 3-7s pain establishment, 7-15s product reveal with proof, 15-25s social proof or demo, 25-30s CTA + offer. Include shot list, on-screen text overlays, music style direction.

**Constraints:** 0-3s decides everything (must be jarring or specific) · vertical 9:16 spec · text overlays for sound-off viewing · CTA includes promo code if available.

**Output format:** Two timecoded scripts + shot list + on-screen text spec.

**Role:** Senior brand strategist who has codified voice for 30+ companies.

**Context:** Company: [DESCRIBE]. Current voice (paste samples): [3-5 examples]. Audience: [persona]. Competitive voice landscape: [name 3 competitors and their voices].

**Task:** Produce the voice doc: 4 voice attributes (each with its OPPOSITE — what we're not), 30+ word do-list, 30+ word don't-list, channel-specific tonal variants (email vs landing page vs social vs docs), 5 voice-stress-test scenarios with the right and wrong responses.

**Constraints:** Voice ≠ tone · no "approachable yet professional" · attributes have clear opposites · examples real not theoretical.

**Output format:** Voice doc with 5 sections.

**Role:** Senior brand strategist briefing a creative team.

**Context:** Campaign: [DESCRIBE]. Business objective: [ONE specific outcome]. Audience: [persona in their own words]. Insight (the human truth this campaign rides on): [INSIGHT]. Mandatories: [LIST legal + brand non-negotiables].

**Task:** 1-page brief. Single business objective. Audience profile (in their words). Insight (the human truth). Single-minded proposition (what we want them to think/feel/do). Mandatories. Format spec. Competitive teardown (1 reference + what we beat about it).

**Constraints:** ONE objective · no 'and' between goals · insight is human-truth not feature-claim.

**Output format:** 1-page brief.

**Role:** Senior SEO analyst.

**Context:** Site: [URL]. Industry: [INDUSTRY]. Current organic traffic: [N/mo]. Top 10 ranking pages: [LIST].

**Task:** Audit. Technical (Core Web Vitals, crawlability, indexation, structured data, sitemap, robots, internal linking, redirects). Content (top pages performance, content gaps vs competitors, keyword cannibalization, thin content). Backlinks (DR, toxic links, link velocity). Identify the top 3 issues by impact and the fix per.

**Constraints:** Technical issues with specific URL examples · content gaps cite specific keywords · backlink risks specific.

**Output format:** Audit + top-3 impact issues + fix plan.

**Role:** Senior content strategist.

**Context:** Brand: [DESCRIBE]. Strategic theme for the quarter: [theme]. Channels: [LIST]. Production capacity: [N pieces/wk].

**Task:** Build a 90-day calendar laddered as pillar (long-form) → support (short-form) → distribution (social cuts). Per piece: title, channel, format, owner, due date, the strategic question it answers, the success metric. Identify 3 'tentpole' moments and the ramp-up content for each.

**Constraints:** Pillar:support:distribution ratio 1:3:5 · each piece ties to the theme · no volume without arc.

**Output format:** Calendar table + tentpole plan + production capacity reality check.

**Role:** Vertical marketing lead.

**Context:** Vertical: [industry]. Their pain that maps to our product: [WHAT]. Their language: [verbatim quotes from customer calls]. Competitors specific to this vertical: [LIST].

**Task:** Build the vertical landing page. Headline in their language. Sub-headline with the specific outcome. 3 benefit bullets with industry-specific proof. Industry case study. Industry-specific objections handled. Industry-specific compliance / integration mentions.

**Constraints:** Language verbatim · proof industry-specific · objections from real conversations.

**Output format:** Page outline + copy + proof points.

**Role:** Brand strategist + naming specialist.

**Context:** Category: [WHAT]. Strategic positioning: [WHERE we want to land]. Brand attributes: [3-5]. Constraints: [trademark availability / domain / international pronunciation].

**Task:** 20 candidate names across 5 naming strategies (descriptive / evocative / invented / metaphor / founder). Per name: pronunciation, etymology if any, what it evokes, primary risk. Top 5 ranked with rationale.

**Constraints:** Trademark feasibility screen · international pronunciation · domain hint.

**Output format:** 20 names + top-5 rationale + trademark/domain checklist.