Marketing & SEO Workflows

Use when the user wants to check whether an A/B test result is statistically significant, or to size a test before running it. Also use when the user mentions A/B test, split test, statistical significance, p-value, confidence level, conversion lift, sample size, or "is this result real / can we call the test." Produces lift, p-value, a significance verdict, and required sample size.

Use when starting work on a brand or product with the AAJ skills, or when any skill needs context about the business that isn't available yet. Also use when the user mentions onboarding, "set up my brand," brand brief, company context, who we are, our ICP, our positioning, brand voice, or "tell the agent about my business." Produces a structured .agents/product-marketing.md brief — company, product, ICP, positioning, value, voice, goals, funnel, and competitors — that every other AAJ skill reads first.

Use when the user wants to check whether content actually sounds like their brand — enforcing a defined voice across AI-generated or team-written copy at scale. Also use when the user mentions brand voice guardrails, tone consistency, on-brand/off-brand, banned words, content governance, style compliance, AI-content review, "does this sound like us", or keeping a large volume of content on-message. Checks content block by block against the brand's own do/don't rules and emits a pass/revise verdict with an audit trail.

Invoke when the user needs to plan, launch, manage, or review a marketing campaign, allocate budget across channels, set up UTM tracking, design a media plan, or conduct a campaign post-mortem.

Use when the user wants to write a cold outbound email sequence — the multi-touch cadence that opens conversations with target accounts. Also use when the user mentions cold email, outbound sequence, email cadence, prospecting emails, sales outreach, follow-up emails, break-up email, or "emails that get replies." Produces a 4–6 touch cold email sequence with subject lines, send timing, and one clear ask per email, grounded in the prospect's pain.

Use when the user wants to plan a content calendar or editorial strategy — topic clusters, cadence, formats, and a repurposing plan across channels. Also use when the user mentions content calendar, editorial calendar, content strategy, topic clusters, pillar content, content cadence, or "what should we publish and when." Produces a structured calendar with clusters, schedule, and a repurposing flow.

Use when the user wants to design a customer or market survey — choosing the questions, structure, scales, and sample size to get unbiased, decision-useful answers. Also use when the user mentions survey, questionnaire, NPS, customer feedback, market research survey, product-market fit survey, sample size, margin of error, "how many responses do I need," or "what should I ask my customers." Produces a structured survey with unbiased questions mapped to decisions, plus computed sample-size, invite, and segment-readability numbers from a runnable engine.

Use when the user wants a discovery call structure or question bank — how to run a first sales call that qualifies and uncovers real pain. Also use when the user mentions discovery call, sales call script, qualifying questions, sales questions, needs analysis, first call, demo call, or "what should I ask on a sales call." Produces a discovery call flow with a prioritized question bank, qualification checks, and next-step language that advances the deal.

Use when the user wants to build or fix lifecycle email — welcome sequences, onboarding emails, nurture, win-back, expansion, or re-engagement. Also use when the user mentions email sequences, drip campaigns, automated emails, lifecycle marketing, email flows, or "what emails should we be sending". Maps which sequences exist, checks the combined send load for fatigue, and writes the sequences that are missing.

Use when the user wants to measure or monitor whether AI answer engines actually name and cite their brand over time — not whether a page is optimized, but what the engines are saying right now. Also use when the user mentions AI share of voice, LLM citation tracking, brand visibility in ChatGPT/Perplexity/Claude/AI Overviews, "are we showing up in AI answers", answer-engine monitoring, or wants to prove GEO work moved the needle. Designs the prompt set, scores the run, and says whether a change between runs is signal or noise.

Use when the user wants to optimize content so it gets cited by AI engines (ChatGPT, Perplexity, Claude, Google AI Overviews) and wins answer-engine snippets — i.e. GEO (generative engine optimization) and AEO (answer engine optimization). Also use when the user mentions AI citations, getting quoted by LLMs, llms.txt, answer-first content, featured snippets, or "make this content rank in AI answers." Rewrites/augments a page to maximize citation likelihood.

Use when the user wants to know whether marketing spend actually caused conversions, rather than just preceded them — incrementality testing, holdout or geo tests, iROAS, or media mix modelling. Also use when the user mentions incrementality, holdout test, geo test, lift test, iROAS, incremental CAC, MMM, "is this channel actually working", or doubts about attributed conversions. Designs the test, sizes it, then reads it out honestly — including whether it was ever powerful enough to answer the question.

Use when the user wants to plan or spec a landing page before building it — structure, copy, sections, and conversion elements. Also use when the user mentions landing page brief, page wireframe, "what should go on this page", page outline, or wants a build-ready spec for a designer, developer, or page builder. Produces a section-by-section brief with copy direction and CTAs.

Use when the user wants to reduce churn, improve retention, or grow net revenue retention (NRR) through onboarding, lifecycle communication, and account expansion. Also use when the user mentions churn, retention, NRR/GRR, net dollar retention, activation, onboarding, customer lifecycle, upsell/expansion, or "why are customers leaving / how do we keep them." Produces churn, NRR, GRR, quick-ratio and lifetime math plus a diagnosis and a prioritized retention plan across onboarding, churn drivers, and expansion.

Use when the user wants to set or sanity-check a total marketing budget — how much to spend overall, as a percentage of revenue, by company stage and business model — and split it across brand, demand gen, content, and tooling. Also use when the user mentions marketing budget, % of revenue on marketing, how much should we spend on marketing, or budget allocation across functions. Produces a recommended budget and a function-level split.

Use when the user wants to build a board-ready marketing report, a KPI dashboard, or a monthly/quarterly performance review — turning raw funnel, spend, and pipeline numbers into metrics and a narrative leadership can act on. Also use when the user mentions marketing reporting, KPI dashboard, board deck, marketing metrics, funnel conversion, CAC or ROI reporting, attribution narrative, or "what do I show the board / how is marketing performing." Produces a full-funnel KPI snapshot (stage conversion, CAC, efficiency, attainment) with period-over-period deltas and a decision-focused narrative.

Use when the user wants to improve product onboarding, activation rate, or time-to-first-value — getting new signups to the moment the product actually works for them. Also use when the user mentions activation, aha moment, time-to-value, first-run experience, product onboarding, user adoption, or "people sign up and never come back". Defines the activation moment from data, finds where new users stall, and specifies the fix.

Use when the user wants to plan, split, or optimize a paid advertising budget across channels (Google, Microsoft, LinkedIn, Meta, TikTok, YouTube, Amazon, Capterra/G2, and more) to hit a CAC target or a customer goal. Also use when the user mentions ad budget allocation, channel mix, media plan, paid spend split, CAC target, marginal CAC, diminishing returns, or "how should I split my ad spend." Produces a defensible per-channel allocation with projected customers, blended CAC, LTV:CAC, payback, and pacing.

Use when the user wants to forecast sales or check pipeline health — whether there's enough pipeline to hit the number and what's likely to close. Also use when the user mentions sales forecast, pipeline coverage, weighted pipeline, quota attainment, pipeline gap, commit vs best case, coverage ratio, or "will we hit our number." Produces a weighted forecast (commit vs best case), a pipeline coverage ratio against the target, the gap, and how much new pipeline is needed.

Use when the user wants to design or fix their sales process — the stages a deal moves through, what has to be true to advance, and what each side does. Also use when the user mentions sales process, sales stages, pipeline stages, deal stages, exit criteria, sales playbook, qualification, MEDDIC, BANT, or "our pipeline is messy." Produces a defined stage-by-stage sales process with entry triggers, verifiable exit criteria, owner actions, and a fitting qualification framework.

Use when the user wants to audit a web page or site for SEO, GEO (generative- engine / AI citation readiness), and AEO (answer-engine / featured-snippet readiness). Also use when the user mentions SEO audit, AI search visibility, getting cited by ChatGPT/Perplexity/Claude, featured snippets, llms.txt, schema, crawlability, or "why don't we show up in AI answers." Produces a 0–100 score across 5 weighted categories, a grade, and prioritized fixes.

Use when the user wants to improve a signup, registration, trial-start or checkout flow — reducing form fields, cutting steps, or fixing where people abandon. Also use when the user mentions signup conversion, form abandonment, trial start rate, registration flow, checkout friction, or "people visit and don't sign up". Scores the flow's friction, ranks what to remove by what it's worth, and specifies the rebuilt flow.

Use when the user wants to build or prioritize a target account list — which accounts to go after, scored by fit. Also use when the user mentions target accounts, ICP fit scoring, account prioritization, ABM list, named accounts, tiering accounts, lead scoring by firmographics, or "who should we sell to first." Produces a fit-scored, tiered account list (A/B/C) with the scoring rationale and the signals each account matched.

Use when the user wants to audit a landing page, homepage, or website for conversion — clarity, calls to action, trust, friction, speed, and tracking. Also use when the user mentions CRO, conversion rate, "why isn't this page converting", landing page review, page teardown, or improving signups/leads. Produces a 0–100 conversion score across 6 weighted categories, a grade, and prioritized fixes.