Agents
Most decks fail for one reason: they pile up information and never answer "so what?" McKinsey trains that out of you — one idea per slide, an action title that states the takeaway, a storyline that builds to a single recommendation. This Skill turns that discipline into a clean, self-contained HTML deck: storyline structured, every headline sharpened to its point, every slide built to carry the argument. Present like the room is full of decision-makers.
At McKinsey, a recommendation was only as good as the research under it. So I learned to do it right: scope the real question, pull from independent sources, triangulate what's actually true, and ground every claim in evidence. This Skill runs that discipline for you — breaking down a question, comparing sources, verifying claims, and writing a structured report with citations you can check. Decisions on evidence, not vibes.
Paid ads advisor for performance marketers who need a diagnosis when ROAS drops, CPA spikes, or CVR falls — ranked hypotheses with confidence levels, not open-ended analysis. Routes to one of five task flows (Build / Diagnose / Decide / Report / Advise), applies the matching framework, and delivers structured output with stated assumptions. Unlike generic AI that asks 10 intake questions first, this outputs an immediate concrete deliverable — then refines with follow-up, not before.
Use when paid ads need structured angle testing or data-driven iteration — not just more copy variants. Supply platform + format + audience, pick from 8 angles (pain, outcome, proof, curiosity, comparison, urgency, identity, contrarian) — every headline char-counted, over-limit flagged and trimmed, bulk CSV included. AI gives wording variants; this skill gives structurally distinct motivations with platform spec validation built in — so every line is legal before it goes live.
A spreadsheet full of numbers isn't an answer — it's raw material. McKinsey taught me to find the number that matters: start from the decision you're making, cut to the one or two insights that change it, then say what to do. This Skill brings that eye to your data — cleaning and structuring it, surfacing the patterns and outliers worth caring about, and writing findings as clear takeaways. Analysis that ends in a decision, not a dashboard nobody opens.
Before a client spent a dollar entering a market, my job at McKinsey was to answer one question: is this real? Excitement isn't demand, and a big TAM slide isn't a market. The discipline is to size it bottom-up, segment down to who actually buys, check what they'll pay, and weigh the competition. This Skill runs that validation on your market — sizing it, separating real demand from hype, profiling the segments worth chasing, and weighing whether to enter. A decision you can defend, not a vibe.
Write B2B cold email marketing sequences that sound human — not templates — and get prospects to actually reply and book time with you. Covers first-touch emails, 6-email cadences with angle rotation, and sequence performance diagnosis — with framework selection (OPP+A, QVA, TIA), per-email subject line variants, and proactive flags for the mistakes that kill reply rates. For SDRs, founders, and sales teams doing B2B outreach to prospects who haven't opted in.
Pricing strategy for when your conversion is low, ARPU is stuck, or you're repricing and need a defensible recommendation — not a framework list. Diagnoses which of three decisions is at stake — packaging, metric, or price point — then applies the right framework and commits to specific numbers. Unlike generic AI that tours every framework, this picks what fits your situation, states a specific number, and flags what would change the answer.
Email marketing sequences for teams that need both the architecture and the copy — entry triggers, exit rules, branching, and every draft — handed off to their ESP in one output. Architecture-first: entry trigger, exit rules, suppression, and branching before a single email is written — then complete drafts for every send. Unlike tools that write emails in isolation, this outputs a deployable Sequence Spec your ESP can run, alongside the complete copy.