Video style · after VoxA video-style skill that directs a short vertical video as painted pages in depth: each idea a transparent page of brush strokes on a plain warm backdrop, the main stroke carrying the material with its own soft, streaked edge as the material's only edge, smaller strokes carrying related material out of focus, and pages that step back and aside as the next arrives so the frame fills with everything said so far, gathering at the end. It fixes the rule of one page per idea, the material, a motion language, three layers, the elements and their verbs, cutting on the transcript's word timings, captions, how to make every picture from real captures with generous padding and nothing generated, and a review checklist.
Video style · after HyperplexedA video-style skill that directs a short vertical video in the manner of Hyperplexed's videos, rewritten from a frame-by-frame study of them: a near-black field where the client's own screens become glass cards floating in depth, dozens at a time, and the explanation is the cards moving — a field that drifts, a grid that tilts into perspective, a ring that turns and unwinds into a helix, one detail lifted out and enlarged, a screen shrunk into a small diagram, one small line typed word by word. It fixes the rule of one built picture per idea, the material, a motion language, three layers, eleven elements each with one verb, cutting on the transcript's word timings, captions, how to make every card from real captures with nothing AI-generated, and a review checklist. It reproduces the moves, never anyone's footage or code.
Video style · after Johnny HarrisA video-style skill that directs a short vertical video as a documentary explainer in the manner of Johnny Harris's work: real photographs cut into layers and pushed through in parallax, a dark map the camera flies into while a route draws and a pin drops, typed labels, one big kinetic line per scene, film grain in every frame and one light leak per scene on a dark warm field. It fixes the material, a motion language (one ease per job), three layers in every scene, eight elements each with one verb, a method for cutting on the transcript's word timings, caption rules, how to make every asset from photographs the client owns and open map data with nothing AI-generated on screen, and a review checklist. It reproduces the moves, never anyone's footage or photographs.
Video style · after VoxA video-style skill that directs a short vertical video as a paper collage in the manner of Vox's explainers: halftone cutouts of real people, torn screenshots of a real site, typewriter labels, ink arrows and one highlighter colour, placed on a lit paper table one element per spoken clause, with hard cuts and a slow camera drift. It fixes the material, a motion language (one ease per job), three layers in every scene, eight elements each with one verb, a method for cutting on the transcript's word timings, caption rules, how to make every asset from material the client already owns with nothing AI-generated on screen, and a review checklist. It reproduces the moves, never anyone's footage or art.
Video style · after cevox__A video-style skill that directs a short vertical video as a flat graphic reel: full colour fields from the brand's palette, one bold animated object per spoken phrase — huge type landing letter by letter, a shape morphing with misregistered ink copies, a cube that extrudes and flies apart, a halftone sphere, tangling tubes, a switch, a quarter-second icon montage — and every cut handed over by an object. It fixes the rule of one object per phrase, the material, a motion language, three layers, nine elements with their verbs, cutting on word timings, captions, drawing everything in code, and a review checklist.
Video style · after FireshipA video-style skill that directs a short vertical video as a dense technical explainer in the manner of Fireship's videos, rewritten from a frame-by-frame study of them, in two modes: the board, where one diagram owns a section and changes on every spoken clause with real clips inside its boxes, and the brief, where a literal picture (a real screen, a stack of captures, a cut-out object, a big word) lands on every line with a cut every one to two seconds. It fixes the rule of one built picture per idea, the material, a motion language, three layers, the elements and their verbs, cutting on the transcript's word timings, captions, how to make every picture from material the client owns with no memes and nothing AI-generated, and a review checklist. It reproduces the moves, never anyone's footage or material.
Agent skillThe rules every video style shares. Before building, a concept gate: name what a reference clip does rather than what is in it, write the message line, propose three concepts, and get a storyboard approved in which every frame says why it means its line. While building, the seam rules: the same axis, direction and speed across every cut, one main direction for the film, an object carrying the eye, cause and effect, and no ambient drift passed off as motion. Adapted from HeyGen's HyperFrames.
Writing voice · after Kevin KellyA blog-writing style skill that makes an AI agent write in the numbered-advice voice of Kevin Kelly: a short personal frame, then a numbered list of compressed, quotable lessons, each one to three sentences and able to stand alone, built from contrasts, reversals, rules of thumb and plain imperatives, mixing the practical with the reflective and explaining almost nothing. A second shape argues one big simple idea with arithmetic the reader can check, real examples and answered objections. It works on any business topic. The skill gives fingerprint tables for both shapes, a build, sentence rules, truth rules that require the lessons to be the user's own, a worked opening and a revision pass.
Writing voice · after Rand FishkinA blog-writing style skill that makes an AI agent write in the transparent research voice of Rand Fishkin: the headline carries the main finding and its number, a short-version summary sits at the top, charts are plain and captioned, and methodology and limitations come before any interpretation. Opinion is clearly labelled, every percentage has its denominator, and the writer's business interest is disclosed. It closes with actions and an invitation to check or reuse the data. It works on any business topic. The skill gives a fingerprint table, a seven-step build, sentence rules, truth rules that refuse to run without real data, a worked opening and a revision pass.
Writing voice · after Tim UrbanA blog-writing style skill that makes an AI agent write in the funny, illustrated deep-dive voice of Tim Urban: it takes an intimidating topic and builds it up from the simplest true idea, as a curious friend who admits what confused them, with a few invented characters or metaphors for the hard ideas, deliberately crude diagrams described with alt text, numbers turned into things you can picture, and a sincere turn near the end. 2,500 to 8,000 words, in parts when long. It works on any business topic. The skill gives a fingerprint table, a seven-step build, sentence rules, truth rules that keep the facts real while the jokes are invented, a worked opening and a revision pass.
Writing voice · after Patrick McKenzieA blog-writing style skill that makes an AI agent write in the insider-explainer voice of Patrick McKenzie: it takes a process outsiders find baffling and walks through how it really works, one actor at a time, naming what each is rewarded and blamed for, so the odd outcome turns out to be the system working as designed. Long, wry and precise, with jargon defined on first use, footnote-style asides, labelled guesses and the writer's own stake disclosed. 1,800 to 5,000 words. It works on any business topic. The skill gives a fingerprint table, a seven-step build, sentence rules, truth rules that forbid invented inside knowledge, a worked opening and a revision pass.
Writing voice · after Ann HandleyA blog-writing style skill that makes an AI agent write in the warm, practical marketing-letter voice of Ann Handley: it opens on a small real moment or a reader's question, talks to the reader as a friend who knows the craft, keeps the asides and the humour on, then turns into a handful of bold, arguable points with plain examples and Not/Instead pairs, closing on a conviction or a question and an optional P.S. It works on any business topic. The skill gives a fingerprint table, a seven-step build, sentence rules, truth rules that forbid invented anecdotes, reader questions and data, a worked opening and a revision pass. It reproduces the moves, never the writer's sentences, coinages or sign-offs.
Writing voice · after Harry DryA blog-writing style skill that makes an AI agent write in the one-example teardown voice of Harry Dry: one real, checkable piece of marketing shown first, often as a before and after, then 75 to 400 words of very short lines pointing at exactly why it works, an honest note on when it won't work for you, and one line to steal. It works on any business topic. The skill gives a fingerprint table, a seven-step build, sentence rules, strict truth rules that require a real example and a named source for every number, a complete example post and a revision pass. It reproduces the moves, never the writer's sentences, titles or examples.
Writing voice · after Ben ThompsonA blog-writing style skill that makes an AI agent write in the strategy analysis voice of Ben Thompson: it starts from a real, dated event or something the writer did, steps back into the history of the market, lays out who supplies, who distributes and who owns the customer, reads company statements critically, gives the strongest objection a fair hearing, and ends on the implication for who wins. Headed sections, first person, long analytical paragraphs broken by short ones. 1,800 to 4,000 words. It works on any business topic. The skill gives a fingerprint table, a seven-step build, sentence rules, strict truth rules for events, quotes and intentions, a worked opening and a revision pass.
Writing voice · after Julian ShapiroA blog-writing style skill that makes an AI agent write in the dense tactical handbook voice of Julian Shapiro: every sentence carries a usable idea, the core concept is named in bold and defined in one line, and the chapter moves from a principle to a framework to numbered imperative steps, with real before-and-after rewrites and a section on mistakes and exceptions. 1,500 to 4,000 words, organised to scan in two minutes. It works on any business topic. The skill gives a fingerprint table, a seven-step build, sentence rules, truth rules for examples and numbers, a worked opening and a revision pass. It reproduces the moves, never the writer's sentences, frameworks or formulas.
Writing voice · after Jason FriedA blog-writing style skill that makes an AI agent write in the blunt, calm-company opinion voice of Jason Fried: a plain title that takes a position, a first line that disagrees with something the industry takes for granted, short declarative sentences with almost no hedging, one everyday analogy carried through, the writer's own company practice as the evidence, and a short flat ending. 200 to 800 words. It works on any business topic. The skill gives a fingerprint table, a seven-step build, sentence rules, truth rules that forbid invented practices, numbers and emails, a complete example post and a revision pass. It reproduces the moves, never the writer's sentences or titles.
Writing voice · after Morgan HouselA blog-writing style skill that makes an AI agent write in the story-led behavioural essay voice of Morgan Housel: a true, specific story from another field told first and at length, a one-line pivot that turns it toward the reader, then a lesson about how people actually behave with money, risk, patience or customers, stated plainly and hedged honestly. Two shapes: one story and one lesson, or several short sections that each pair a story with a lesson. It works on any business topic. The skill gives a fingerprint table, a seven-step build, sentence rules, strict truth rules that require every story to be sourced or the user's own, a worked opening and a revision pass. It reproduces the moves, never the writer's sentences.
Writing voice · after Seth GodinA blog-writing style skill that makes an AI agent write in the ultra-short daily-post voice of Seth Godin: one idea in 70 to 350 words, a two-to-five-word title, a first line that reframes a familiar word or habit, a single contrast pair at the core, mostly one-line paragraphs, no lists, links or selling, and an ending that hands the reader a question or a choice. It works on any business topic. The skill gives a measurable fingerprint table, a six-step way to build the post, sentence rules, a complete example post and a revision checklist. It reproduces the moves, never the writer's sentences or titles, and it never licenses invented numbers or stories.
Writing voice · after Paul GrahamA blog-writing style skill that makes an AI agent write in the plain-essay voice of Paul Graham: one counterintuitive claim stated in the first two paragraphs, argued step by step in short everyday words, with honest hedges, the strongest objection answered, no headings or bullet lists, and a close that circles back to the opening. It works on any business topic. The skill gives a measurable fingerprint table, a seven-step way to build the post, sentence-level rules, a banned-word list, a worked example and a revision checklist. It reproduces the moves, never the writer's sentences, and it never licenses an invented statistic or client story.
Agent skillA five-pass review of every page one template produces — a set of service pages, tool pages or product pages — asking two questions: can a search engine index them, and can an AI answer engine lift a passage and attribute it to you? It reads the deployed HTML rather than the source, because the markdown converters behind most fetch tools strip the structured data out and a page with correct markup then reads as having none. It grades each page against a written rubric, checks whether a machine can tell the page and the organization are the same business, tests whether individual passages stand alone well enough to be quoted, and looks for the template seams nobody checks. Findings come back worst-first with the file that would fix each one. Generative engine optimization, nothing to do with geography. It changes nothing and emits no score out of 100.
Full-Stack Marketing & Technology