whyashthakker/estack▌

### verify-ui - Check a UI change in a real browser before calling it done. - Starts or finds the dev server, opens the changed pages, takes screenshots at phone and desktop widths in light and dark mode, reads console errors, and looks for layout bugs that typecheck and curl miss. - Use after any change to pages, components, or styles, or when the user says "check it visually", "screenshot it", "does it look right", or "verify the UI".

### ux-review - Review a flow, screen, or piece of product copy from the user's point of view. - Checks orientation, next steps, friction, error recovery, and leaked internal details, then rewrites the copy in plain words. - Use when the user asks to improve UX, review a flow, simplify onboarding, write button or error copy, reduce friction, or asks "is this confusing".

### ste100 - Write or rewrite prose in ASD-STE100 Simplified Technical English (Issue 9) and remove AI slop. - Applies the countable STE rules (20-word procedure sentences, 25-word descriptive sentences, 6-sentence paragraphs, active voice, allowed verb forms, 3-word noun clusters, one instruction per sentence, condition before command), then a slop check built from Wikipedia's "Signs of AI writing" list, then an optional linter. - Use for docs, READMEs, runbooks, instructions, error messages, UI copy, incident reports, release notes, agent prompts and skill files, or when the user says "STE", "STE100", "ASD-STE100", "plain English", "simplify", "too wordy", "cut the fluff", "de-slop", "sounds like AI", or "make it human".

### social - Write X posts, X threads, and LinkedIn posts with a clear point of view, in the user's own voice. - Names the subject in the first line, takes a debatable side on ideas (never on people), backs it with sourced facts, keeps links in the first reply, and scores each draft before offering it. - Use when the user asks to write, draft, or plan posts for X, Twitter, or LinkedIn, or to turn a blog post, launch, or news story into social posts.

### short - Plan and script short vertical videos (YouTube Shorts, Instagram Reels, TikTok) that hold attention. - Picks a topic with a clear payoff, writes the hook for the first 2 seconds, a tight 30 to 90 second script, the first frame, on-screen text, visuals, three title options, the description, and a pinned comment. - Use when the user asks for a Short, Reel, TikTok, or vertical video script, or wants to turn a post, launch, or news story into a short video.

### explain - Explain code, a concept, a diff, or what the agent just did, in layers that match the user's level. - Starts with one plain sentence, then goes deeper only as far as needed, with a small diagram or example. - Use when the user says "explain", "what does this do", "I don't get this", "walk me through", "ELI5", "how does X work", or asks about a file, function, error, or term.

### catch-up - Brief the user on the AI news that matters to their project, not all AI news. - Reads the project (stack, models, tools, dependencies), pulls current news and trends from the explainx.ai MCP server, and keeps only items that change something for this project, each with a "so what" and an action. - Use when the user says "catch up", "what's new in AI", "what did I miss", "anything new for my stack", or asks if a recent model, tool, or release affects them.

### pick-model - Choose the right AI model for each task in a project or workflow using current prices, not memory. - Finds where models are used, groups calls by task type, compares live prices from the explainx.ai MCP server, and recommends a model per task with the cost change. - Use when the user asks "which model should I use", "this is too expensive", "cut my AI bill", "cheaper model for X", or sets up subagents, bots, or pipelines that call LLMs.

### estack - Entry point for eStack, the AI operator stack from explainx.ai. - Reads the task and routes it to the right eStack skill (explain, quiz-me, catch-up, pick-model, premortem, ship, verify-ui, ux-review, seo-geo, blog, social, short, ste100). - Use when the user types "/estack", says "estack", asks "which skill should I use", or starts a task that spans learning, building, and growing a product with AI agents.

### ship - Finish and ship a change safely. - Checks what changed, runs the project's own typecheck, lint, and tests, stages only the files this task touched, writes a short commit message, updates the changelog only for real product changes, and pushes after the user agrees. - Use when the user says "ship it", "push", "commit and push", "deploy", "we're done", or asks to update release notes.

### seo-geo - Make a page rank in Google and get cited by AI answer engines (ChatGPT, Perplexity, Gemini, Claude, Google AI Overviews). - Audits or writes the page with an answer-first structure, specific numbers with sources, FAQ and article schema, clean meta tags, internal links, and crawl access for AI bots. - Use when the user mentions SEO, GEO, AI search visibility, "rank for", "get cited by ChatGPT", schema, JSON-LD, meta tags, or indexing.

### quiz-me - Turn the work the agent just did (or a topic, file, or doc) into a short quiz so the user learns while they ship. - Asks 3 to 5 questions one at a time, grades each answer, and explains the gaps. - Use when the user says "quiz me", "test me", "did I get this", "check my understanding", or after a large change they must own and maintain.

### premortem - Run a premortem on a plan, launch, migration, or change before it ships. - Assume it already failed, list the most likely reasons, rank them by likelihood and cost, and turn the top risks into checks, guards, or a rollback plan. - Use when the user says "premortem", "what could go wrong", "stress test this plan", "is this safe to ship", or before a launch, a data migration, a pricing change, a big refactor, or anything costly to undo.

### blog - Research and write a blog post that readers trust and AI engines cite. - Reads the site's existing posts to match voice and format, researches from primary sources (and what practitioners say), writes an answer-first post with real numbers and citations, adds an FAQ, optimized images, and internal links both ways, then validates it. - Use when the user wants to write, draft, research, update, or edit a blog post or article.