Loading...
Loading...
Found 755 Skills
Use this skill to design, redesign, audit, or implement substantial business websites, marketing sites, landing pages, ecommerce surfaces, editorial sites, and related web experiences. It governs product truth, content architecture, visual direction, implementation, responsive behavior, accessibility, performance, motion, SEO, and release QA. For tiny fixes, use its minimal path and load only the relevant reference module.
A portable, framework-agnostic Lighthouse CI performance-gate system for any web frontend. Enforces Core Web Vitals budgets (LCP, INP via the TBT lab proxy, CLS) and category score floors (performance, SEO, accessibility, best-practices) as a blocking CI check on every pull request. Runs Lighthouse against the production build with median-of-N runs for stability, on mobile emulation by default with an opt-in desktop form factor. Ships a single `lighthouserc.cjs` config, an npm `lhci` script, and a GitHub Actions workflow. Use this skill when adding performance gates to a project, configuring Lighthouse CI, tuning Core Web Vitals budgets, setting category score thresholds, wiring a Lighthouse GitHub Action, or debugging flaky or failing Lighthouse runs. Works with Next.js, Remix, Astro, SvelteKit, Vite, or any app that serves a production build over HTTP.
Next.js 16 portfolio with MDX blog/projects, Once UI, auto SEO, and endless theming.
Optimize Walmart Marketplace product listings for search visibility and conversion. Covers Walmart SEO, content quality scoring, rich media, and Walmart-specific listing requirements.
Audits and fixes technical SEO, researches search demand, creates content briefs, and measures SEO/AEO performance. Use when asked to "audit SEO", "fix indexing", "improve AI visibility", "check keyword volume", "write an SEO brief", or "why did organic traffic drop". For writing the article use ghostwriter; for visual redesign use ui-design.
Redesign an existing site or app without losing what already works — audits the current surface first, classifies what to preserve (brand, IA, SEO, content), picks a refresh/reskin/rebuild scope, then modernizes deliberately. Use when the user says "redesign", "modernize this site", "refresh the UI", "make this look current", or points at an existing page/URL they want improved rather than rebuilt from scratch. Invoke when the user asks for redesign on their UI, or mentions 'redesign' alongside design / UI / frontend work.
Discover, price and run AI models on Muapi (api.muapi.ai) — image, video, audio, lipsync, 3D, LLM text, SEO/data tools. Use when the user mentions Muapi or muapi.ai, asks "which Muapi model for X", "list Muapi models", "generate an image/video/song/voiceover with Muapi", wants a model's schema or price, or wants generated media saved into their project. Covers search, schema inspection, cost estimate, file upload, async submit, polling and downloading results.
Main entry for WeChat Official Account content: completes topic selection, material collection, writing, and review, and independently adds image matching, typesetting, or draft box publishing as requested by users. It is also responsible for distributing style settings, learning & revision, data review, and multi-platform rewriting to the corresponding wewrite-* modules. Trigger keywords: 公众号 (Official Account), 微信文章 (WeChat article), 微信推文 (WeChat tweet), 草稿箱 (draft box), 微信排版 (WeChat typesetting), 写公众号 (write Official Account article), 写一篇 (write an article). General articles, blogs, emails, short videos, and website SEO do not trigger this skill.
Narrow broad customer categories into specific, reachable who-where segments for customer discovery, positioning, traction tests, sales outreach, or SEO personas. Use when feedback is inconsistent, the market is too broad, personas are vague, users request too many different features, or the team does not know where to find target customers.
Bootstrap a Bun workspaces monorepo — Elysia API (one file per route group), Vite/React/Tailwind v4 web with coss UI as the base component library and lucide-react icons, Drizzle/Postgres db package, per-workspace zod-validated config/env.ts, shared zod schemas validated at both ends, shared pino logger with request correlation, Better Auth, centralized useRoutes.ts, React context-module vs hook conventions, SPA SEO via Cloudflare Worker + API share.html, bun:test, mandatory code-comment spec (file headers, doc comments, TODO/ASSUMPTION/CONFIRM tags), ESLint flat + Prettier, one-command `bun run check`, dev.sh multi-port stack, Conductor settings.toml. Use when asked to scaffold/start a new Bun monorepo, add a workspace/route/context to one, fix SPA social cards, or set up this stack.
Use when a site needs a combined accessibility and responsive-quality review: alt text, headings, keyboard use, focus, contrast, form labels, reduced motion, phone and tablet layouts, overflow, tables, dialogs, touch targets, sticky bars. It runs one shared runtime pass and routes to the accessibility and mobile specialists. Do not use it to claim WCAG conformance, to replace assistive-technology testing, or for backend or SEO work.
WeWrite Editorial Review Module: verifies tasks, factual sources, viewpoints, and practicality, directly revises drafts when necessary, and only when they meet the editorial threshold will a WeChat Official Account final draft be generated. It also responds to requests like "check this article". General code review and website SEO are not triggered.