Web & Frontend

digital-stoic-org Bundle

Generate interactive HTML wireframe prototypes grounded in UX research artifacts. Translates empathy maps, JTBD, forces, journey maps, VPC, personas into nuanced interaction design — not just labels, but information hierarchy, trust patterns, friction reduction, emotional pacing. Consumes /ux-strategize output. Use when "wireframe", "prototype", "mockup", "ux wireframe", "html prototype", "interaction design".

wpank Bundle

Next.js App Router best practices — Server Components, data fetching, caching, routing, middleware, metadata, error handling, streaming, Server Actions, and performance optimization for Next.js 14-16+.

pramoddutta Skill

End-to-end testing skill using Cypress for web applications, covering custom commands, network intercepts, fixtures, cy.session, and component testing patterns.

agents-inc Bundle

Resend + React Email templates

agents-inc Bundle

WCAG, ARIA, keyboard navigation

forgeyclap Skill

Build the GLOBAL, opt-in, read-only Forge Project Registry — a cross-project index of every Forge project (status, last run, open tickets, port) plus a self-contained home-view HTML. Use when the owner wants a bird's-eye view across all their Forge projects.

barkleesanders Bundle

Render inline interactive visuals — SVG diagrams, HTML widgets, charts, and explainers — directly in the conversation. Use this skill whenever the user asks to visualize, diagram, chart, illustrate, or explain something visually, or when an explanation would genuinely benefit from a spatial/interactive diagram rather than text. Also triggers for: flowcharts, architecture diagrams, data visualizations, interactive explainers, comparison layouts, UI mockups, and any request containing 'show me', 'draw', 'map out', 'visualize', or 'diagram'. Even when the user doesn't explicitly ask for a visual, use this skill proactively when the topic has spatial, sequential, or systemic relationships that a diagram would clarify better than prose.

shinpr-claude-code-workflows Skill

Execute tasks following appropriate rules with rule-advisor metacognition

shinpr-claude-code-workflows Skill

Orchestrate full-cycle implementation across backend and frontend layers

zangxin75 Bundle

Expert frontend developer for React, Vue, Angular, and modern JavaScript/TypeScript. Use when creating components, implementing hooks, handling state management, or building responsive web interfaces. Covers React 18+ features, custom hooks, form handling, and accessibility best practices.

forgeyclap Skill

Forge playbook for full-stack apps with frontend + backend + database + auth. Use when building a complete application, web app, SaaS, CRUD app, or data-backed dashboard with a database and login — keywords: full-stack, app, SaaS, backend, API, database, Postgres, Supabase, auth, login, JWT, session, signup, CRUD, end-to-end. Coordinates frontend, backend, DB, and auth specialists across git worktrees.

devin-axis Skill

Create accurate, readable WeChat Official Account article drafts with a clear title, digest, HTML body, source links, and a reviewable call to action.

anhvu1107 Bundle

ALWAYS use this when the request matches FP TS React: Practical patterns for using fp-ts with React - hooks, state, forms, data fetching.

bartosh16 Bundle

Buduje kompletny, gotowy do wdrożenia formularz jako Google Apps Script Web App — trzy pliki do przeklejenia (Code.gs, Index.html, appsscript.json), backend na Apps Script, dane w Google Sheets, komunikacja przez google.script.run. Bezpieczeństwo backendu i deploymentu traktuje na równi z wyglądem: walidacja serwerowa, allowlisty pól zamkniętych, twarda neutralizacja formula injection, honeypot, LockService, minimalne oauthScopes, sekrety wyłącznie w Script Properties. Kończy własnym code review i werdyktem SECURITY REVIEW — PASS oraz dokładną instrukcją wdrożenia. ZAWSZE używaj tego skilla gdy użytkownik mówi: "zrób formularz w Apps Script", "formularz Google Apps Script", "Web App z formularzem", "formularz zapisujący do Google Sheets", "ankieta w Apps Script", "bezpieczny formularz firmowy", "formularz z Code.gs i Index.html", "google.script.run saveResponse", "formularz do arkusza bez Google Forms", "chcę własny formularz zamiast Google Forms", "formularz na intranet do Sheetsa", "appsscript.json z minima

jewgah Skill

Run the frontend and backend checks that CAN actually be run for the current change, then report what ran, a battle-tested score out of 100, and the checks that still need a human. Use after implementing a feature or a bugfix and before committing it: "test this", "run the tests", "did I break anything", "how solid is this change", "what still needs manual testing", "teste ça", "est-ce que c'est bien testé". Runs the repo's own tooling only, never a new framework. It reports; it never commits, pushes, or deploys.

jewgah Bundle

Verify frontend changes end to end after editing a web app, instead of manually clicking through pages. Use this whenever you have changed UI code and need to confirm nothing broke: "verify my frontend", "check the site after these edits", "did my UI break", "did my changes break anything", "make sure these routes still work", "smoke test the app", "check for console errors", "validate the pages I touched". Works with Next.js (app and pages router), React, Vite, and any local dev server. Built to be token cheap: it reads console errors and failed network requests first and writes full page state to disk, so it only pulls a snapshot or a screenshot into context when a route actually fails. Use it before saying a frontend change is done.

abramovmarketing88-byte Bundle

Запускает независимое сравнение ответов нескольких нейросетей (GPT, Gemini, DeepSeek или third) по одному маркетинговому контексту, пишет панели, scorecard «что лучше» и консенсус. Use when the user asks for сравнение нейросетей, мульти-ИИ, GPT vs Gemini vs DeepSeek, multi-ai-compare, сверить анализ моделями. Not for полный клиентский HTML-пакет без явного сравнения (client-market-plan оркестрирует этот скилл), и не замена audience/competitor/product analysis.

abramovmarketing88-byte Skill

Анализирует HTML-страницу с точки зрения современного дизайна, UX, визуальной эстетики и лучших мировых практик, затем самостоятельно улучшает дизайн. Use when the user asks to improve website/page design, redesign UI, сделать редизайн, улучшить дизайн сайта/страницы, polish UI/UX, or modernize the look of HTML/CSS frontend.

abramovmarketing88-byte Bundle

Оркестрирует клиентский маркетинговый пакет: product-analysis → audience-analysis → competitor-analysis → multi-ai-compare → market-action-plan → финальный HTML с панелями нейросетей и планом (дни/часы/ответственные). Use when the user asks for полный анализ для клиента, клиентский маркетинговый пакет, HTML-отчёт ЦА+конкуренты+план, client-market-plan, мультиагентный анализ рынка под презентацию клиенту, или прикрепляет skills/analiz. Not for одиночный анализ ЦА (audience-analysis), только конкуренты (competitor-analysis), только продукт (product-analysis), только план (market-action-plan), только сравнение моделей (multi-ai-compare), лендинги (selling-landing), или linear-orchestrator.

smukh Bundle

Reviews and repairs accessible form labeling, instructions, autocomplete, grouping, validation, error summaries, announcements, redundant entry, and authentication. Use for form, field, label, validation, error-message, autocomplete, or login accessibility work.

smukh Bundle

Audits a defined page or component state with deterministic browser evidence and explicit manual-review boundaries. Use for accessibility audits, axe scans, WCAG checks, or when asked to find accessibility barriers without yet changing source.

smukh Bundle

Reviews or repairs modal and non-modal dialog behavior, including naming, initial focus, containment, Escape, inert background, close controls, and focus restoration. Use for dialog, modal, drawer, popover-as-dialog, or focus-trap work.

smukh Bundle

Repairs confirmed accessibility findings in responsible source code and verifies the same state afterward. Use when asked to fix an accessibility issue, axe finding, keyboard failure, or accessibility regression—not for an evidence-only audit.

smukh Bundle

Reviews login, MFA, one-time codes, recovery, and reauthentication for accessible completion. Use for authentication-specific accessibility; use accessible-forms for general labeling and validation.

smukh Bundle

Reviews an interface component's native semantics, name-role-value, keyboard behavior, focus, colors, motion, target size, announcements, and disabled states. Use for design-system, component, widget, button, menu, tabs, toggle, tooltip, or interactive UI accessibility.

smukh Bundle

Converts a verified accessibility repair into the narrowest durable user-behavior test. Use after an accessibility fix or when asked for an axe, component, Playwright, keyboard-journey, or manual accessibility regression record.

smukh Bundle

Reviews charts and dashboard interactions for equivalent information access, data alternatives, filtering, and nonvisual operation. Use for data visualization accessibility when source data and chart purpose can be inspected.

smukh Bundle

Reviews native data tables and interactive grids, including sorting, editing, selection, pagination, and virtualized rows. Use for tabular-data accessibility rather than CSS layout grids.

smukh Bundle

Reviews editable comboboxes and suggestion popups, including async search, active options, selection, and dismissal. Use for autocomplete or custom select accessibility; ordinary native selects need no custom keyboard model.

yoyothesheep Bundle

Iteratively screenshot a running dev server with Puppeteer and fix UI issues until the interface matches design guidelines. Use when asked to review, polish, or QA frontend pages.

rdleclerc Bundle

Use when the user needs high-bandwidth visual communication rather than a text wall: browser-first HTML decision boards, implementation plans, questionnaires, architecture/source/code-review maps, status or incident reports, visual briefs, or interactive decision receipts for Codex/Claude coding workflows. Produces local self-contained HTML artifacts as generated views while preserving Markdown/source/ledger authority.

rdleclerc Bundle

Portable guide for creating, updating, migrating, deprecating, and evaluating Uber-style SKILL.md skills for Codex, Claude, and compatible coding agents. Use when users want to create a new general skill, update an existing skill, audit an existing skill or skill pack with read-only shape lint plus behavioral evals, migrate or purge legacy local skill-creator or skill-creator-pro aliases, add scripts/references/assets, run eval-driven skill iteration, compare with-skill vs without-skill behavior, generate an HTML review report, or tune a skill description for better triggering. For OpenClaw/Gaia/Type0/Soho-specific skills, prefer openclaw-agentic-skill-creator.

songyw2003 Bundle

Create or refresh a single, minimal HTML showcase for a previously reproduced repository. Use when Codex needs to present verified reproduction results, images, videos, conclusions, current progress, blockers, and concrete next steps in one self-contained white-background, black-text HTML file for a demo, handoff, progress review, or report.

get-convex Skill

Add a capability to the CURRENT Convex app — consults the served Convex capability catalog for always-current procedures (billing, crons, auth, agent, search, …); falls back to built-in hosting or @convex-dev component search. TRIGGER when the user runs /add, or asks to add hosting/publishing or any backend capability to an existing Convex app.

carthworks Skill

Optimises Next.js applications for Core Web Vitals, bundle size, and perceived performance. Use when building, auditing, or debugging a Next.js app's performance. Activates when the user asks about slow page loads, LCP, CLS, INP, image optimisation, SSR vs SSG vs ISR decisions, bundle analysis, or when Lighthouse scores are poor. Applies to Next.js App Router (13+) and Pages Router.

carthworks Skill

Audit web applications and websites for legal compliance, consumer trust, privacy policies, terms of service / terms & conditions, cancellation/refund policies, about & contact pages, pricing & support information, cookie consent, licensing, accessibility, and anti-dark-pattern practices. Use when auditing or preparing a site for launch, legal compliance review, privacy check, trust verification, removing dark patterns, hidden fees, fake reviews, or verifying copyright and business details. Don't use for generic backend performance tuning or non-web tasks.