Web & Frontend

rare Bundle

Publish or share an existing local HTML deck (HTML PPT / slide file) to Slidesfly to get a shareable short URL. Use ONLY when (1) a .html file already exists on disk AND (2) user mentions "publish / share / 分享 / 发布 / 传到网上 / 给我链接 / put online / 上线 / make this shareable", OR wants to manage existing Slidesfly decks (list / delete / change visibility / versions / restore / claim / login). DO NOT use this skill to generate the HTML deck. If the user wants to create a new deck, use a slide-generation skill (e.g. anthropic/slides, codex/slides, marp, reveal.js) or write HTML inline FIRST, then invoke this skill to publish the resulting file.

realraelrr Bundle

Use when an agent needs to convert local PDF, Office, spreadsheet, HTML, text, Markdown, or image files into docling-skill source.* sidecars before downstream reasoning, retrieval, wiki ingestion, or handoff.

shenhao-stu Skill

Reverse-engineer and clone one or more websites in one shot — extracts assets, CSS, and content section-by-section and proactively dispatches parallel builder agents in worktrees as it goes. Use this whenever the user wants to clone, replicate, rebuild, reverse-engineer, or copy any website. Also triggers on phrases like "make a copy of this site", "rebuild this page", "pixel-perfect clone". Provide one or more target URLs as arguments.

shopify Bundle

Implement WCAG 2.2 accessibility patterns in Shopify Liquid themes. Covers e-commerce-specific components including product cards, carousels, cart drawers, price display, forms, filters, and modals. Use when building accessible theme components, fixing accessibility issues, or reviewing ARIA patterns in .liquid files.

stevesolun Bundle

Gated micro-skill pipeline system. Auto-triggers when building, generating, or creating any multi-step output (documents, code, presentations, reports). Enforces a Scope-Plan-Build-Check-Deliver pipeline where each step has a pass/fail gate. Use this whenever the output quality matters and the task has more than one component.

wpacademy Bundle

Develop WordPress themes following official WordPress coding standards, theme review requirements, accessibility standards (WCAG 2.1 AA), and modern web development best practices. Use this skill whenever the user wants to create, scaffold, or develop a WordPress theme — including block (FSE) themes, classic themes, child themes, or hybrid themes. Also trigger when the user mentions "WordPress theme", "WP theme", "block theme", "FSE theme", "theme.json", "template parts", "style variations", "child theme", or wants to build a custom design/layout for WordPress. Even if the user just says "build me a theme for X" or "I need a theme", use this skill.

charleskozel Bundle

Autonomous penetration testing coordinator using ReAct methodology. Automatically activates when user provides a target IP or asks to start penetration testing. Orchestrates reconnaissance, exploitation, and privilege escalation until both user and root flags are captured. (project)

higashi-masafumi Bundle

高品質で記憶に残るフロントエンドUIを設計・実装するスキル。HTML/CSS/JSやReact/Vueのコンポーネント・ページ・アプリの作成/改修、レイアウト/タイポグラフィ/配色/モーション/美的方向性が重要な依頼で使用する。

dafang Bundle

Transpile React Web applications (v18+) into Taro 4.x code optimized for WeChat Mini Program. Use this skill when converting React components, pages, or utilities to Taro-compatible code with proper JSX element mapping, event handler transformation, navigation/routing conversion, and API shim layer.

tenkoh Skill

Set up Vitest testing environment for Next.js projects

mujingquan835 Bundle

制作新 PPT、演示文稿、幻灯片、汇报材料,或在“其余不变”的前提下修改已有大师 PPT 时使用。基于预置视觉主题组合页面,生成可离线打开、可在浏览器编辑的 HTML 演示,支持导出 PPTX / PDF 文件。

teo5777 Bundle

生成产品原型 / 页面流程线框图，移动端(App)与 PC(桌面 Web)两种形态。当用户想做产品原型、线框图、页面流程图、交互流程、App 原型、后台/管理系统原型、把多个页面平铺出来用箭头标注点击流转时使用。产出单文件 HTML：移动端用 iOS 标准尺寸(375×812)+Apple HIG 字号，PC 用桌面尺寸(1440×900)+更密的 Web 字号；同为极简黑白灰线框风格，内置标注系统与整页截图导出。

ufec Bundle

Complete best practices for using react-i18next and i18next in React Native / React projects. Trigger this skill when the user mentions internationalization, multilingual, i18n, i18next, react-i18next, translation files, namespace, language switching, locale, AI translation, or auto-translation. Applicable scenarios: setting up i18n architecture from scratch, namespace design for large-scale projects (10+ pages), TypeScript type-safe integration, translation file structure conventions, AI auto-translation workflows, and any i18next-related questions.

ujjwal502 Bundle

Systematic root-cause debugging for any codebase — frontend, backend, libraries, services, CLIs, browser extensions, GitHub apps, data pipelines, infra. Use whenever something is broken, failing, flaky, slow, or behaving unexpectedly - a bug report, stack trace, failing or flaky test, regression, crash, hang, memory leak, wrong output, CI-only failure, production incident, or "works on my machine". Also use when asked to add logs, add console.log or print statements, instrument a code path, or trace execution from A to Z. Replaces guess-and-patch with reproduce, trace, localize, root-cause, minimal fix, and proof.

ujjwalks Bundle

Reviews a website, landing page, or product concept through the eyes of its real buyers and reports purchase intent. Builds attribute-conditioned buyer personas, runs a synthetic panel using the SSR method, maps workflow-coverage gaps and incumbent alternatives, and returns scored segments, verbatim objections, and prioritized fixes. Use whenever the user wants a landing page, website, pricing page, or product idea reviewed from the customer's perspective, asks "would people buy this", "validate my idea", "test this concept", "how will my target audience react", wants purchase-intent or pricing feedback, a synthetic panel, focus group, or market research on a startup or product concept, or asks you to act as their customers or buyers — even if they never mention personas, surveys, or purchase intent. NOT for signal inventory or instrumentation planning: if the user asks what buying or intent signals to track, collect, or instrument, use signal-lens instead.

muthuishere-agent-skills Bundle

Manage desktop windows and monitors on macOS, Windows, and Linux. List open windows, list monitors (with which one is ACTIVE / has the FOCUSED window), move a window into a predefined zone (1A, 1B, 2A..2D), an N:M split, or absolute / monitor-relative coordinates, resize a window in place, focus a window, **bulk-apply a layout of many windows in one call (`windowctl batch`)**, and request the macOS Accessibility permission needed for move / resize / focus / batch. Trigger on: list windows, show open windows, what windows do I have, list monitors, show displays, which monitor is active, where's my cursor, which monitor has focus, move chrome to the left half, snap terminal to the right half, put slack on monitor 2, place editor in the top-right quarter, three-way / N-way split, send to external display, resize chrome to 900x700, make this window smaller, focus jira, raise window, bring app to front, apply my layout, save my arrangement, restore work mode, batch place windows, request / check accessibility perm

thanhdongnguyen Bundle

Comprehensive Ink skill for building CLI applications with React. Covers components (Text, Box, Static, Transform), hooks (useInput, useApp, useFocus), Flexbox layout, testing, and accessibility.

umbraco Bundle

Build, run, and drive the Umbraco.UI (UUI) web-component library via its Storybook. Use when asked to run/start/launch Storybook, screenshot a UUI component, drive the component library in a browser, or build/preview the components.

unshdee Skill

Evaluate a RAG or LLM app. Use when the user wants to test, score, benchmark, or catch regressions in a retrieval/RAG/LLM system, generate an evaluation/golden dataset from their docs, measure hallucination/groundedness/correctness, or gate CI on answer quality. Generates a golden set from the user's own corpus, runs LLM-as-judge plus retrieval metrics, and produces a shareable HTML scorecard.

the1812 Bundle

Bilibili-Evolved local dev server workflow. Use when working in the Bilibili-Evolved repository and needing to start the dev server, compile or watch one registry component/plugin, create a component/plugin scaffold through the dev server, reason about HTTP build-on-request versus WebSocket commands, or use DevClient during local feature development.

theplannerivan Bundle

面向社媒笔记、评论、搜索词、开放题、访谈摘录、品牌与竞品内容的定性分析工具箱。先检查数据结构与证据能力，向用户说明推荐方法、方法步骤、预期信息和边界并取得确认，再在消费者洞察、情感定位、沟通策略、品类颠覆、文化结构、消费任务与价值链、品牌关系或品牌社群路线中选择一个主方法，按需加载最多两个辅助镜头，交付来源清楚、可追溯的 Markdown 分析报告与单文件 HTML。适用于用户要求从不同规模、结构和证据角色的材料中选择合适方法、提炼洞察、比较品牌或形成策略判断；不要求用户预先懂方法或替模型做路由。

thebigyovadiaz Bundle

Formats raw weather data (current conditions + forecast, e.g. from Open-Meteo) into a markdown report and a standalone HTML report, in the same language the report was requested in, saves both to reports/, and summarizes in chat. Use when asked to write, format, or save a weather report from data that's already been fetched.

theclaymethod Bundle

Use when explaining systems, code changes, plans, or data with diagrams, charts, comparison tables, HTML pages, or slides.

theclaymethod Bundle

Route software work across Claude Code and Codex while balancing subscription quota and keeping the top-level host as a thin accountable orchestrator. Use for multi-agent planning, implementation, codebase exploration, debugging, frontend work, cross-provider delegation, optional adversarial review, Claude or Codex custom-agent setup, cross-provider command runbooks, or deciding between Fable/Opus/Sonnet/Haiku and GPT-5.6 Sol/Luna. Also use when the user asks for minions, model routing, quota-aware orchestration, task-to-pattern examples, or a Claude–Codex worker/reviewer pipeline.

thecodacus Bundle

Guidance for building programmatic videos with rendiv — a React/TypeScript framework for composing video scenes, animating with springs and interpolation, and rendering to MP4/WebM. Use when writing or modifying rendiv compositions, working with rendiv animation APIs, or setting up a rendiv project.

utooland Skill

Use when syncing upstream vercel/next.js changes into this repository's next.js submodule, especially changes under the upstream turbopack/ subtree, resolving rebase conflicts, adapting local Rust crates to upstream API changes, fixing utoo-web wasm builds, updating snapshots, or committing submodule and local follow-up fixes.

uxdudu Skill

Evaluates interfaces, components, screens, and flows against universal UX/UI principles (heuristics, UX laws, Gestalt, cognitive psychology, accessibility) and delivers concrete, prioritized improvements. Use whenever the user shares UI code, screenshots, components, or mockups and wants feedback — even if they don't use the words "critique" or "review". Also trigger when the user asks "what's wrong with this UI", "how can I improve this", "review my component", "does this look right", "give me feedback on this design", or shares any interface and asks for thoughts. Trigger for partial slices too (a single button, form, or card) — not only full screens.

themarchrain Bundle

当用户手动加载本技能后，后续所有对话均以"AI 时代硬核编程导师"模式运行。 本技能面向具有一定计算机基础的学习者，包括但不限于：前端开发（JavaScript/Vue3/React）、后端开发（Java/Spring/Go）、全栈开发等。 在 vibe-learning 模式下，AI 不代写完整代码，而是通过控制变量法、苏格拉底式引导、知识分级，帮助用户在真实项目开发中建立坚实的技术理解。

vagerent Bundle

生成交互式HTML产品原型的专家技能。当用户需要创建产品原型、UI界面原型、 可交互的HTML演示页面、产品功能展示页面，或提到"原型"、"prototype"、 "产品界面"、"UI原型"、"交互原型"、"演示页面"等时使用。

theoephraim Skill

Write and edit NMBL templates correctly — .nmbl files, <template lang="nmbl"> blocks in Vue/Svelte/Astro components, and nmbl`…` tagged literals in React/Solid/Qwik. Use whenever generating or modifying NMBL syntax. Covers the syntax, per-framework control flow, the whitespace pitfalls that cause compile errors, and how to verify output.

theplannerivan Bundle

从中文历史方案中提炼和维护 Method Wiki，或从项目 Brief、研究和分析资料出发，与用户共创策略方向与 Storyline，展开 Page Architecture，完成逐页提案文案、数字事实审计、HTML 审阅和 Markdown 交付。适用于提案、方案、竞标、策略共创、Storyline、逐页文案、历史方案方法提炼及 Wiki 增补任务。

theplannerivan Bundle

通用定量决策分析与离线 HTML 报告 Skill。用于 CSV、TSV、Excel、JSON 或结构化表格的描述、比较、时序、分群、驱动、漏斗、推断、实验和情景分析。先检查数据与决策语境，由 Agent 推荐方法、预期信息和边界并取得用户对精确方案的确认，再执行可回溯分析、判断合成和咨询式数据报告。不用于以原音意义为主的定性分析，也不在缺少识别设计时承诺因果或正式预测。

vansh-nagar Skill

Design and build a new premium button for the button grid — novelty check against ButtonsArr, technique recipes by tier (CSS shadow-stack materials, framer-motion swaps/springs, GSAP magnetic/morph, SVG-filter glass/gooey), repo conventions, and grid + registry wiring. Only use when the user explicitly runs /cool-buttons; do not auto-trigger.

vantezzen Bundle

How to use the @autoform/* packages with React Hook Form or TanStack Form to automatically generate React forms from Zod, Yup, or Joi schemas with any UI library (shadcn/ui, MUI, Mantine, Ant Design, Chakra UI). Use this skill whenever the user wants to create a form from a schema, select a form adapter, build forms with custom field components, set up fieldConfig for label/description/inputProps/fieldType, create multi-step forms, nest AutoForm instances, customize AutoForm UI components, or customize field/object/array wrappers. Trigger this skill even when the user just mentions "autoform", "auto form", "auto-form", "autoform", "schema-driven form", or "generate form from schema".

thewidlarzgroup Bundle

Use when a React Native app uses or is choosing the react-native-video library — playing/controlling video or audio, the v6 `Video` component or the v7 `useVideoPlayer`/`VideoView` player API, source/props/events (onLoad, onProgress, onEnd, paused, resizeMode, source, drm), HLS/DASH, DRM (Widevine/FairPlay, `@react-native-video/drm`), captions/tracks, Picture-in-Picture, background or lockscreen audio, fullscreen, buffering, offline/downloading, or native iOS/Android setup; also when deciding between v6 and v7 or migrating between them. Triggers on "react-native-video", "RNV", `Video`, `useVideoPlayer`, `VideoView`, and similar.

vect-g Bundle

将课程课件、作业文件（PDF、DOCX、Markdown、HTML、图片等）、课堂代码和历史答案格式转成简洁的大学生风格 Markdown 作业答案，并可由主 agent 按模块调度子代理解题与 review。Use when asked to complete course homework, read homework files in varied formats, match homework to lectures/slides/code, use methods taught in class, imitate previous hw*_solution Markdown style, create solution folders, decompose assignments across subagents, or generate necessary scripts, figures, or data files for homework submissions.