Web & Frontend

harzva Bundle

IEEE Visual Accessibility: color accessibility, figure readability, font size, grayscale safety, and accessibility-aware graphics.

harzva Bundle

Elsevier Component Router: detect manuscript components such as table, figure, caption, related work, method, experiment, ablation, references, declarations, and route them to the correct component skills. Use for Elsevier AI, computer vision, pattern recognition, expert systems, information science, and medical AI journals.

harzva Bundle

Elsevier Ablation Study: ablation design, component-level evidence, sensitivity analysis, and mechanism validation.

harzva Bundle

Elsevier Visual Accessibility: color accessibility, figure readability, font size, grayscale safety, and accessibility-aware graphics.

18816132863 Bundle

Convert files and office documents to Markdown. Supports PDF, DOCX, PPTX, XLSX, images (with OCR), audio (with transcription), HTML, CSV, JSON, XML, ZIP, YouTube URLs, EPubs and more.

18816132863 Bundle

Create, edit, or fix spreadsheet files (.xlsx/.xlsm/.csv/.tsv). Trigger whenever the task produces or modifies a spreadsheet — even if the user never says 'Excel'. Covers: data analysis, sorting, filtering, pivot summaries, formulas (VLOOKUP/INDEX+MATCH/SUMIFS), charts, cross-sheet references, conditional formatting, financial models, budgets, trackers, and invoices. Implicit triggers include: '帮我做个表', '整理/分析/汇总/对比数据', 'organize this data', 'build a budget', 'chart this'. More broadly, if the user asks to analyze, summarize, compare, track, or visualize data and a spreadsheet is the natural output, use this skill. Always trigger for uploaded .xlsx/.csv/.tsv files. Keywords: 表格/数据分析/汇总/对比/图表/跨表/财务/dashboard/chart. Do NOT trigger when the primary deliverable is a Word doc, HTML report, standalone script, or database pipeline.

18816132863 Skill

创建一个通过摄像头进行手势交互的网页，利用MediaPipe实时识别手势，实现对网页元素的直观操控。当需要「通过摄像头识别手势」与网页交互时使用这个Skill。

18816132863 Skill

该skill提供了很专业的html生成指导。当用户需求与html相关，请参考本skill指导。

18816132863 Bundle

统一的文档格式转换工具。 支持 Word (DOCX/DOC)、PowerPoint (PPTX/PPT)、Excel (XLSX/XLS)、PDF、Markdown (MD)、HTML 等多种格式互转。 适用场景： - 在多种格式间转换文档（HTML↔PDF、Word↔PDF、Markdown→Word 等） - 批量或单文件转换 - 支持多种格式描述方式，如 excel/xls/xlsx、doc/docx/word、md/markdown 触发方式： - 用户说 "转换文档格式"、"docx转pdf"、"html转ppt"、"excel转pdf"、"md转word" - 使用 "/xiaoyi-doc-convert <文件> <目标格式>" 格式 关键触发词： - 通用：文档转换、格式转换、doc convert、file convert - PDF：转pdf、转PDF、export to pdf、保存为pdf - Word：转word、转doc、转docx、word转换、doc转pdf、docx转pdf - Excel：转excel、转xls、转xlsx、xls转pdf、xlsx转pdf、excel转pdf、表格转pdf - PPT：转ppt、转pptx、转powerpoint、ppt转pdf、pptx转pdf、幻灯片转pdf - Markdown：md转word、md转pdf、markdown转word、markdown转pdf、md转docx、markdown转excel - HTML：html转pdf、网页转pdf、html转word、html转ppt

18816132863 Bundle

Create and present web-based slides for developers using Markdown, Vue components, code highlighting, animations, and interactive features. Use when building technical presentations, conference talks, or teaching materials.

18816132863 Skill

A designer-turned-developer who crafts stunning UI/UX even without design mockups. Code may be a bit messy, but the visual output is always fire.

cas-bigdatalab Bundle

内容解析预处理工具。读取采集后的 JSONL、JSON 或 TXT 文本记录，执行轻量内容解析，输出带标题、段落结构和内容类型的统一解析记录文件。 当用户提到接入内容解析、采集后预处理、提取标题和段落、识别 plain/markdown/html 内容结构等需求时使用此 skill。 即使用户没有明确说出"内容解析"，只要任务涉及把已采集文本内容解析成统一结构，就应该使用此 skill。 不负责文件采集、表格抽取、内容清洗、质量校验、过滤筛选或格式转换。

cas-bigdatalab Bundle

接入资源格式识别工具。读取单个文件或目录中的接入资源，识别文本、表格、文档、图像、HTML、数据或未知类型，输出带推荐处理路由的格式识别结果文件。 当用户提到格式识别、资源类型预判、采集入口分流、为文本/表格/文档/图像/HTML 选择后续处理路径等需求时使用此 skill。 即使用户没有明确说出"格式识别"，只要任务涉及在采集入口判断文件类型并分配推荐处理路由，就应该使用此 skill。 不负责读取正文内容、提取图像元信息、表格采集、文档解析、格式转换或实际执行后续处理。

cas-bigdatalab Bundle

清理文本示例中的HTML代码。当用户提到清理HTML、去除HTML标签、HTML转文本、提取网页文本等需求时使用此skill。 即使用户没有明确说出"HTML"，只要任务涉及从HTML代码中提取纯文本，就应该使用此skill。

cas-bigdatalab Bundle

指定文本片段删除工具。读取结构化数据中的文本字段，删除用户显式给出的固定片段并保留其他字段不变。 当用户提到删除固定词、固定占位符、固定水印短语、固定噪声片段等需求时使用此skill。 即使用户没有明确说出 skill 名，只要任务是按明确片段从文本字段中移除内容，就应该使用此skill。 不负责按类别自动识别 HTML、URL、emoji、数字、标点、控制字符等内容，这些应交给专用清洗 skill。

neuralblitz Skill

Expert guidance on agentic AI systems, autonomous agents, and AI orchestration. Use for: building agentic AI systems, tool orchestration, memory systems, planning and reasoning, multi-step workflows, feedback loops, evaluation frameworks, ReAct patterns, and building sophisticated AI pipelines.

microwind Bundle

当验证CSS代码时，分析CSS语法，检查样式规范，优化CSS性能。验证响应式设计，检查可访问性，和最佳实践。

microwind Bundle

当开发React组件时，设计组件架构，实现状态管理，优化性能。处理组件通信，实现复用逻辑，和最佳实践应用。

davekilleen Skill

Scrape web pages via Scrapling — stealth fetching, anti-bot bypass, CSS selectors, no API key. Use when the user says 'scrape', 'pull data from this URL', 'extract from this site'. Not for meaning-based search of the user's own vault; use `enable-semantic-search`.

davekilleen Bundle

Toolkit for styling artifacts with a theme. These artifacts can be slides, docs, reportings, HTML landing pages, etc. There are 10 pre-set themes with colors/fonts that you can apply to any artifact that has been creating, or can generate a new theme on-the-fly.

davekilleen Bundle

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

davekilleen Bundle

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

davekilleen Bundle

Suite of tools for creating elaborate, multi-component claude.ai HTML artifacts using modern frontend web technologies (React, Tailwind CSS, shadcn/ui). Use for complex artifacts requiring state management, routing, or shadcn/ui components - not for simple single-file HTML/JSX artifacts.

quantumquirkxyz Skill

Design and build extended reality (AR/VR/MR) experiences — 3D interaction, spatial computing, headset development, immersive UX — with performance, comfort, and accessibility as first-class concerns.

quantumquirkxyz Skill

Design accessible UX — keyboard navigation, focus order, semantics, contrast, and assistive-technology support — with inclusive interaction patterns.

quantumquirkxyz Skill

Design physics talks — seminars, conference presentations, posters, public outreach — with audience-level adjustments, timing, visual conventions, and accessibility.

quantumquirkxyz Skill

Perform manual test sessions — exploratory checks, edge cases, accessibility, and user-visible regressions — with explicit reproduction notes.

quantumquirkxyz Skill

accessibility-testing

quantumquirkxyz Skill

Define and evolve reusable UI tokens, components, and usage rules as a coherent system.

quantumquirkxyz Skill

Shape frontend work into a clear visual system, interaction model, and implementation seam — with explicit state and motion boundaries.

quantumquirkxyz Skill

Design mathematics presentations — Beamer slides with TikZ diagrams, colour accessibility, speaker notes, and audience-level adjustments — for seminars, conferences, or lectures.

quantumquirkxyz Skill

Design and grade math problem sets and exams — difficulty progression, rubric, anti-cheating variants, accessibility, and LaTeX layout.

quantumquirkxyz Skill

Track physics literature — arXiv (hep-th, cond-mat, astro-ph, gr-qc, quant-ph, nucl-th, physics.*), INSPIRE-HEP, NASA ADS, Web of Science, citation alerts — with domain filters.

quantumquirkxyz Skill

Design inclusive products — WCAG compliance, assistive technology support, keyboard navigation, color contrast — with explicit user access guarantees.

quantumquirkxyz Skill

Design accessible interfaces — semantics, focus management, keyboard flows, contrast, and assistive-technology compatibility — with inclusive interaction patterns.

lamm-mit Bundle

Generate optimized LLM prompts using chain-of-thought, ReAct, and other scientific reasoning patterns