Web & Frontend

winhok Bundle

面向拿不到代码仓库的测试工程师，分析网站已交付的 HTML、JS/CSS、公开 source map、浏览器状态和运行记录，逆向建立页面、路由、资源、接口、状态与角色分支的全局测试地图，为 TestSpec 分析、测试点和用例设计提供实现证据。用户说没源码、无仓库、逆向 Web、分析打包 JS/bundle、梳理线上网站全貌、找隐藏测试面或判断测哪里时使用；按已确认用例执行验收走 app-test，有源码的实现校准走 testspec-code-calibrate，主动安全探测不使用本 skill。

yaojingang Bundle

Use only for explicit legacy GEOFlow template skill questions, old PHP template-package contracts, or historical outputs using root index.php/article.php/category.php/archive.php and includes/*.php. Route current Laravel Blade themes, reference-site cloning, homepage modules, lead_form, theme editor, channel frontend, and target-package mapping to yao-geoflow-design. Do not use for new frontend design, backend implementation, raw HTML copying, or live activation.

yaojingang Bundle

当用户需要系统、详细、完整地生成一篇可发布的 GEO 科普文章，并附带 How-to 教程、概念解释、购买/选择指南、避坑清单、FAQ、术语表、证据分级、读者场景、决策路径、品牌自然植入建议、真实数据核验附录，以及带固定目录菜单的 HTML 包、Word、PDF 和 Markdown 四格式报告时使用；适配 Kimi、千问、豆包、DeepSeek、元宝等国内 AI 搜索/问答平台；不用于榜单排行、整站诊断、页面审计、标题生成或无证据品牌软文。

yaojingang Bundle

当用户需要生成 GEO 品牌对比内容、品牌替代方案、选型页、竞品对比页、FAQ 对比问答或“某品牌和其他方案怎么选”的内容包时使用，面向 DeepSeek、豆包、千问、Kimi、腾讯元宝生成中文简体、证据绑定、同口径、公平表达的品牌对比报告，并默认交付 Word、PDF、HTML、Markdown 四格式。

yaojingang Bundle

Build evidence-backed GEO brand knowledge bases from official sites, product pages, help centers, white papers, sales materials, media releases, certifications, and trusted third-party sources. Use when asked to generate reusable brand fact cards, FAQ, prohibited expressions, source indexes, prompt input packs, or Word/PDF/HTML/Markdown four-format Chinese GEO knowledge-base deliverables for Kimi, Qianwen, DeepSeek, Doubao, Yuanbao, content production, monitoring, page design, or customer-service preparation.

yaojingang Bundle

当用户需要基于品牌 Brief、选题配置、关键词、竞品库和可信来源生成 GEO 榜单评测文章、best/top/alternatives/vs/persona/use-case 意图内容、评选方法、核心对比表、榜单正文、适合人群、FAQ、来源表和 Word/PDF/HTML/Markdown 四格式文章包时使用；适配 DeepSeek、豆包、千问、Kimi、元宝；不用于全景诊断、后台归因、单页审计、纯标题生成或无证据软文排行。

aias Bundle

Use when adding or reviewing `useEffect`—unnecessary effects, effect vs event handler, deriving state in effects, reset state on prop change, fetch in effect, effect chains, race conditions, or "do I need an effect". Triggers on React data-flow and synchronization questions alongside `/react-best-practices`. Summary here; full official walkthrough in references/react-dev-full-article.md (react.dev "You Might Not Need an Effect").

aias Bundle

Use when reviewing or cleaning up a change-set — a branch, PR, workspace diff, staged changes, or recent commits. Triggers on "review the changes", "review this PR", "review my branch", "anything I'm missing", "is this dead?", "clean up", "deslop", "tighten", "simplify", "dedup", "reduce LOC", "refactor pass", "knip", "find dead code". Also covers TypeScript types/imports/barrels and HTML/CSS/markup conventions (semantic elements, flex/grid, declaration order, a11y, tokens, CLS). Two modes: REVIEW (read-only, numbered findings) and APPLY (make changes). Owns every review and cleanup of the user's own change-set in this setup, including when a harness ships its own review command.

aias Bundle

Use when writing or reviewing React/Next.js—hooks, server/client boundaries, data fetching, re-renders, bundle splitting, suspense, streaming, or performance tuning. Triggers on .jsx/.tsx, memo, hydration, "slow render", RSC patterns. For `useEffect` specifically, refer to `/avoid-effects`.

aias Bundle

Use whenever motion questions arise—easing, duration, springs, entrance/exit, hover, stagger, scroll-linked animation, interruptibility, reduced motion, or "janky"/"make it smooth". Triggers on Framer Motion (motion/react), GSAP, CSS keyframes/transitions, cubic-bezier, @starting-style, clip-path, transform-origin, modal/drawer/tooltip/toast motion, drag/gesture feel, GPU-safe properties. Design and implement purposeful web animation.

stukh Skill

Generate comprehensive manual test cases from requirements. Covers happy path, validation, security, edge cases, and accessibility. Outputs markdown and TMS-importable formats. Use when: (1) creating manual test cases, (2) building QA checklist, (3) preparing test plan for a feature, (4) generating TMS-importable test cases.

leihuang23 Bundle

Review a code change in repository context for behavioral regressions, correctness, security, privacy, accessibility, operability, and test quality. Use for diffs, pull requests, or pre-commit review. Do not use to summarize code without evaluating it.

timschoch Skill

Use when building or customizing Payload CMS Admin Panel components. Covers component types (Root, Collection, Global, Field), Server vs Client components, hooks, styling, performance, and troubleshooting.

rosuh Skill

Best practices for Android Intent security. Use this skill when auditing component configurations in AndroidManifest.xml activities, services, receivers) or source code handling incoming Intents (getIntent, getParcelableExtra) to prevent Intent Redirection and unauthorized access.

langgenius Skill

Run accessibility and visual design review

langgenius Skill

Accessibility refactoring specialist. Automatically fixes accessibility issues across multiple files. Performs complex refactoring like extracting accessible components, restructuring markup, and implementing proper ARIA patterns.

langgenius Skill

Closes the audit→edit→verify loop. Runs an accessibility audit, applies fixes to source code, and re-audits to confirm. Prefers live-DOM auditing via a browser MCP when available; falls back to static HTML audit when not.

langgenius Skill

Build or review accessible React UI. Use when implementing UI components, reviewing UI code, checking accessibility, choosing Base UI React primitives, or validating forms, overlays, keyboard behavior, focus management, accessible names, and Testing Library queries.

langgenius Skill

Color contrast analyzer for WCAG compliance. Use when analyzing color contrast in code files, when user mentions WCAG compliance, color accessibility, contrast ratios, or when discussing colors in UI components. Calculates contrast ratios, identifies violations, and suggests accessible color alternatives that preserve design themes.

langgenius Bundle

Implement internationalization with Lingui in React and JavaScript applications. Use when adding i18n, translating UI, working with Trans/useLingui/Plural, extracting messages, compiling catalogs, or when the user mentions Lingui, internationalization, i18n, translations, locales, message extraction, ICU MessageFormat, or working with .po files.

langgenius Skill

Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.

langgenius Bundle

Use when writing Playwright tests, fixing flaky tests, debugging failures, implementing Page Object Model, configuring CI/CD, optimizing performance, mocking APIs, handling authentication or OAuth, testing accessibility (axe-core), file uploads/downloads, date/time mocking, WebSockets, geolocation, permissions, multi-tab/popup flows, mobile/responsive layouts, touch gestures, GraphQL, error handling, offline mode, multi-user collaboration, third-party services (payments, email verification), console error monitoring, global setup/teardown, test annotations (skip, fixme, slow), test tags (@smoke, @fast, @critical, filtering with --grep), project dependencies, security testing (XSS, CSRF, auth), performance budgets (Web Vitals, Lighthouse), iframes, component testing, canvas/WebGL, service workers/PWA, test coverage, i18n/localization, Electron apps, or browser extension testing. Covers E2E, component, API, visual, accessibility, security, Electron, and extension testing.

312362115 Bundle

专业图表生成技能：根据需求自动选择合适的图表类型，生成符合设计规范的 PNG 图表。 覆盖 29 种图表：结构图（流程图、泳道图、时序图、架构图、状态图、ER图、类图、思维导图、甘特图、Kanban、Git Graph 等） 和统计图（柱状图、折线图、饼图、雷达图、热力图、散点图、桑基图、漏斗图、瀑布图、矩形树图、柱线混合图等）。 统一工具：HTML/SVG + 内联 JS 布局计算。ER/类图使用 ELKjs 布局引擎。 所有图表遵循统一的设计规范（配色/字体/组件/间距），风格现代简洁。 支持三种输出：PNG（默认）、HTML（富文档嵌入）、DSL（Mermaid 文本，嵌入 MD 文档）。 触发词：画图、画一个、生成图表、流程图、架构图、时序图、柱状图、对比图、关系图。 即使用户没有说"画图"，只要需求中涉及可视化展示（流程、架构、数据对比、关系），都应触发此技能。 被 deep-research 等其他技能调用时，同样遵循本规范生成图表。

xhqing Bundle

Markdown 转 PDF 一条龙（pandoc 转 HTML + Chrome headless 打印 + 像素级排版定量验证）。当用户要把 md / markdown 文档转成 PDF、导出 PDF、生成 PDF 交付版（个人文档、报告、说明书、标书、笔记等，尤其中文文档），或 PDF 出现「内容只占半页 / 右半边空白 / 窄栏 / 页数虚多 / 打开无内容」等排版问题需要修复或验证时，必须使用本 skill。

yusifeng Bundle

Use when the user wants a reusable rolling execution pattern (README + TODO-INDEX) like plans/web-reference-react-refactor, and wants to run delivery in small validated loops.

yusifeng Skill

Use when changing web CSS/UI styling so requirements, state ownership, and acceptance checks are locked before edits to prevent rework churn.

zengtianli Skill

会话结束时生成单文件富 HTML 汇报（dark 风 + vault nav + KPI + 可点击），保存到 ~/Dev/wiki/handoffs/dev/ 并打开浏览器。用户说"汇报 / debrief / 会话总结 / 做个 html / /debrief"触发。

zengtianli Bundle

并行 agent team 处理多目标任务，每个 agent goal-loop 自闭环；产出 HTML 报告给用户看。用户说 "dispatch / 派 agent / agent team 做 / 多并行 / 一次性处理 N 个 / 全部一次性 / 不留尾巴 / 目标驱动并发 / P1=N 直接" 等触发。

zengtianli Bundle

作图默认方法 — 自包含 HTML/SVG 所见即所得预览（多样式）→ 用户批准 → 导出 SVG+PNG+PDF 多格式 + 带下载/复制按钮的 HTML。任何"作图/可视化/改样式/好看点/热图/出图/preview"触发；尤其投稿级、需反复调样式、用户给旧图截图要复刻的场景。

zengtianli Skill

一条命令出 session 现状 + ROI 全景 HTML（包装 cc_sessions.py index + regen_dev_roi.py，输出规范 /debrief 风 HTML，含 vault nav + KPI clickable + per-project 表）。用户说「列会话 / session 现状 / 会话 ROI / sessions / /sessions / 看下 session / 清理候选」时触发

zengtianli Skill

把一批散落的 retro/会话记录按主题线合并成少数 HTML 知识节点（起因→迭代→现状），原文归档到 _archive，织入 wiki 知识网。用户说"4月所有会话讲了啥+修到哪""合并/整合 retro 不要思维负担""摘要这些 retro/会话"时触发。

bonnguyenitc Bundle

Use when building web components, pages, artifacts, or applications — especially when high design quality is needed. Generates creative, polished code that avoids generic AI aesthetics (purple gradients, Inter font, card-in-card layouts).

bonnguyenitc Bundle

Use when working on mobile app features, reviewing mobile code, or making architecture decisions — regardless of platform (React Native, Flutter, iOS, Android)

bonnguyenitc Bundle

Use when building web UI, designing component architecture, or reviewing frontend code — regardless of framework (React, Vue, Svelte, etc.)

bonnguyenitc Skill

Use when designing or building mobile app UI for iOS, Android, React Native, Flutter, SwiftUI, or Jetpack Compose

pedronauck Skill

JavaScript and TypeScript language patterns — const/let, async/await, ESM imports, and typed unknowns. Use when writing or reviewing JS/TS in frontend or backend. Don't use for React component patterns (use react), general file-size or nesting standards (use code-standards), or test structure (use tests).