Web & Frontend

xgent-ai Bundle

开发/修改 XGENT Portal 的嵌入式微应用前端（micro 型 App，iframe + @xgent/portal-sdk，即 apps/*-app）。凡任务涉及新建一个 App 前端、给某 App 加页面/导航项/Dashboard Widget、SDK 握手/getToken/callService、consent 授权屏、或 iframe 内的 UI 异常（弹窗无效/菜单点不动/主题/路由同步/全屏/剪贴板）时，务必先用本 skill——即使用户没提"微应用"三个字。Use when building or changing any micro-app frontend embedded in the portal (apps/*-app), the portal SDK handshake, navItems, dashboard widgets, or iframe-specific UI issues.

xgent-ai Bundle

把一个 App 的新版本发布到 XGENT.ai Portal —— 在 App 自己的 repo 里用 xrel_ 发布令牌一条命令提交「前端产物 dist / bump 版本 / 换镜像 / 整份 app.manifest 清单」，落成发布提案：无治理变更自动生效，改权限面的进平台「发布审核」等批准；不登录门户控制台、不找门户运维代传。凡任务涉及发版/发布前端或后端镜像/上传产物/提交或修改 app.manifest.json/首次把 App 接入门户/release-cli/xrel_ 令牌/POST /api/market/release/、配 vite base、在 CI 里写发布步骤、或出现「发布 401 / 404」「发布 200 但 ok:false」「PROPOSAL_PENDING / 一直 pending 等审」「/apps/<key>/ 白屏或资源 404」「发上去了但线上没变 / 容器没换版」这类症状时，务必先用本 skill 再动手——即使用户只说「发个版」。Use whenever publishing or debugging an XGENT portal app release from the app's own repo — frontend dist, backend image, or manifest/governance changes via release proposals: release tokens, packaging, version bumps, CI wiring, pending approvals, or a blank/404 /apps/<key>/ page after a publish.

yaklang Skill

基于 grep 文本搜索和文件读写的代码安全审计技能。通过正则表达式模式匹配在项目源码中 定位危险函数调用、敏感数据流和已知漏洞模式，覆盖 30+ CWE 漏洞类型， 支持 Java、Golang、PHP、Python、C/C++、JavaScript 等多种语言的安全审计。

yakoub-ai Skill

Audit and improve accessibility in Flutter apps. Use when the user wants to check WCAG compliance, add semantic labels, verify screen reader support, or review tap target sizes and text scaling behavior. Trigger phrases: "check accessibility Flutter", "add semantic labels", "a11y Flutter", "screen reader Flutter", "accessibility audit", "TalkBack Flutter", "VoiceOver Flutter", "WCAG Flutter", "semantic widgets Flutter", "focus order Flutter", "text scaling Flutter", "accessible Flutter app".

codename-co Skill

Guide for creating React components using HeroUI in the DEVS platform. Use this when asked to create new UI components, pages, or modify existing React code.

daiki48 Skill

Leptos v0.8.x frontend development guide. Components, signals, resources, async, forms, and ownership patterns.

decocms Bundle

Create and edit presentation decks as single self-contained HTML files with a live, editable preview and print-to-PDF export. Use when the user wants slides, a deck, or a presentation.

decocms Bundle

Render any text file (HTML, markdown, config, SQL, email) from a mustache template plus JSON data. Use when an output's shape is fixed ahead of time and only the values change.

tt-a1i Bundle

Scan a codebase for deepening opportunities, present them as a report — HTML on request — then grill through whichever one you pick.

mizchi Skill

End-to-end automatic markup — recreate a page or component as HTML/CSS from a target screenshot (or UI Contract IR), driven by deterministic signal tools with an optional VLM assist. Pipeline; scaffold the landmark skeleton (contract scaffold), converge composition (build page - missing/extra components, ordering, stacking gaps), converge each part (build component + report.json), then audit decoration (check palette / tokens / theme). Works with any agent model including Haiku; the tools are pure Playwright + pixel math, no API key required. Use when asked to implement markup from a design image, rebuild a page to match a reference, or prove a screenshot-to-HTML loop converges.

mizchi Bundle

Focus visual regression testing on ONE component instead of a whole page, so the diff is small enough to read and to hand to a model. Mounts a story from a Playwright component-testing gallery and screenshots only that component (`vlmkit check story`), then loops baseline → diff → fix → re-run to green. Includes copyable gallery reference implementations (vanilla / React / Vue) because Playwright ships no template for the gallery. Use when repairing or restyling a specific component, when a full-page diff is too noisy or cascades, or when a project wants per-component VRT baselines. Not for whole-page comparison (use vrt-visual-diff) or for generating browser tests from a spec (use spec-to-playwright).

mizchi Skill

General-purpose deterministic verification for any HTML/CSS work — no API key, no reference design required, no project setup. Route by task; run the matching vlmkit gate (integrity / copy / layout / breakpoints / scroll / handlers / interactions / verify markup); read the kickback; fix; re-run to green. Use whenever you wrote or edited markup and want to know if it is actually correct — broken-page defects, copy fidelity, responsive boundaries, keyboard operability, design-target match — instead of eyeballing a screenshot. Works standalone in any repo via `npx vlmkit`; this is the drop-in generalist skill, distinct from the full-workflow skills (auto-markup / mock-markup / dynamic-markup).

mizchi Skill

Markup with dynamic behavior — recreate a page whose requirements include responsive breakpoints, scrollable panels, and CSS animations from target screenshots plus a short motion brief, then prove the behavior with the deterministic dynamic-gate suite (check breakpoints / scan scroll / check animation / check motion). Static pixel convergence delegates to the auto-markup skill. Works with any agent model — the agent's own vision is the only VLM required, no API key; Haiku handles structure/spacing cheaply, hard 1px endgames measured to need Sonnet (see Model selection). Use when a markup task specifies how the page behaves (resizes, scrolls, animates), not just how one screenshot looks.

mizchi Skill

Compare two rendered pages (URL pairs or local HTML) and produce a structured Markdown report tailored for coding agents — pixel diff per viewport, per-section diffRatio, computed-style diff split into universal vs. breakpoint-gated, and worst-viewport screenshot paths. Use when the agent just made a UI change and needs to know whether it altered visible output, where it altered it, and which CSS properties drove the change. Works on a single HTML/URL pair without baseline state.

mizchi Skill

Plan and sequence a whole-screen markup problem by decomposing it into components first, then routing each phase to the loop that fits it — outline extraction from a reference, per-component construction, and the handoff where a converged component is frozen as a story baseline so later edits are checked per component instead of per page. Use when the task is a whole screen or feature rather than one component, when a reference/mock exists and you need to decide the component boundaries before writing markup, or when converged markup needs to become maintainable. Not a build loop itself — it routes to auto-markup / mock-markup / dynamic-markup / component-vrt and defines the handoff between construction and maintenance.

mizchi Skill

Closed-loop CSS auto-repair. Given a fixture with a known regression (one CSS property or one selector block removed), iterate with a VLM that proposes the missing fix from the diff screenshot, apply it, and re-run until the diff falls below a threshold. Currently scoped to the CSS-challenge fixture set in `src/experiments/css-challenge/`; adapting to an arbitrary repo requires writing a fixture entry. Use when measuring whether a VLM model can recover a known regression, not for production self-healing.

mizchi Skill

Five DOM/pixel-based signal tools for markup work — turn a screenshot + HTML scaffold into a converging pixel diff (build component), crop a page screenshot into per-component PNGs (scan component), audit hard-coded values against a design-token scale (check tokens), verify theme parity (check theme — light vs dark render), and stress-test layout under inflated text (stress i18n). All five are pure DOM + Playwright + pixel processing — **no VLM / no API key required**. The agent supplies the markup reasoning; the tool surfaces the signal. Use when you've authored HTML/CSS and want signal back without paying VLM latency or cost.

mizchi Skill

Evaluate whether a framework / CSS-library / build-system swap (Tailwind → vanilla CSS, reset-css switch, bundler swap, etc.) produced a visually-equivalent result. Three modes — compare (deterministic pixel + CSD), blind (agent runs without baseline reference), subagent (dispatched-agent verification) — let the caller pick the rigour level. Use when the diff is large by construction (the markup was rewritten) and a flat pixel diff would drown the actual regressions in noise.

rohitguta2432 Bundle

Design a production architecture for an AI chatbot on WhatsApp running on AWS (End User Messaging Social or Meta Cloud API, SNS/SQS, Lambda, Bedrock, DynamoDB, Knowledge Bases). Produces an architecture doc with diagrams, component table, KB vs tool split, cost estimate, and a production checklist. Use when the user says "WhatsApp bot on AWS", "WhatsApp chatbot architecture", "Bedrock WhatsApp", "design my WhatsApp AI agent", "WhatsApp + Lambda", or asks how to connect an LLM to WhatsApp on AWS.

45ck Skill

component-boundary-reviewer

polakinio Bundle

Turn ideas, workflows, screenshots, or design briefs into credible product design direction and frontend guidance that avoids generic AI-looking UI.

polakinio Bundle

Set up and run Codex custom subagent orchestration for software projects. Use when a user wants a project-local `.codex/agents/*.toml` team, an `AGENTS.md` orchestration contract, a software-factory workflow, parallel Codex subagents, or reusable agent chains such as architect to backend/frontend to tester/security/reviewer.

axisrobo Skill

Generate a draw.io architecture diagram (or PNG) from an Architecture YAML file. Produces .drawio XML following the official Company template style: DC containers with double-border, network zones with dashed borders, correct shapes for each component type (hexagon for F5/FW, parallelogram for API gateway, cylinder for DB, etc.), edges labeled with protocol and auth. Optionally exports PNG. Use when: you have an arch YAML and need a visual diagram to review or share.

akarachen Skill

Find and remove unused code across frontend and backend. Use when the user asks to "clean up dead code", "find unused exports", "remove unused commands", "delete dead code", or wants to identify and eliminate unreferenced functions, types, dependencies, or Tauri commands. Covers both TypeScript/React frontend (via knip) and Rust/Tauri backend analysis.

sanhuang520-ship-it Bundle

中式网页主题库。当用户要"中国风网页""国风网站样式""古风博客主题""中式配色 CSS""水墨风页面""新中式网页""给网站换个中国风皮肤"时使用。提供 8 套可直接引入的 CSS 主题，内置中文排版规范。

singh-gur Bundle

Creates polished, source-controlled diagrams from requirements, prose, sketches, or existing systems. Recommends Excalidraw first, with D2 as a text-based alternative; uses Iconify icons, prioritizes visual fidelity and clean connector routing, preserves editable sources, renders outputs, and visually inspects every result. Use for architecture, conceptual, component, data-flow, control-flow, sequence, process, deployment, network, ER, trust-boundary, and other technical diagrams.

smileynet Skill

Validate a lesson against all quality guidelines — code block metadata, narrative framing, downloadable files, SVG theming, accessibility, glossary coverage. Dispatchable as a subagent for independent review. Trigger: validate lesson, check lesson, lesson compliance, review lesson quality.

softinter-chiangrai Skill

Creates a main menu/navigation hub component with dynamically generated menu items based on selected capabilities (search, create, save, delete). Prompts for entity name and available actions, generates menu card and routes. Use when the user asks for Day 2 step 3 of the CRUD drill, or asks to build a main menu for up-app.

softinter-chiangrai Skill

Scaffolds up-app (Angular 22 + Tailwind CSS). CRUD drill Day 2 step 0. Trigger: 'day2 step0', 'create up-app'.

stanfordspezi Bundle

Choose between React Native and Apple-native for a digital health app, set up the matching Spezi starter template, and move existing planning briefs into the new project so the coding agent has full context for implementation.

yang20040317-svg Skill

数据可视化图表专项方法论。当载体是数据图表/HTML/报告且需要"把数据变精致可读的图"时触发。覆盖：数据形状选图主键、一图一结论、标题写结论、细读型vs快读型、视觉编码诚实性、色彩语义、交互三问、库外新图现场造句、敢于说不、图表交付自检13项。触发词：「数据可视化」「图表」「做几张图」「把这数据画一下」「dashboard」「report」「一图一结论」。

yang20040317-svg Skill

前端/数字产品设计通用原则专项方法论。当产出是 Web/App 界面、交互数字产品、或含动效的页面，需要"像专业前端设计师一样"打磨信息架构、文案、视觉观感与动效时触发。覆盖：结构装置即信息、反模板校准（避免AI默认观感）、复杂度匹配愿景、文案即物料（UX写作）、动效编排时刻、动效语义与具体手法、前端设计通用原则。触发词：「前端设计」「网页界面」「数字产品」「UX写作」「反AI模板」「结构装置」「文案」「动效编排」「signature元素」。

yang20040317-svg Bundle

联网找素材做参考专项。**模式 1 默认路径的强制前置步骤**——用户输入任务 brief 后自动触发，去参考站找「对应的设计」作本次设计依据；用户主动说「找参考/找灵感/找配色/找音效/看看别人怎么做/搜一下案例」时同样触发。覆盖：12 个策展源（Pinterest 与爱给网需登录；Cosmos/ArtStation/Behance/Unicorn Studio/Refero Design/Awwwards/ThreeUI/React Bits/Spline Community/Codrops Creative Hub 开放可直抓）、**agent-browser CLI 截图读图（复用 Chrome 登录态，首选用于登录源与 JS 渲染画廊）**、开放源直抓与登录源带会话抓取的两种手法、合规红线（仅作参考不擅发、版权与署名）。接入设计工作流第二层「感知物料」，作为真实素材补给线。

zeroz-lab Bundle

将自然语言 3D 产品或空间需求转成自包含生产任务书，配置环境、Agent 分工、证据评分与返工退出条件；明确要求制作成品或继续已有制作时，推进 Blender 静态场景构建、渲染评审与验收。适用于创意定向、产品可视化、拆解和空间场景；默认只交简报。已有项目的孤立排错、CSS 3D 和打印切片不适用。

zeroz-lab Bundle

Turn complex workflows, responsibilities, states, and system relationships into mobile-readable HTML + SVG diagrams. Use for flowcharts, swimlanes, state machines, layered architectures, and hub-and-spoke explainers that need disciplined layout, routing, and audit.

zzyong24 Bundle

AI演示文稿全流程制作：内容结构化→设计选型→AI插画/HTML构建→PPTX导出。17种实战验证的视觉风格（漫画/极简/数据叙事/国风），可编辑HTML与全AI视觉两条路径自由选择。当用户提到"做PPT"、"制作幻灯片"、"演示文稿"、"Keynote"、"slides"、"课件"、"汇报材料"、"路演"时使用。