Web & Frontend
Web development agent skills handle frontend and full-stack work: component patterns, CSS and accessibility fixes, performance budgets, and framework conventions. Install a skill once and your AI agent follows the same playbook in every project, from quick prototypes to production apps.
-
esaterbiltavus Bundle Dilekce TreacTREAC (Thesis → Rule → Explanation → Application → Conclusion / Tez → Kural → Açıklama → Uygulama → Sonuç) ve TREACC (... → Counterargument → Conclusion / karşı argüman katmanı eklenmiş) yöntemiyle Türk hukukunda dilekçe ve savunma hazırlamak için kullanılır. Tetikleyiciler: "TREAC yöntemiyle/şemasıyla dilekçe", "TREACC ile savunma yaz", "tez-merkezli dilekçe", "Thesis-Rule- Explanation-Application-Conclusion dilekçe", "kuralın yorumunu öne çıkaran brief". Net bir tez kurulabilen ve kuralın içtihat/öğretiyle yorumunun önem taşıdığı savunma ve briefler için güçlüdür. Çıktı docx/html/udf/pdf üretilir.
-
esaterbiltavus Bundle Dilekce TreatTREAT (Thesis → Rule → Explanation → Application → Thesis restated / Tez → Kural → Açıklama → Uygulama → Tezin Tekrarı) yöntemiyle Türk hukukunda dilekçe ve savunma hazırlamak için kullanılır. Tetikleyiciler: "TREAT yöntemiyle/şemasıyla dilekçe", "TREAT ile dava/cevap/savunma yaz", "tez-açıklama-uygulama-tez modeli", "Neumann modeli dilekçe/savunma". Tek güçlü tez etrafında kurgulanan; tezi okuyucunun zihnine yerleştirip sonda pekiştirerek "çerçeveleyen" dosyalarda güçlüdür. Çıktı docx/html/udf/pdf üretilir.
-
esaterbiltavus Bundle Dilekce CrexacCREXAC (Conclusion → Rule → Explanation → Example → Application → Conclusion / Sonuç → Kural → Açıklama → Emsal Örnek → Uygulama → Sonuç) yöntemiyle Türk hukukunda dilekçe ve savunma hazırlamak için kullanılır. Tetikleyiciler: "CREXAC yöntemiyle/şemasıyla dilekçe", "CREXAC ile dava/cevap/savunma yaz", "emsal-örnek odaklı dilekçe", "benzer olayda mahkeme şöyle değerlendirdi dilekçesi", "Conclusion-Rule-Explanation-Example-Application-Conclusion". Emsal kararın güçlü olduğu, kuralın benzer bir olayda nasıl uygulandığını göstermenin tezi taşıdığı dosyalarda kullanılır. Çıktı docx/html/udf/pdf üretilir.
-
esaterbiltavus Bundle Dilekce CrraccCRRACC (Conclusion → Rule → Rule explanation → Application → Counterargument → Conclusion / Sonuç → Kural → Kuralın Açıklaması → Uygulama → Karşı argüman → Sonuç) yöntemiyle Türk hukukunda dilekçe ve savunma hazırlamak için kullanılır. Tetikleyiciler: "CRRACC yöntemiyle/şemasıyla dilekçe", "menfaat/policy argümanlı çok katmanlı dilekçe", "karşı argüman + hakkaniyet dengesi içeren dilekçe", "Conclusion-Rule-Ruleexplanation-Application-Counterargument-Conclusion ile dava/cevap/savunma yaz". Karmaşık, çok yönlü ve menfaat dengesi/hakkaniyet gerektiren meselelerde kuralı içtihatla açıklar, karşı argümanı çürütür ve policy boyutunu işler. Çıktı docx/html/udf/pdf üretilir.
-
esaterbiltavus Bundle Dilekce CrupacCRuPAC (Conclusion → Rule → Rule proof → Application → Conclusion / Sonuç → Kural → Kuralın İspatı → Uygulama → Sonuç) yöntemiyle Türk hukukunda dilekçe ve savunma hazırlamak için kullanılır. Tetikleyiciler: "CRuPAC yöntemiyle/şemasıyla dilekçe", "kuralın içtihatla ispatına dayanan dilekçe", "Conclusion-Rule-Ruleproof-Application-Conclusion ile yaz", "kural ispatı katmanlı dilekçe". Kuralın varlığı veya kapsamı tartışmalı olup yargı içtihadıyla desteklenmesi gereken dosyalarda kuralı ayrı bir adımda ispatlar. Çıktı docx/html/udf/pdf üretilir.
-
esaterbiltavus Bundle Dilekce ToulminToulmin Modeli (Claim → Grounds → Warrant → Backing → Qualifier → Rebuttal / İddia → Dayanak → Gerekçe/Köprü → Destek → Çekince → Çürütme) çerçevesiyle Türk hukukunda dilekçe ve savunma hazırlamak için kullanılır. Tetikleyiciler: "Toulmin modeliyle dilekçe", "Toulmin ile itiraz/bilirkişiye itiraz", "iddia-dayanak-gerekçe(warrant) analizi", "karşı tarafın argümanındaki köprüyü hedefleyen dilekçe". Vakıayı talebe bağlayan örtük hukuki köprüyü (warrant) görünür kılar; karşı tarafın argümanındaki zayıf halkayı hedeflemekte güçlüdür. Çıktı docx/html/udf/pdf üretilir.
-
esaterbiltavus Bundle Dilekce Klasik RetorikKlasik Retorik Düzeni (Cicero/Quintilian) — Exordium → Narratio → Partitio → Confirmatio → Refutatio → Peroratio (Giriş → Olay Anlatımı → Konu Bölümleme → İspat → Çürütme → Sonuç) yöntemiyle Türk hukukunda dilekçe ve savunma hazırlamak için kullanılır. Tetikleyiciler: "klasik retorik düzeniyle dilekçe", "Cicero/Quintilian düzeni", "Exordium-Narratio-Partitio-Confirmatio-Refutatio-Peroratio", "anlatı gücü yüksek kapsamlı dilekçe". Olay örgüsü zengin, çok bölümlü ve hem ispat hem çürütme gerektiren dosyalarda anlatıyı güçlü bir iskelete oturtur. Çıktı docx/html/udf/pdf üretilir.
-
facebook Bundle Add UIAdd UI components to a Meta Display Glasses webapp — screens, buttons, lists, cards, forms, toggles, counters, or nav bars. Works with vanilla JS and React apps. Use when the user wants to add any interactive UI element or new screen.
-
facebook Skill Add Text InputAdd text entry to a Meta Display Glasses webapp. Standard HTML inputs open the on-glasses composer (handwriting + voice) when focused and tapped. Use when the user wants a text field, search box, form input, or notes area.
-
fattain-naime Bundle Cwp SecurityThis skill should be used when the user asks to "configure CSF firewall", "set up ModSecurity", "install SSL certificate", "enable AutoSSL", "harden server security", "configure SSH security", "set up brute force protection", "block IP address", "whitelist IP", "install OWASP CRS", "check for hacks", "run security audit", "configure firewall rules", or needs to manage any security component on a CWP server.
-
fattain-naime Bundle Cwp WebserverThis skill should be used when the user asks to "configure Apache", "configure Nginx", "set up Varnish", "switch web server stack", "edit vhost template", "rebuild vhosts", "fix web server errors", "configure SSL for web server", "set up reverse proxy", "enable Brotli compression", "fix 502 bad gateway", "fix redirect loop", "manage web server modules", or needs to manage any CWP web server stack component.
-
ferueda Skill React To ReviewEvaluate, analyze, and systematically react to an adversarial code review report. Decide on the action for each finding (Implement, Adapt, Decline), provide clear justifications, and define the plan to implement the accepted changes.
-
gnurio Skill Manage Color ContrastEnsure WCAG AA accessibility and readability
-
rshvr Skill Cohere LanggraphCohere LangGraph agents reference for building ReAct agents, multi-tool workflows, agents with memory, and human-in-the-loop patterns. Covers both prebuilt and custom agent architectures.
-
ruan-cat Skill Use IconifyUse when 开发者需要在后台项目 `apps/eams-frontend` 中显示图标,尤其是要在 Vue 页面、配置驱动菜单、组合式函数、或兼容旧 `IconXxx` 写法之间选择合适方案时使用。适用于 `ReIcon`、`IconifyIconOffline`、`IconifyIconOnline`、`useRenderIcon`、离线图标扩展和 iconify 接入排错。
-
rusel95 Bundle IOS LocalizationProduction-grade iOS localization skill covering String Catalogs (.xcstrings), CLDR pluralization, SwiftUI/UIKit localization APIs, RTL layout, date/number/currency formatting, and enterprise patterns (modular apps, white-label, accessibility localization). This skill should be used when creating or editing localized iOS strings, working with .xcstrings or .strings files, implementing pluralization, formatting dates/numbers/currencies for display, building RTL-compatible layouts, localizing accessibility labels, setting up localization in Swift Packages, or reviewing code for localization correctness. Use this skill any time someone is working with iOS localization, i18n, l10n, String Catalogs, plural rules, RTL, date formatting, or translated strings — even if they only say 'add a string' or 'format this date' or 'make this work in Arabic.' Also audit any newly generated user-facing iOS code for localization failures before finalizing — AI coding assistants systematically produce broken localization (hardcod
-
rusel95 Bundle IOS AccessibilityProduction-grade iOS accessibility skill covering VoiceOver, Dynamic Type, color contrast, motion, Switch Control, Voice Control, and WCAG 2.2 compliance for both SwiftUI and UIKit. This skill should be used when creating new iOS screens or views, reviewing existing iOS code for accessibility, adding VoiceOver support, fixing Dynamic Type issues, auditing WCAG compliance, implementing accessibilityLabel/traits/hints, grouping elements for assistive technology, adding custom actions or rotors, respecting system accessibility preferences (reduce motion, increase contrast, differentiate without color), writing accessibility-focused XCTest audits, or preparing apps for enterprise compliance (ADA, EAA, Section 508). Use this skill any time someone is working with iOS accessibility, VoiceOver, Dynamic Type, assistive technology, WCAG mapping, or accessibility modifiers in SwiftUI or UIKit — even if they only say 'make this accessible' or 'add VoiceOver support' or 'check contrast.' Also run an accessibility pass on
-
sainytk Bundle SlackcliRead and write Slack via the local slackcli CLI (channels, DMs, threads, search, canvases, reactions, messages). Use when the user asks to read, search, summarize, send, or react to Slack messages, or to inspect Slack channels, DMs, threads, canvases, or saved items.
-
scrapfly Skill Scrapfly CLIUse the Scrapfly CLI (`scrapfly`) to scrape web pages, capture screenshots, extract structured data with AI, crawl entire sites, and drive a cloud browser over CDP from a shell. JSON envelope on stdout for every command. Use when the user asks to "scrape a URL", "screenshot a page", "extract data from HTML", "crawl a site", "drive a browser with Playwright/CDP", "bypass anti-bot", or any task involving the `scrapfly` command.
-
scrapfly Skill Scrapfly RpaUse the Scrapfly RPA API to run typed workflow graphs against managed cloud browsers, retrieve produced artifacts (HTML snapshots, downloads, HTTP response bodies, JS return values), and route those artifacts into Scrapfly's managed bucket or your own customer GCS or S3 bucket. Use when the user asks to "run an RPA workflow", "fetch artifacts from a run", "configure BYOS storage", "set up customer GCS or S3 for RPA", "test a storage destination", or any task involving the /v2/rpa/* endpoints.
-
semanticpixel Skill ReviewReview a GitHub PR or GitLab MR with craft-level attention to semantic HTML, CSS architecture, accessibility, TypeScript patterns, and code quality. Auto-detects platform from URL or git remote. Proposes inline diff comments, shows them for approval, only posts what the user approves. TRIGGER when the user says "/abc:review", "review this PR/MR", "review <url>", or passes a PR/MR number.
-
siva01c Skill Tiny FixLow-ceremony workflow for trivial, low-risk changes: typos, comments, CSS/styling tweaks, string changes, single-line fixes with no logic impact. Use to avoid the overhead of the full feature workflow when the change cannot break anything. If during the fix the change turns out to touch logic, security, config, or schema, stop and escalate to the feature-workflow skill.
-
siva01c Skill Feature WorkflowPhased workflow for delivering a Drupal feature or non-trivial change: plan, implement, review, test, finalize. Use when building a new custom module, adding a route/form/plugin, changing entity structure or schema, or any task touching more than a couple of files. Do NOT use for typo fixes, CSS tweaks, or single-line changes — use the tiny-fix skill instead. Each phase has an exit condition; do not move to the next phase until it is met.
-
skmtc Bundle Skmtc ModelThe model-generator shape for Skmtc: one definition per component schema, built by copying the shipped SKELETON package and filling its SLOT markers with the target library's syntax. Covers the edge cases every model generator must survive — refs, recursion, optional vs nullable, additionalProperties, enums, readOnly/writeOnly. Use when authoring or editing a generator that maps schemas to a validator/schema/type library ("write a gen-<lib>", "map OpenAPI models to <lib>"). Load ALONGSIDE skmtc-generator (engine rules) and skmtc-lang-typescript (TS layer).
-
unisone Skill SummarizeSummarize or extract text/transcripts from URLs, podcasts, and local files (great fallback for “transcribe this YouTube/video”); Don't use for simple HTML page extraction; use web_fetch tool directly.
-
varunk130 Skill AI Accessibility AuditWCAG 2.2 Level AA accessibility audit for AI product surfaces - color contrast, focus order, ARIA usage, keyboard navigation, motion/animation, reduced-motion respect, alt text, and form label association. Use when: accessibility audit, a11y review, WCAG audit, screen reader compliance, keyboard-only navigation, color contrast check, focus management, ARIA review, accessible AI UX.
-
vectojs Skill Vectojs StylesUse when styling VectoJS UI with @vectojs/styles — CSS-property-name style objects, var() token themes with setTheme switching, css() merging, font composition, per-axis padding, or migrating CSS/web styling habits onto the numeric Virtual Math Tree.
-
vectojs Skill Vectojs ParadigmUse FIRST when building, changing, or debugging any UI in a VectoJS project — before writing code, before taking screenshots, and especially when tempted to add HTML elements, write CSS, use querySelector, or "look at" a rendering problem visually.
-
vectojs Bundle Vectojs Core RuntimeUse when building or reviewing VectoJS apps with @vectojs/core, Scene/Entity, canvas rendering, semantic DOM projection, accessibility, automation, framework mounting, or lifecycle cleanup.
-
wanghie Bundle Nqh Research Creator ProductBóc tách 1 sản phẩm cụ thể của creator qua công tắc loại (SaaS / Dịch vụ / Vật lý / Digital / Cộng đồng) + bộ lớp riêng theo loại. Có nhánh dịch vụ với kinh tế đơn vị + kinh tế khách hàng + cung ứng nhân lực bắt buộc. Output là báo cáo HTML dark-theme (Inter · tabular-nums) chuyển từ chẩn đoán sang kê đơn cho creator sắp bắt tay làm. Kích hoạt khi nói "research sản phẩm creator", "bóc tách sản phẩm X", "clone sản phẩm này được không".
-
zizhanovo Bundle Dby Publish公众号图文流水线 · 终态是**排版好的公众号 HTML**或**文章进自己公众号草稿箱**时用它(只存草稿、绝不群发)。 输入是**已写好的** Markdown/HTML,本流水线不代写正文,只做之后的确定性运维:渲染 → 图片预上传 → 封面 → 存草稿。 ⚠️ 它会**写进用户自己的公众号后台**,用户只要成稿时别自作主张跑它。存草稿需绑号 + DOUBAOYA_API_KEY; 只做本地渲染 / 换主题时不需要。 Trigger words: 正文写好了怎么发 / 要排版好的公众号 HTML / 接着排版发草稿 / 写公众号 / 转公众号排版 / 推公众号草稿 / 重新推草稿 / 带封面发布到草稿箱 / 把文章存进公众号草稿箱 / 公众号图文流水线 / dby-publish / 存公众号草稿 / 公众号草稿箱 / 代发公众号草稿箱 / addDraft / draft/add / 图文推进公众号 / 稿子发到公众号后台。
-
lidessen Bundle PerfRun web UI performance tests for the agent-worker project. Automates build, daemon restart, cache-bust version bump, Lighthouse audit, and metric reporting — all in one command. Use this skill when the user says "run perf", "check performance", "lighthouse", "perf test", "why is it slow", "check TBT", "性能测试", "跑一下性能", or wants to measure/compare web UI performance. Also trigger after making changes to semajsx/style, render, or any web UI component when performance impact needs verification.
-
mohitmishra786 Skill IntegrationConnect frontend to backend, integrate third-party services, handle authentication, and implement error handling
Audited -
qoderai Bundle Diagnose Backend BugDiagnose a bounded backend or multi-service failure from GitHub Issues, Jira, Aone, user-provided exports, logs, traces, responses, stack traces, or job records. Use when a service, API, RPC, worker, queue, CLI, or scheduled job bug needs correlation through the project's existing observability route before repair; do not use for frontend-only defects or generic logging reviews.
-
qoderai Bundle Reproduce Frontend BugBuild a bounded, replayable browser or UI bug reproduction from GitHub Issues, Jira, Aone, user-provided exports, screenshots, videos, comments, or attachments. Use for browser, WebView, IDE or desktop UI, interaction, responsive, rendering, accessibility, or visual defects that need evidence-preserving reproduction before diagnosis or repair; do not use for ordinary implementation or backend-only failures.
-
swarmclawai Bundle Openai Image GenGenerate images via OpenAI Images API (GPT Image, DALL-E 3, DALL-E 2). Supports batch generation with random prompt sampler and HTML gallery output. Use when asked to generate images with OpenAI and an OPENAI_API_KEY is available.
Frequently asked questions
What are Web & Frontend agent skills?
Web development agent skills handle frontend and full-stack work: component patterns, CSS and accessibility fixes, performance budgets, and framework conventions. Install a skill once and your AI agent follows the same playbook in every project, from quick prototypes to production apps.
Which Web & Frontend skills are most installed?
Popular Web & Frontend skills on SkillMD right now include ios-accessibility, review, perf. Rankings shift as installs change; sort this page by "Most installs" for the live list.
Do Web & Frontend skills work with Claude Code and Cursor?
Yes. Every skill here ships as a SKILL.md file, an open format that works in Claude Code, Claude.ai, Cursor, Codex, Windsurf, and 60+ other agents. Install one with npx skillmds@latest add <owner>/<name>, or copy the file into your agent's skills directory.