Web & Frontend

iuiaoin Bundle

Generate high-quality HTML presentation decks with a strict two-stage workflow; manually invoked only when the user runs `/deck --plan` (guided brief, then create PLANNING.md), `/deck --generate` (produce final slides from approved PLANNING.md), and optionally `/deck --export pptx` (export generated slides to PPTX format), supporting technical sharing, architecture reviews, strategy decks, research summaries, pitch decks, and team updates as standalone 1280x720 (16:9) HTML slides.

iuiaoin Bundle

Turn any docs folder, wiki, or knowledge base into an interactive knowledge map — a standalone HTML force-directed graph of concepts, domains, and reader journeys, with search, group filtering, and per-node links back to the source documents. Manually invoked via the /knowledge-graph command with a path to the docs/wiki folder, optionally followed by a focus hint and "--linkbase" plus a published wiki URL to make nodes link to the online wiki; also fits requests like "map this wiki", "visualize our docs as a graph", or "make a knowledge graph of this folder".

shanghua1 Bundle

构建带 AI 辅助的交互式学习网页应用。单 HTML 文件，支持任意题材（编程、剪辑、建模、英语等）。包含课程导航、随堂测验、交互练习、AI 出题/讲解/问答、进度持久化、Skill 管理。当用户想创建学习网站、教程页面、交互式课程、AI 辅助教学系统时使用。

skillmedev Skill

Designs multi-layer caching - CDN, application, and database - choosing the pattern, TTL, and invalidation plan per data type, and produces a cache-decision table plus stampede protection. Use when someone asks "should I cache this", "Redis or CDN for this endpoint", "how do I invalidate this cache", "why is my cache hit rate so low", or is bolting Redis onto a slow service. Do NOT use for sizing or tuning database connection pools - use connection-pool-tuner instead - and do NOT use for frontend bundle, image, or Core Web Vitals work - use web-performance instead.

zhuzhu0833-star Bundle

Researches official university programme pages and handbooks, writes a Chinese curriculum summary, generates an A4 single-page HTML brief, and drafts WeChat moment promotional copy. Use when the user asks to 总结课程设置, 专业介绍单页, 课程总结, 朋友圈宣传, curriculum brief, programme overview HTML, or send a programme summary to a student.

skillmedev Skill

Runs a full WCAG 2.2 accessibility audit of an interface - keyboard, screen reader, contrast and zoom, forms, and media, in a fixed pass order - and delivers a severity-triaged findings table with concrete fixes. Use when someone asks "is this page accessible", "run an a11y audit on this UI", "will this pass WCAG AA", "why can't a screen reader use this form", or is preparing for an accessibility review, procurement questionnaire, or VPAT. Do NOT use for color-and-contrast-only questions such as palette checks or colorblind-safe data visualization - use color-accessibility instead.

skillmedev Skill

Build an application on Builder.io's open-source Agent-Native framework (@agent-native/core) - the model where the agent acts inside the app as a first-class peer to the UI, sharing one set of actions and one database with the interface. Covers the core primitives (actions as the single source of truth, SQL-backed shared state, real-time sync, context-awareness, agent-to-agent, automations, the skills convention), the CLI and cloneable-template workflow, and where to read version-matched docs. Use when someone says "build an agent-native app", "use the agent-native framework", "defineAction", "@agent-native/core", "clone an agent-native template", "make the agent a peer to my UI", or "an app where the agent and the UI call the same actions". Do NOT use for authoring generic Claude Agent Skills / SKILL.md files - that is skill-creator; do NOT use for building a standalone MCP server unrelated to this framework - that is the MCP-builder path; do NOT use for plain Next.js / React scaffolding with no agent runtim

dhruvhkumar Skill

UI state completeness enforcer that ensures every interactive component handles all possible states — not just the happy path. Triggers when creating, reviewing, or modifying any interactive UI element: buttons, forms, inputs, cards, lists, tables, navigation, modals, notifications, or any component the user can interact with.

dhruvhkumar Skill

UX design curator that enforces the 21 Laws of UX (by Jon Yablonski) on every interface, layout, interaction, and visual design decision. Triggers when creating, reviewing, or modifying any user-facing UI — web pages, apps, dashboards, forms, landing pages, emails, or component libraries.

itamarb2010-jpg Skill

Add an event listener to a Minecraft plugin — a Listener class with @EventHandler methods, wired into onEnable with registerEvents. Use this whenever the user wants to react to something happening in-game: on join/quit, block break/place, player interact, entity damage/death, inventory click, chat, respawn, or any Bukkit/Paper event. Handles priority, cancelled-event handling, and hot-event performance. Reads the target stack from .mcplugin/config.yml.

daddia Skill

This skill should be used when the user asks to "map the incentives here," "why is this player behaving this way," "predict how X will react," or has a strategic situation where a player's actual incentive structure — not their stated motivation — needs to be reasoned through.

feixuecode Bundle

Convert everyday questions, concepts, keywords, unfamiliar terms, or "what is X / how does X differ from Y" requests into reusable Chinese knowledge cards, Quarkdown mother drafts, Slidev presentation sources, and interactive HTML explainers. Use when the user wants to understand, remember, compare, review, or build a personal knowledge base for concepts; especially for fragmented internet-era knowledge such as tools, methods, acronyms, technical terms, products, workflows, and conceptual questions. The skill researches like a lightweight hv-analysis pass, stores structured JSON plus Quarkdown/Markdown records, generates a polished interactive HTML page, creates Slidev source when useful, and reuses existing entries on repeated or similar questions.

schalkneethling Bundle

Write tests that start with acceptance criteria, then add implementation tests for robustness. Use when writing unit tests (Vitest), end-to-end tests (Playwright), visual regression tests, or accessibility tests. Emphasizes user-centric testing, semantic locators, accessibility validation, and the balance between acceptance and implementation testing.

daddia Skill

This skill should be used when the user asks "how will competitors react to this," "will this move invite retaliation," "war-game this decision," or has a planned strategic move that needs competitor response forecasted from their actual incentive structure, not generic assumption.

wensonlu Bundle

Use when Dog Project needs to watch or classify H5, React Native, Capacitor, or iOS changes and choose the cheapest safe sync path - decides between H5 cap copy, RN bundle generation, and native iOS rebuild prompts

buzzmatic Bundle

Headless browser automation using Playwright Python for AI agents. Use for web scraping without authentication, form automation, screenshot capture, page interaction, accessibility tree extraction, and programmatic browser control. Ideal when you need deterministic element selection via snapshot refs (@e1, @e2), headless operation, or batch browser automation tasks. Works cross-platform (Windows, macOS, Linux). Complements claude-chrome which handles authenticated sessions.

zengfanling Bundle

独立的需求方案文档 skill。Use when the user wants to单独撰写需求方案、输出 `reqdoc.md`、`demo.html`、整理需求文档、生成可评审的 Markdown 需求稿和可交互原型，或提到 `zfl-reqdoc`、`需求撰写`、`需求文档`、`reqdoc.md`、`demo.html`。

zengfanling Bundle

独立的 UI/UE 设计 skill。Use when the user wants to单独做 UI 方案、UI/UE 设计、高保真方向图、参考图分析、设计迁移、控件切图、HTML 交互效果页，或提到 `zfl-ui`、`UI设计`、`效果图`、`高保真`、`ui.md`、`HTML交互网页`。

bestagentkits Bundle

Generate Playwright tests. Use when user says "write tests", "generate tests", "add tests for", "test this component", "e2e test", "create test for", "test this page", or "test this feature".

bestagentkits Bundle

Converts a markdown deck (slides separated by `---` HR boundaries or by `# ` H1 headings, with optional `<!-- notes: ... -->` presenter notes blocks) into a single-file HTML presentation with arrow-key / space / PgDn / PgUp / Home / End / P / Esc keyboard navigation, presenter mode (split view with current slide + speaker notes + clock + next-slide preview), URL-hash deep linking, and `@media print` page-per-slide for PDF export. Triggers when the markdown-html-orchestrator classifies an input as SLIDES, or when invoked directly via /cs:md-slides. Reuses md-document's markdown parser for slide-body rendering and reads design-system tokens via config_loader.py. Refuses if input has no clear slide boundaries, produces a 1-slide deck, or `--strict-notes` is on with < 50% notes coverage. Use after orchestrator routing.

oli-deacon Bundle

Default frontend taste skill for Codex. Use when implementing or redesigning web UI, app surfaces, dashboards, settings, docs, or component libraries and you want stronger visual judgment, preservation of existing patterns, and a lightweight pre-flight review before shipping.

bestagentkits Bundle

Use when Codex should act as the UX Architect specialist from Agency Agents. Technical architecture and UX specialist who provides developers with solid foundations, CSS systems, and clear implementation guidance

bestagentkits Bundle

Generates unit tests, integration tests, and E2E tests for React/Next.js applications. Scans components to create Jest + React Testing Library test stubs, analyzes Istanbul/LCOV coverage reports to surface gaps, scaffolds Playwright test files from Next.js routes, mocks API calls with MSW, creates test fixtures, and configures test runners. Use when the user asks to "generate tests", "write unit tests", "analyze test coverage", "scaffold E2E tests", "set up Playwright", "configure Jest", "implement testing patterns", or "improve test quality".

bestagentkits Bundle

Accessibility audit skill for scanning, fixing, and verifying WCAG 2.2 Level A and AA compliance across React, Next.js, Vue, Angular, Svelte, and plain HTML codebases. Use when auditing accessibility, fixing a11y violations, checking color contrast, generating compliance reports, or integrating accessibility checks into CI/CD pipelines.

bestagentkits Bundle

Use when Codex should act as the UI Designer specialist from Agency Agents. Expert UI designer specializing in visual design systems, component libraries, and pixel-perfect interface creation. Creates beautiful, consistent, accessible user interfaces that enhance UX and reflect brand identity

bestagentkits Bundle

Frontend development skill for React, Next.js, TypeScript, and Tailwind CSS applications. Use when building React components, optimizing Next.js performance, analyzing bundle sizes, scaffolding frontend projects, implementing accessibility, or reviewing frontend code quality.

bestagentkits Bundle

Fullstack development toolkit with project scaffolding for Next.js, FastAPI, MERN, and Django stacks, code quality analysis with security and complexity scoring, and stack selection guidance. Use when the user asks to "scaffold a new project", "create a Next.js app", "set up FastAPI with React", "analyze code quality", "audit my codebase", "what stack should I use", "generate project boilerplate", or mentions fullstack development, project setup, or tech stack comparison.

bestagentkits Bundle

Build complete transactional email systems: React Email templates, provider integration (Resend, Postmark, SendGrid, AWS SES), preview server, i18n support, dark mode, spam optimization, analytics tracking. Use when adding transactional email to a new product, migrating between email providers, refactoring legacy email templates for accessibility, or adding internationalization to existing templates.

bestagentkits Bundle

Audit and manage dependencies across multi-language projects. Identifies vulnerabilities, license conflicts, transitive dependency risks, and safe-upgrade paths. Use when auditing third-party packages before release, investigating a CVE, planning a major version bump, or running a license-compliance review. Examples: 'audit our npm dependencies', 'do we have GPL contamination', 'plan the upgrade to React 19'.

bestagentkits Bundle

Index of the engineering-team skills bundle for Claude Code, Codex, Gemini CLI, Cursor, OpenClaw, and 6 more tools. Architecture, frontend, backend, QA, DevOps, security, AI/ML, data engineering, Playwright, Stripe, AWS, MS365 (stdlib-only Python tools). Use when browsing or choosing among engineering-team role skills — load only the one specialist SKILL.md you need, never bulk-load the bundle.

bestagentkits Bundle

Use when Codex should act as the Accessibility Auditor specialist from Agency Agents. Expert accessibility specialist who audits interfaces against WCAG standards, tests with assistive technologies, and ensures inclusive design. Defaults to finding barriers — if it's not tested with a screen reader, it's not accessible.

bestagentkits Bundle

Production-grade Stripe integrations: subscriptions with trials and proration, one-time payments, usage-based billing, checkout sessions, idempotent webhook handlers, customer portal, and invoicing. Covers Next.js, Express, and Django patterns. Use when integrating Stripe for the first time, debugging webhook reliability issues, migrating from a different payment provider, or adding usage-based billing to an existing subscription product.

bestagentkits Bundle

Use when Codex should act as the Unity Architect specialist from Agency Agents. Data-driven modularity specialist - Masters ScriptableObjects, decoupled systems, and single-responsibility component design for scalable Unity projects

bestagentkits Bundle

Use when Codex should act as the Senior Developer specialist from Agency Agents. Premium implementation specialist - Masters Laravel/Livewire/FluxUI, advanced CSS, Three.js integration

bestagentkits Bundle

Use when Codex should act as the Frontend Developer specialist from Agency Agents. Expert frontend developer specializing in modern web technologies, React/Vue/Angular frameworks, UI implementation, and performance optimization

apareek89 Bundle

Turn any topic into a single, self-contained interactive HTML lesson — mental-map first, click-to-deepen modules, (i) glossary tooltips, business + code examples, and a graded knowledge check — OR turn a free-text brief into an installable Agent Skill. Use when the user says "teach me X", "make/build a lesson on X", "explain X interactively", "I want to learn X", "create a course on X", "help me understand X", or "build/make a skill for X", "create an agent skill for X". Topic-agnostic; runs fully on your own Claude with no server, API key, or account.