Web & Frontend

gloom-sh Bundle

Comprehensive OpenTUI skill for building terminal user interfaces. Covers the core imperative API, React reconciler, and Solid reconciler. Use for terminal OpenTUI development tasks including components, layout, keyboard handling, animations, and testing. Do not use for Electrobun/desktop-web-only window chrome, CSS, or browser renderer work unless terminal OpenTUI behavior is also in scope.

gloom-sh Skill

Testing Gloomberb at every level: CLI commands for fast data/integration checks, OpenTUI's built-in test harness for component tests, and tmux for full end-to-end terminal TUI testing. Use this skill when you need to verify terminal TUI features, write OpenTUI regression tests, or smoke-test the terminal app. Do not use it for Electrobun/desktop-web-only visual or window chrome work unless tmux/OpenTUI coverage is explicitly needed.

gntc-labs Skill

Deploy a static site or Next.js app to VibeHost and get a private shareable URL. Use when the user wants to ship, host, preview, or publish a built frontend or Next.js app.

gnurio Bundle

Render a real, publication-ready data graphic (SVG or HTML) that obeys Tufte's principles — minimal ink, range-frame axes, direct labels, honest proportions. Use when someone wants to design, build, create, draw, plot, or visualize a chart or graph the Tufte way, or to rebuild a chart after a critique found problems. This is the skill that outputs an actual chart file. Not for critiquing an existing graphic (`tufte-critique`).

govindmaheshwari2 Bundle

Execute flow YAML files as end-to-end tests against web, Android, and iOS apps. Drives platform drivers (agent-browser, adb, idb) step-by-step, captures screenshots and video, and produces a structured report. Supports declarative steps (tap, type, scroll, assert, screenshot, wait) and AI-driven steps for dynamic UI interactions. Key capabilities: - Multi-platform: web (agent-browser), Android (adb), iOS (idb) - Conditional steps with when:/else: for platform-specific flows - AI steps with goal-directed execution, sub-steps, and full iteration logging - Verify steps: AI-evaluated plain-language checks with pass/fail per check - iOS reliable tapping: uses idb ui describe-point to get true hit-test frames - Video recording on all platforms; automatic screenshots after every step - Generates results.json + viewer.html report even on failure or cancellation

grafana Skill

Build queries with the Infinity data source — the query types (JSON, CSV, TSV, XML, GraphQL, HTML, UQL, GROQ, Google Sheets, Series, Transformations), the parsers (Frontend/simple, Backend JSONata, JQ, UQL, GROQ) and which support alerting, the sources (URL, Inline, Reference, Azure Blob, Random walk), output formats (table, timeseries, logs, trace, node graph, dataframe), root selector and columns, computed columns/filters/summarize, pagination, and template variables. Use when a user asks how to query Infinity; how to fetch JSON/CSV/XML/GraphQL/HTML from a URL or inline; how to select rows and columns; how to transform data with UQL/GROQ/JSONata/JQ; how to make a query work with alerting; how to paginate; or how to use variables in a query.

grinchinc Bundle

Apply an opinionated personal UI implementation system on top of good-ui for web apps and product interfaces, including fully authored visual styling, real icon assets, 4px/8px spacing, standardized control sizes, edge clearance, expanded hit areas, complete interaction states, intentional focus behavior, continuity-preserving motion, shadcn-first primitives, production component galleries, temporary dev overlays, Git checkpoints, and optional OpenRouter-backed features. Use for new UI, substantial UI revisions, component-system work, interaction polish, or in-product design exploration.

handsontable Bundle

Use this skill whenever the user asks about Handsontable — a JavaScript data grid component with spreadsheet-like UX. Triggers include: mentions of "handsontable", "HotTable", "data grid", "@handsontable/react-wrapper", spreadsheet component in React/Angular/Vue, HyperFormula formulas inside a grid, cell types (dropdown, checkbox, date, numeric) in a grid context, or questions about Handsontable theming, plugins, hooks, configuration options, or column/row features. Also trigger when the user wants to add an editable spreadsheet-like table to a web app, or asks about copy/paste, sorting, filtering, frozen rows/columns, merged cells, or context menus in a grid. This skill covers Handsontable used with any framework (React, Angular, Vue 3, vanilla JS) and HyperFormula as the Formulas plugin engine inside Handsontable. Do NOT use this skill for headless/standalone HyperFormula usage without Handsontable — that is covered by the separate "hyperformula" skill.

hanfangyuan4396 Bundle

当需要制作文字卡片图片时使用，包括生成卡片 HTML，并调用底层 HTML 转图片能力输出最终图片。适用于公众号长文封面、小红书/小绿书图文封面等场景。

hanfangyuan4396 Bundle

当需要把 HTML 文件渲染成图片时使用，包括读取 HTML 文件、执行渲染，并将生成的图片保存到本地文件。

harehare Skill

Fetches web pages and extracts structured data using mq's toolchain (mq-crawl for fetching/crawling/JS rendering, mq for HTML-to-Markdown selector-based extraction, http() for in-query requests). Use when the user wants to scrape a URL, pull structured data out of a webpage, crawl a site, or turn HTML into Markdown/JSON — an alternative to a one-off curl-plus-parser script.

hazat Skill

Show native UI from scripts and agents — dialogs, forms, visualizations, floating widgets, cursor companions. Supports macOS, Linux, and Windows. Use when you need to display HTML to the user, collect input, show a chart, render markdown, or create any visual interaction without a browser.

hermai-ai Bundle

Build a private code based preview of a local React or Next.js dashboard across Hermai's bundled customer brand test pack. Use when a developer wants to test automated customer branding, inspect dashboard components, choose safe brand surfaces, or review a white label experience without login, API credits, or source upload.

hicay Bundle

Build and deploy forms without a backend using Formcarry as the form endpoint. Use this skill when the user mentions "formcarry," "form backend," "form endpoint," "contact form," "no backend form," "form without server," "collect form submissions," "form API," "HTML form submission," "form handling," "lead capture form," "feedback form," "survey form," "registration form," or wants to add a working form to any website, landing page, or app without building server-side code. Covers HTML forms, AJAX submissions (React, Vue, Fetch, Axios), file uploads, spam protection, webhooks, auto-responders, field validation, Stripe payments, and the Formcarry REST API.

letstri Bundle

Per-primitive API for Seitu: createStore, createComputed, createSchemaStore, createSubscription/createReadableSubscription, createDebounced(Fn), createThrottled(Fn), createWebStorage(Value), createIndexedDb(Storage/Table), createMediaQuery, createIsOnline, createScrollState, and the React, Vue, Solid, and Svelte useSubscription/Subscription bindings. Use once you know which primitive or framework binding you need; read seitu-overview first for the mental model and decision tree.

lexmount Bundle

Use Lexmount WebFetch through webfetch-cli for lightweight public page extraction and DOM dump tasks. Prefer this skill when the task needs structured extraction or rendered HTML capture without creating a live remote browser session.

locize Bundle

Takes an app from hardcoded strings to a localized, continuously translated one with i18next (Locize optional): stack detection, config, wrapping strings in t(), key extraction, Locize sync, and AI translation. Use when the user asks to add or set up i18n, internationalization, localization, translations, or multi-language support, including phrasings like "add i18n", "internationalize my app", "make my app multilingual", "make my app translatable", "localize my app", "find hardcoded strings", "wrap my strings", and library-specific ones like "set up i18next", "add react-i18next", "use next-i18next". Also use when the user names languages they want to support ("I want German and French", "support more languages"), when an app already has i18next but strings are still hardcoded, or when translations need to move to a managed backend. Do not use for translating or reviewing strings in a project whose i18n is already set up.

londey Skill

Component boundaries, interfaces, bound SVA properties, and conformance-harness discipline for SystemVerilog projects

lottiefiles Bundle

Use when building or modifying plugin UI with @lottiefiles/creator-plugins-ui. Applies when adding React components in src/, using Button/Select/Slider/Dialog/Toast/NumberInput or other library components, setting up Tailwind CSS theming or dark mode, using the cn() utility, troubleshooting Base UI data attributes or missing styles, or updating the plugin UI theme to match Creator's interface theme.

lottiefiles Bundle

This skill should be used when developing LottieFiles Creator Plugins with the Creator Plugin API. It applies when (1) creating a new Creator Plugin from scratch, (2) working on plugin code in plugin.ts, ui.html, plugin/ or src/ directories, (3) using the creator global API for scene manipulation, (4) building plugin UI (HTML or React) that communicates with a plugin sandbox, or (5) the user mentions "Creator plugin", "LottieFiles plugin", "creator API", or works with files like plugin.ts, ui.html, or manifest.json in a plugin project context. Triggers on requests like "create a plugin", "add a feature to my plugin", "import assets into Creator", or "animate a layer".

lutzseverino Bundle

Opinionated, standalone React component architecture guidance for React projects. Use when reviewing or designing component boundaries, deciding whether UI should stay inline, become a local helper, become a component boundary, or become another boundary kind, surfacing credible wider React architecture options, classifying components as presentational, interactive, or container, applying compound, headless, or polymorphic patterns, setting packaging and ownership rules, or reasoning about providers, pages, forms, loading, and error shells.

lynx-family Bundle

Provides authoritative guidance for Lynx development involving pages, templates, components, CSS, layouts, elements, web migration, rendering or styling bugs, and code review. Applies to *.ttml, Lynx *.tsx, and all Lynx-specific files, and requires searching the installed API docs before acting.

magallon Bundle

Generates and manages end-to-end tests for critical user flows in any web project. Covers test design, Page Object Model, selector strategy, wait patterns, auth state reuse, test data management, network mocking, visual regression, accessibility testing, flaky test diagnosis, and CI/CD pipeline configuration. Stack-agnostic — adapts to Playwright, Cypress, Selenium, Laravel Dusk, Capybara, or any browser automation framework. Use this skill when the user asks to write E2E tests, automate browser tests, test user flows end-to-end, fix flaky tests, set up visual regression testing, configure E2E in CI/CD, debug failing E2E tests, or test across multiple browsers. Also triggers when the user mentions Playwright, Cypress, browser testing, smoke tests, critical path testing, or end-to-end test automation. Works with testing-strategy — use testing-strategy first to decide WHAT to test, then this skill to implement the E2E tests.

magallon Bundle

Analyzes any web project and recommends a comprehensive testing strategy: what to test, which test type to use (unit, integration, component, E2E), how to prioritize coverage, and what mocking approach to follow. Can also generate tests based on its recommendations when the user asks. Use this skill when the user asks "what should I test", "create a testing strategy", "what tests does this project need", "analyze test coverage gaps", "which parts of my code need tests", "help me prioritize testing", "review my tests", "generate tests for this module", or any request to plan, evaluate, or create tests for a codebase. Also triggers when the user mentions testing pyramid, test coverage, TDD, test-driven development, or asks about the right type of test for a piece of code.

magic-link-sso Bundle

Choose and coordinate the right Magic Link SSO integration for supported web frameworks. Use when an agent needs to implement, explain, compare, or troubleshoot magic-link or optional email OTP sign-in in Angular SSR, Fastify, Next.js App Router, Nuxt SSR, or Django projects, when the framework is unclear and must be inferred from the codebase, when a static or CSR-only app should be protected through Magic Link SSO Gate, or when the agent should choose the correct bundled framework guide instead of re-deriving the integration from scratch. Assume the project has access to the Magic Link SSO server and, where relevant, the published framework packages on npm or PyPI unless the repo clearly indicates a local workspace or unreleased package build.

maotoumao Bundle

从零开始开发 MusicFree 桌面版主题包的完整指南。 当用户要求编写、创建、设计 MusicFree 桌面版主题包，或要求根据参考图/色彩/风格关键词生成主题时触发。 涵盖：CSS 变量体系、色彩设计范式、静态主题、动态 iframe 主题、资源优化、打包测试、提交到主题市场等完整流程。 本 Skill 面向 AI 执行，指导 AI 与社区贡献者（可能无前端经验）协作完成主题包开发。

internet-development Skill

Construct a new app page from scratch using this repo's component system. Use when the user says "build a new page for X", "create a settings page", "add a dashboard for Y", "scaffold an app screen", or otherwise wants a Next.js page assembled from the project's elements/components/patterns. Produces a route under pages/, picks the right Page shell + chrome + layout, wires up modals if needed, and (if it's a gallery showcase) registers it in common/constants.ts.

isatimur Bundle

Create Excalidraw diagrams as editable `.excalidraw` JSON that make a visual argument — architecture, flowchart, sequence, state, ER, timeline, swimlane, quadrant, loop/flywheel, layers, nested, tree, org chart, venn, pyramid, process, medallion, data flow, IT current-state, evidence/protocol explainers, before/after comparisons, and charts — with themed brand skins, a taste gate, progressive type refs, and a mandatory render-inspect loop. Prefer this over static HTML/SVG or Mermaid-slop when the diagram must open in Excalidraw/Obsidian/VS Code, prove claims with evidence artifacts, or iterate until it looks right. Triggers on "make a diagram", "draw the architecture", "visualize this", "excalidraw", "flowchart", "system design diagram", "sketch this out", "whiteboard it", or brand-matched technical diagrams.

itwin Skill

Instructions and best practices for building/modifying a UI Tree component displaying iModel data in a hierarchical way.

ivy-interactive Bundle

Clone a repo, independently analyze its stack, run the Ivy.StackAnalyzer CLI plus three reference tools (specfy/stack-analyser, microsoft/component-detection, github-linguist) via one helper script, compare them, and record disagreements as suggestion files — including whether the report yields a clean stack hash. Use when the user types /review-stack-analyze <repo-url> or asks to review/validate the analyzer's output against a real repository.

iwasa-kosui Bundle

Kamae (構え) — robust server-side TypeScript design. Functional domain modeling with discriminated unions, pure state transitions, Result types, schema-validated boundaries, and PII protection. TRIGGER when: writing TypeScript domain models, use cases, repositories, state transitions, error handling, boundary validation, or PII handling on the server side; designing types for business logic; implementing entity/value-object semantics in TS. SKIP: frontend React/Vue components, browser code, build tooling, code generation scripts, pure infrastructure-as-code; code unrelated to domain logic.

iwasa-kosui Bundle

Adversarial code review of server-side TypeScript for adherence to the kamae principles (discriminated unions, branded types, Result error handling, boundary validation, PII protection). TRIGGER when: reviewing a pull request, audit, or quality check of TypeScript server-side code involving domain models, repositories, use cases, business logic, or boundary code. SKIP: frontend code review, infrastructure-as-code review, test-only review, code review unrelated to domain logic.

jackwener Bundle

Grade a team's frontend implementation against its spec on 10 weighted dimensions, producing a markdown report + JSON summary with evidence.

jamesrochabrun Bundle

Render UI variants or any visual — mockups, reports, diagrams, dashboards — into AgentHub's Studio panel beside this session, on a scratch surface that never touches project files. Use when the user asks to see, compare, mock up, or explore options, versions, or variants of a component or screen, asks "what would it look like", or wants a rendered document. Also invoked explicitly as /agenthub-studio.

jasny Bundle

Migrate React + TypeScript + Tailwind codebases from utility-class-heavy feature code to CVA-based styling and normalized ui/ component wrappers. TRIGGER when: user asks to convert inline Tailwind class logic to class-variance-authority, normalize raw primitives into reusable ui components, or execute large incremental styling migrations with behavior preservation and mode-controlled visual drift policy. DO NOT TRIGGER for redesigns, visual refreshes, or generic styling advice.

jason8-8 Bundle

Session-start ritual and close-out loop for one focused work session. Trigger whenever the user says "start working", "let's work", or any close variant meaning they are sitting down to work now. Also trigger for close-out when, after a session, they say "done", "session done", "wrap up", or report what they finished. Pulls {{TASK_MANAGER}} and {{CALENDAR}}, sweeps rotting tasks into a numbered "Needs a call" strip, asks up to three micro-questions, then recommends a ranked pick with the work split between you and Claude and per-task time estimates on an HTML session card. On "go": starts delegable drafts and writes a calendar block. At close-out: ticks off completed tasks, renames the calendar block to what actually happened, and logs the session to {{SESSION_LOG}}. Do NOT trigger for "plan my day" or "morning briefing" — whole-day planning is a different job.