Web & Frontend

onnokh Bundle

Effect-TS (the `effect` package) conventions for TypeScript — use for any work building, debugging, or reviewing Effect code, whether the user names the APIs or only describes the situation. Triggers: defining a service, its Layer, and its dependencies; root Layer / ManagedRuntime problems (e.g. layers instantiated more than once); Schema.Struct vs Schema.Class, branded IDs, or tagged errors; evolving a persisted/wire schema without a risky migration; runtime config via Config/ConfigProvider; retry/backoff Schedules; caches with TTL; Stream or queue-backed event sources; outgoing HTTP clients with typed errors; and "how do Effect codebases usually handle…" questions. Not for generic side effects, React useEffect, audio/sound effects, Effect scheduler internals, or non-Effect libraries like Zod or Drizzle.

opbr Bundle

Transform raw data, statistics, reports, or plain text into beautiful, interactive HTML infographics and data visualizations. Use this skill whenever the user wants to visualize data, create charts, make an infographic, turn numbers into visuals, display statistics beautifully, build a dashboard, summarize data visually, or create any kind of visual data story. Trigger even when the user just says things like "make this look good", "visualize this", "turn this into a chart", "make an infographic", "create a visual summary", or pastes raw numbers and says "show this". Works with CSV data, copied table data, bullet points of stats, or even descriptive text containing numbers.

opbr Skill

Generate high-quality, publish-ready technical tutorials for beginner, intermediate, and advanced readers. Use this skill whenever the user wants to write a tech article, tutorial, or blog post — especially for platforms like WeChat Official Account or Juejin. Trigger when the user says things like "write a tutorial", "help me write an article", "generate a blog post", "explain X in a structured way", or asks to produce educational content about a programming topic. Covers frontend, backend, algorithms, and AI/ML domains.

openobserve Bundle

Authoring guardrails for building ANY new frontend UI in the OpenObserve web app (web/) — new views, pages, panels, dialogs, feature components, or edits to existing ones. Enforce seven house rules the moment you write Vue/template markup: (1) use OPageHeader for every page/module header, (2) build UI from O2 library components in web/src/lib — never bare HTML controls when an O2 equivalent exists, (3) NEVER write px — always rem, including inside Tailwind class arbitrary values ([320px] is banned; 1rem = 16px, so px/16 = rem and px/4 = the Tailwind step). px is allowed ONLY where it is the genuinely correct unit — hairlines, shadow/ring widths, query conditions, IntersectionObserver rootMargin, zero inside calc()/clamp(), user-facing copy, canvas/email consumers — and there it MUST carry an eslint-disable-next-line local/no-hardcoded-px with a `-- <reason>` at the site, never a side-file exemption (in a <style> block the directive goes inside the block as a CSS comment). The local/no-hardcoded-px rule runs i

openobserve Skill

Playbook for resolving ESLint and TypeScript errors in the OpenObserve web/ frontend (Vue 3 + TS). Rule-by-rule fixes with before/after examples, plus conventions for typing (inline vs dedicated file), unused code, Vue-specific rules, casts, and formatting. Use when fixing lint/type-check errors or writing new web code so fixes are consistent with the codebase standard.

opensource03 Bundle

React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.

packmindhub Bundle

Create, update, and manage GitHub issues using MCP tools. Use this skill when users want to create bug reports, feature requests, or task issues, update existing issues, add labels/assignees/milestones, or manage issue workflows. Triggers on requests like "create an issue", "file a bug", "request a feature", "update issue X", or any GitHub issue management task.

packmindhub Bundle

Clean Architecture for React Native (Expo) with TypeScript and Bun. Use this skill when creating features, refactoring code, or reviewing code in React Native projects. Enforces strict separation between Core (domain), Infrastructure (adapters), and UI layers. Implements ports/adapters pattern, Result pattern for errors, and atomic design for components.

pawel-up Bundle

Guide and audit Node.js CLI application development against 37 established best practices covering UX, distribution, interoperability, accessibility, testing, error handling, development setup, analytics, versioning, and security. Use this skill when building, extending, reviewing, or scaffolding a Node.js CLI — including when someone says "audit my CLI", "review my CLI code", "I'm building a CLI tool", or asks about adding argument parsing, error handling, color output, STDIN, --json flags, exit codes, --version flags, or npm publishing. Applies even when best practices are not explicitly mentioned. Also trigger for "how should I implement X in my CLI" or "what's the right way to do Y in a Node.js CLI". Do NOT use for Node.js backend or API development with no CLI entry point.

perdolique Skill

Nuxt conventions for framework routing, middleware, SSR data fetching, Nitro handlers, request cancellation, runtime config, and typing. Use whenever work touches a Nuxt app or APIs such as `useFetch`, `useAsyncData`, `useRequestFetch`, `$fetch`, or `definePageMeta`, including requests framed only as Vue SSR or typed internal API work.

perdolique Skill

Perd-specific Vue SFC conventions for imports and responsive styling. Use whenever creating or reviewing `.vue` files in Perd. Excludes framework routing and app-level data fetching.

petekass Skill

Scaffolds new web projects per Launchgrade Web Standards 2026. Generates required artifacts (HTML head, robots.txt with AI-crawler defaults, sitemap.xml, security.txt, manifest, favicon set, stack-specific CSP config, 404/500, llms.txt, project AGENTS.md). Triggers on "new website", "setup", "start project", "boilerplate", "required files", "landing page", "neue Website", "Setup", "Projekt starten", "Pflicht-Files".

platformatic Bundle

Integrate, configure, and deploy Platformatic Watt for Node.js and PHP applications. Use when users ask to: - "add watt", "setup watt", "integrate watt", "configure watt" - "deploy with watt", "containerize my app", "deploy to kubernetes" - "migrate to watt", "port my app to watt" - "create watt.json", "configure platformatic" - "wattpm", "wattpm create", "wattpm inject", "wattpm logs" - use wattpm CLI commands, manage running applications - work with Node.js application servers - run PHP, WordPress, or Laravel in Node.js Supports Next.js, Nuxt, React Router, TanStack Start, Vite, Express, Fastify, Koa, Remix, Astro, NestJS, PHP, WordPress, and Laravel.

platformatic Bundle

Build applications that use the Vercel Workflow SDK against a self-hosted Platformatic Workflow Service via `@platformatic/world`. Use when users ask to: - "add workflow to my app", "use workflow sdk", "self-host vercel workflow" - "set up @platformatic/world", "platformatic world", "PLT_WORLD_SERVICE_URL" - "trigger a workflow run", "start a workflow", "resume a hook" - "wire workflow in Next.js", "instrumentation.ts for workflow" - "use workflow with Fastify", "@platformatic/workflow-fastify" - "workflow build --target standalone", "callback handlers", ".well-known/workflow" - "queue handler", "world.start()", "register handlers" Covers `@platformatic/world` (the World adapter), the Vercel Workflow SDK `'use workflow'` / `'use step'` authoring model, framework wiring (Next.js via `instrumentation.ts`, Node/Express/etc. via explicit `world.start()`), and the optional `@platformatic/workflow-fastify` plugin for mounting standalone-build handlers on Fastify. Does NOT cover deploying or operating the Workflow S

portel-dev Bundle

Build, test, validate, and improve Photon MCPs — single-file TypeScript MCP servers. Use for creating photons with @format annotations (table, chart:bar, slides), stateful photons using this.memory for persistent storage, photons with @readOnly/@destructive annotations, custom UI using @ui tags/HTML templates, photons wrapping APIs (Stripe, payments), task scheduler photons with cron, user-configurable settings (protected settings), this.render() for live output, photon build for standalone binaries, mermaid diagrams for photon architecture, editing .photon.ts files, @auth for MCP OAuth identity (this.caller), identity-aware locks for multiplayer/turn-based photons, @format slides for Marp-style presentations. Also use for validating photon UIs (promise checking, visual QA, functional testing), improving photon quality via autoloop, and auditing whether a UI consumes all backend methods. DO NOT trigger for general TypeScript or non-photon MCP.

portel-dev Skill

Automated visual UI issue detection from screenshots. Use EVERY TIME you take a screenshot with agent-browser during UI development. Runs local Qwen3-VL model on Apple Silicon — zero API cost. Catches layout bugs, contrast issues, missing content, alignment problems, and accessibility violations that you'd otherwise miss while focused on one specific fix.

facebook Skill

Best practices for writing idiomatic Relay code. ALWAYS use this skill when writing or modifying React components that use Relay for data fetching. Covers fragments, queries, mutations, pagination, and common anti-patterns. Use when you see `useFragment`, `useLazyLoadQuery`, `usePreloadedQuery`, `useMutation`, `usePaginationFragment`, `graphql` template literals, `react-relay` imports, or `__generated__/*.graphql` files. Also use when asked to explain Relay concepts, debug Relay issues, or review Relay code.

fasalzein Bundle

Binary pass/fail quality gates for UI code — run before shipping any component, page, or feature. Use when the user asks to QA, audit, review, or harden UI, before merging UI work, or after any design implementation to verify it. Covers anti-slop, accessibility, consistency, interaction states, performance, responsive, and live in-browser verification.

filipebraida Bundle

Build production-ready React/Next.js UIs with shadcn/ui components. Full lifecycle - install, customize, compose, debug, optimize. Covers components, forms, tables, theming, animations, and hooks.

filipebraida Bundle

Build AdonisJS 6 + Inertia.js (React) applications from scratch through production. Full lifecycle - setup, pages, forms, shared data, debugging.

fivetaku Skill

Build a new site, deck, or card from scratch using a design.md brief (or synthesize one on the fly). Pairs with insane-design (analysis) and insane-apply. The build skill writes deterministic HTML+CSS into insane-build/{session}/variations/v{N}/ honoring §18 DON'T grep, AI-slop guards, and persona lock-in. Defaults to v1 × 1 (single variation) for token economy; v1/v2/v3 variations are opt-in only. Korean triggers: "빌드", "만들어줘", "새로 만들어", "처음부터", "랜딩 만들어줘", "덱 만들어줘", "카드뉴스 만들어줘", "insane-build". English triggers: "build", "scaffold", "from scratch", "make a landing", "make a deck", "make a card".

flohhhhh Bundle

Use when building, reviewing, or refactoring Sharply Bot features that integrate with the Sharply frontend/app. Apply this skill for Discord command work, command deployment changes, message context commands, Sharply internal API integrations, mirrored bot-doc updates, or any cross-repo change where ownership between `sharply-bot` and `sharply` must stay clean.

floracat526 Bundle

Generate final PNG images from prompt text or prompt files using configured image-generation providers. Supports provider and model selection, aspect ratios, image size, quality presets, reference images, and sequential or batch generation. Use when the user asks to generate, draw, or create images, or when another skill needs direct PNG output instead of HTML/SVG previews.

floracat526 Bundle

Create or revise standalone HTML/SVG architecture diagrams, runtime flow diagrams, sequence diagrams, and PPT-like technical visuals. Use when a user wants human-readable publication-ready diagrams instead of Mermaid, or wants help improving node layout, arrow accuracy, spacing, overlap handling, Chinese labels, or overall visual style for architecture and flow charts.

full-stack-skills Bundle

Provides comprehensive guidance for Avue CRUD component including table operations, form handling, and data management. Use when the user asks about Avue CRUD, needs to implement table CRUD operations, or build data management interfaces.

full-stack-skills Bundle

Provides comprehensive guidance for Avue Form component including form configuration, validation, and dynamic forms. Use when the user asks about Avue Form, needs to create dynamic forms, implement form validation, or work with form configurations.

fulldotdev Bundle

Manages shadcn components and projects — adding, searching, fixing, debugging, styling, and composing UI. Provides project context, component docs, and usage examples. Applies when working with shadcn/ui, component registries, presets, --preset codes, or any project with a components.json file. Also triggers for "shadcn init", "create an app with --preset", or "switch to --preset".

fulldotdev Bundle

Guides Fulldev client projects using Astro, Fulldev UI, content/schema/layout architecture, reusable components, blocks, theming, and shadcn-compatible Fulldev registry installs. Use when working in Fulldev client projects, installing or composing @fulldev components, shaping content-driven Astro pages, or deciding where project responsibilities belong.

fulldotdev Skill

Audit and update the existing Fulldev Astro UI registry against current data-slot and shadcn/ui Base UI Vega. Use for periodic whole-library upstream parity passes, not ordinary single-component edits.

getstream Skill

Measure React Native performance on-device for stream-chat-react-native — Hermes CPU profiles, deterministic call/listener counting, component render profiling, and memory/jank capture. Use when asked to benchmark a change, prove or disprove a perf claim, compare before/after, find what re-renders or what's heavy on the JS thread, or "do some perf testing". Drives the SampleApp on a connected Android device via the perf/ toolkit. Read this BEFORE measuring — it encodes which instrument to pick and the methodology mistakes never to repeat.

miantiao-me Bundle

Use when the user wants to build, edit, or redesign screens for TRMNL e-paper devices. Handles dashboards, KPI displays, item lists, data tables, quotes, rich text, charts, and any screen layout — converting content briefs, data descriptions, or plain HTML into `<x-trmnl::...>` Blade component markup. Also use when they mention "trmnl-blade", "TRMNL Framework", "e-paper screen", or describe content for an e-ink display, even without naming TRMNL directly.

micheleangioni Bundle

Create a new fullstack Next.js. Use this skill when the user asks to create a new Next.js project or application.

mickzijdel Skill

Full visual review of non-trivial UI work — a scoped breakpoint/state/theme matrix, a measurement sweep, a coverage ledger, and a defect report a fix agent can act on. Use after implementing or changing non-trivial product UI (a shared component, a layout, a new screen) before reporting it done, and whenever the user asks for a visual review, visual QA, screenshot review, or polish pass. For a single-file tweak use vischeck:verify instead.

mickzijdel Skill

Visually verify UI changes by taking authenticated screenshots of the local dev server, with a measurement sweep for what shouldn't be eyeballed. Use after editing any view, template, component, or layout file. For non-trivial UI work spanning several screens, breakpoints, or states, use vischeck:review instead. If screenshot redirects to a login page, invoke vischeck:setup-auth first.

mindsdb Skill

MANDATORY reading before building ANY HTML dashboard, chart, plot, interactive report, or browser-based visualization (create_artifact type="html-app", or the frontend of a fullstack app). Contains the full HTML output contract: self-contained file rules, Apache ECharts setup, dark theme, layout/design standards, and large-dataset handling. Recall it BEFORE writing the first line of dashboard HTML. When in doubt, recall it.

mindsdb Skill

MANDATORY reading before writing ANY backend, API, server, or fullstack application code (create_artifact types fullstack-stateless-app / fullstack-stateful-app, or anything that will be launched with launch_backend). Contains the complete hard contract: the canonical FastAPI+Mangum backend.py template, SECRETS handling, /api/* route prefix rules, static/ frontend layout, requirements.txt, and the launch/preview workflow. Building a backend without recalling this skill first WILL break launch and deployment. When in doubt, recall it.