Web & Frontend

libreqoe Bundle

Project workflow for invoking the local review sub-agents Thomas, Helen, Beck, Jonas, The Reaper, and Heckler during LibreQoS coding sessions. Use when code changes need recent-diff review for DRY/duplication, slop detection, Rust quality, accessibility, test coverage, scope control, and algorithmic sanity.

locaweb Skill

Two-layer automated testing strategy for Go + React web applications. Covers backend unit/integration tests (Go) and frontend component tests (Vitest). Tests are written in tandem with application code — every handler gets a test file, every interactive component gets a test file. Use this skill whenever the user asks to test, run tests, add tests, or verify the application.

locaweb Skill

Create distinctive, production-grade frontend interfaces with high design quality. Use this skill when the user asks to build web components, pages, artifacts, posters, or applications (examples include websites, landing pages, dashboards, React components, HTML/CSS layouts, or when styling/beautifying any web UI). Generates creative, polished code and UI design that avoids generic AI aesthetics.

loft-sh Skill

Manages the Kubernetes compatibility matrix data and React component. Use when adding/removing K8s versions, updating conformance test results, or documenting known issues.

loft-sh Skill

Audit and fix the vCluster docs feature table that the FeatureTable component renders from src/data/features.yaml. Covers three facets - sidebar tier badges (FREE/ENTERPRISE) versus plan assignments in the plans repo, feature docs_url link targets, and which FeatureTable rows each page imports. Use when verifying badges, checking that feature links resolve to the right page, or confirming a page surfaces the correct rows.

lubluniky Bundle

UI/UX expert for design systems, accessibility, and avoiding generic AI-generated design patterns

mae616 Skill

Astroプロジェクトの設計・実装・レビューを、HTML中心/Islands Architecture/クライアントJS最小化の思想で整理する。Astro、Islands Architecture、SSG/SSR選択、コンテンツサイト構築、パフォーマンス最適化、JS削減、マルチフレームワーク統合、.astroファイルに関する相談で必ず使うこと。ユーザーが「静的サイト」「ブログ」「ドキュメントサイト」「ランディングページ」と言った場合も、Astroが技術スタックに含まれていれば適用する。

mae616 Skill

React/Next.jsプロジェクトで、UI=計算モデル（コンポーネント/状態/レンダリング）を軸に、設計・実装・レビュー・性能改善の判断を整理する。React、Next.js、JSX、コンポーネント設計、useState/useEffect、状態管理、Server Components、SSR/SSG/Streaming、App Router、バンドル最適化、再レンダリング問題に関する相談で必ず使うこと。ユーザーが「コンポーネントの分割」「stateの置き場所」「パフォーマンスが遅い」「RSCの使い分け」と言った場合にも適用する。

mae616 Skill

Svelte/SvelteKitプロジェクトにおいて、UI=状態の直接的な反映という思想を軸に、コンパイル時最適化・状態管理・レンダリング・配信量の設計を整理する。Svelte、SvelteKit、.svelteファイル、リアクティビティ、$state/$derived、コンパイラ最適化、軽量UI、store設計、配信量削減に関する相談で必ず使うこと。ユーザーが「Svelteでアプリを作りたい」「ランタイムを減らしたい」「仮想DOMなしのフレームワーク」と言った場合にも適用する。

mae616 Skill

Three.js（WebGL/3D表現）のScene-Camera-Renderer三位一体と手動メモリ管理を軸に、ウェブ3Dの設計・実装・パフォーマンス最適化を整理する。Three.js、WebGL、React Three Fiber（R3F）、3Dシーン構築、メッシュ/マテリアル/テクスチャ、メモリリーク、dispose()、インスタンシング、シェーダー、GLTFローダーに関する相談で必ず使うこと。ユーザーが「ブラウザで3D」「WebGLで表示」「3Dモデルをウェブに載せたい」「パーティクルエフェクト」と言った場合にも適用する。

mae616 Skill

Tailwind CSSをutility-first（早すぎる抽象化を避ける）思想で運用し、UI実装の認知負荷を下げながら一貫性と保守性を保つための設計・レビュー・リファクタ判断を整理する。Tailwind CSS、utility-first、CSS設計、クラス肥大化、デザイントークン、コンポーネント化の境界、レスポンシブ設計、ダークモード、tailwind.config、@applyの使い方に関する相談で必ず使うこと。ユーザーが「クラスが長すぎる」「CSS設計を統一したい」「デザインシステムを作りたい」と言った場合、Tailwindが技術スタックに含まれていれば適用する。

magicare-ai Bundle

Maximizes legitimate PDPM NTA (Non-Therapy Ancillary) comorbidity capture by parsing hospital referral/discharge documentation for the ~50 CMS-published NTA conditions and services, producing an evidence-backed capture worksheet with point totals, tier, and a documentation-request list. Also audits a completed MDS against the packet to find missed points. Use whenever the user mentions NTA, non-therapy ancillary, comorbidity capture, missed NTA points, PDPM component scoring, or MDS Section I/O/K/M coding for reimbursement — or asks to review a hospital packet, H&P, med list, or discharge summary for conditions that affect SNF payment.

majdghithan Bundle

Version-aware best practices for Laravel Livewire (Caleb Porzio's full-stack framework), covering v1 through v4. Use whenever building, reviewing, or upgrading Livewire components, wire:model bindings, actions, events, validation, lifecycle hooks, or single-file/island components. ALWAYS detects the installed Livewire major version first, because behavior flips significantly between majors (wire:model default changed in v3; component model + wire:model bubbling changed in v4). Covers every upgrade path (v1->v2, v2->v3, v3->v4).

onflow Bundle

Guide for setting up and configuring Flow blockchain projects. Covers flow.json structure (networks, accounts, contracts, dependencies, deployments), FCL frontend integration with React, Flow CLI workflow, emulator setup, testnet/mainnet deployment, environment-based configuration, and multi-network strategies. TRIGGER when: setting up a Flow project, configuring flow.json, setting up FCL, deploying contracts, switching networks, debugging deployment issues, "flow init", "flow emulator", "flow project deploy", "flow.json", "FCL config", "testnet deploy", "mainnet deploy", "contract deployment", "network configuration", "flow dependencies install", "emulator setup", "how to deploy to testnet", "configure FCL with React". DO NOT TRIGGER when: writing Cadence code or asking about syntax (use cadence-lang), building token contracts (use cadence-tokens), generating new contracts (use cadence-scaffold), auditing code (use cadence-audit).

ontology-of-everything Bundle

Builds a PPT / 胶片 / 汇报 / 授课 deck as a plain single-file 1920×1080 HTML in a pluggable style (Huawei 华为 official light/dark, Apple, generic), confirming outline and per-page table first; optional PPTX export. Use when the user explicitly invokes $html-slides; not for general slide-design questions.

ontology-of-everything Bundle

Builds evidence-only Kimball semantic layers for enterprise knowledge from APIs, CLIs, or tables/databases with an HTML decision workbench; emits OKF/YAML. Use when 企业知识、知识建模、KM、semantic-km-creator、semantic-creator、semantic layers, dimensional models, ontology, OKF, 语义层、接口转语义、维度建模或本体.

openshift Skill

Run tests (frontend, backend, unit, or all)

openshift Skill

Generate React Testing Library tests following OCP Console best practices

org2ai Bundle

ORGII-specific React 19 performance review and implementation guidance, adapted from Vercel Engineering. Use for React performance, re-render, async waterfall, bundle, heavy dependency, virtualization, high-frequency event, Context/provider, or store-subscription work. Do not trigger for styling, copy changes, or routine single-file UI bug fixes without a performance concern.

penpot Bundle

Semantically rename Penpot layers to HTML element names (nav, header, main, section, article, button, input, label, h1-h6, p, ul, li, img) or kebab-case role names, replacing auto-generated names like 'Rectangle 12'. Use to clean up layer naming, prepare a file for handoff, or as a precondition for accessibility audits (heading hierarchy) and design-to-code review (semantic mapping). Triggers: 'rename layers', 'semantic layer names', 'rename to HTML elements', 'clean up layer names', 'fix layer naming', 'add semantic names to layers', 'prepare layers for handoff'.

penpot Bundle

Document a Penpot design for handoff by building a clean annotation layer BESIDE the design (never on top of it): a left context card (the 'How might we' goal, business rules, links, status, feedback wanted/not), numbered pin markers on the UI, matching observation/recommendation note cards on the right, and optional tooltips — all wrapped in a single hideable group so the clean design can be revealed. Reuses an annotation component kit + tokens if present; proposes and creates a minimal one if missing. NOT for auditing (use penpot-audit-*) or renaming layers (use penpot-rename-layers). Triggers: 'document this design', 'annotate this screen', 'prepare this for handoff', 'add design annotations', 'explain this flow for devs', 'add observation notes', 'create a critique card', 'spec this screen for handoff'.

penpot Bundle

Build and maintain Penpot components with COMPLETE variant matrices — sizes, hierarchies, and all interactive states (default/hover/pressed/focus/disabled) — fully tokenized and correctly named. Use to create a new component with variants, fill in missing states, or normalize an existing component. Triggers: 'create a Button component with variants', 'build component variants', 'add hover/pressed/disabled states', 'make a variant matrix', 'turn this into a component with sizes', 'normalize this component'.

penpot Bundle

Audit a Penpot design against WCAG 2.1/2.2 AA (optionally AAA) and produce a structured severity report: color contrast, touch/target sizes, text alternatives, heading hierarchy, and keyboard/focus order. Proposes fixes — does not auto-apply. Also serves as the Evaluator in the brief-to-screen loop. Triggers: 'check accessibility', 'accessibility audit', 'WCAG check', 'contrast audit', 'a11y review', 'check color contrast', 'is this accessible'.

penpot Bundle

Review a Penpot design against its implemented code (a source component or Storybook story) and emit a structured DRIFT report. Use when an engineer needs to confirm the build matches the design: extract HTML/CSS from a selection, map its tokens/structure/states to the code component, diff them, and list what each side is missing with severity and a reconciliation. Degrades gracefully to a design-system-token check when no code source is supplied. Triggers: 'design to code review', 'does my code match the design', 'design code parity', 'compare Penpot to my component', 'check this against Storybook', 'extract HTML/CSS from this selection', 'find design drift', 'design implementation diff'.

peteski22 Bundle

Validate TypeScript/React code against style and architectural conventions

printpractical Bundle

Use on a brownfield codebase that needs a CONTEXT.md hierarchy. After intake, reverse-engineers the system and component architecture from existing code to produce root and component CONTEXT.md files. Use when that context would materially help; architect and triage do not require it. Also use when CONTEXT.md files are severely out of date.

printpractical Bundle

Use for behavior-preserving refactors, cleanup, technical debt reduction, or code-quality audits across a named path, component, layer, package, or the whole stack. Audits first, requires explicit user selection, then executes small verified batches with an independent review. Routes behavior changes and firm-contract changes to architect.

quangpl Bundle

Build polished Chrome extension UIs (popup/sidepanel/options). Analyze existing UI, suggest improvements, set up design systems, enforce a11y and UX best practices.

revenantworks Bundle

Defines a brand and its voice — identity, naming, palette, taglines, firewall — and applies them on request across skills, packs, artifacts, docs, and repos. Ships neutral — no brand exists until one is built or handed in; outputs spec-clean. Trigger to create, define, rebuild, or consolidate a brand, voice, or style guide; to apply a brand or voice to a built skill, artifact, repo, or doc; to audit a repo, tree, or skill set for drift — wrong names, off-palette colors, off-voice copy, stale handles or taglines; to export a voice profile or HTML brand-guide card; or say brandwright build / apply / audit / export. Applying a voice to one message is commwright's via the exported profile; a whole skill set's rebrand is a handoff — brandwright defines the identity, skillwright port propagates it.

revfactory Skill

마크다운 보고서(특히 SK하이닉스 분석 보고서)를 모던·세련된 인터랙티브 웹페이지로 변환하는 오케스트레이터. design-lead·visualization·frontend·motion·QA 5인 팀을 조율해 데이터 시각화 차트, 글래스모피즘 UI, 배경 애니메이션(WebGL/Canvas), 마이크로 인터랙션, 다크 모드, 반응형 레이아웃을 갖춘 정적 웹사이트를 생성. 트리거: '보고서를 웹페이지로', '웹사이트로 만들어줘', 'HTML로 변환', '인터랙티브 웹페이지', '모던 웹사이트 빌드', '데이터 시각화 페이지', '하이닉스 보고서 웹', 'report to webpage', '리포트 시각화'. 후속 작업: '디자인 수정', '차트만 다시', '배경 애니메이션 변경', '모션 강도 낮춰', '컬러 테마 바꿔', '반응형 수정', '특정 섹션만 재빌드', '이전 결과 개선' 시에도 반드시 이 스킬을 사용.

revfactory Skill

디자인 토큰 기반의 HTML 시맨틱 마크업, 모듈화된 CSS, Vanilla JS 인터랙션, 반응형 레이아웃, 다크/라이트 모드, 스크롤 기반 네비게이션을 구현하는 프론트엔드 빌드 스킬. 정적 사이트(no build step) HTML/CSS/JS 빌드 요청 시 반드시 사용.

revfactory Skill

웹페이지의 디자인 토큰 준수, 데이터 정확성(보고서 원본 vs 페이지 표시값 1:1), HTML 시맨틱·접근성(WCAG AA), 반응형(320/768/1280/1920), 성능, 모션 적정성, 브라우저 호환성을 점진적·경계면 교차 비교로 검증하는 스킬. 웹페이지 QA·검증·정합성 점검 요청 시 반드시 사용.

strapi Skill

Adds a new language/locale to the application. Involves Strapi admin config, Next.js i18n routing, and translation files. Use this skill whenever the user mentions adding a language, translation, i18n, multilingual support, locale, or internationalization — even if they don't explicitly say 'locale'. Also triggers on: add language, add locale, new language, new translation, support another language.

strapi Skill

Scrape a strapi.io page, extract content for specific components, transform to match local Strapi schemas, and seed into local Strapi via MCP. Schema-driven and resilient to evolving schemas. Triggers: seed content, scrape strapi, import content, seed page, seed component.

strapi Bundle

Copy a component from strapi.io by extracting structure and computed styles via Playwright, mapping to local design tokens, and generating a full-stack component (Strapi schema + React + population config). Triggers: copy component, copy section from, replicate from strapi, clone component.

strapi Skill

Review recently created page-builder components, identify reusable JSX/Tailwind patterns, extract them into elementary components, and update the component registry. Use as a checkpoint between batches of copy-component migrations. Triggers: consolidate patterns, extract reusable, review components for patterns, checkpoint review.