Web & Frontend

qbs784 Skill

Use when writing or reviewing acceptance criteria, a definition of done, or the exit conditions for a piece of work; when a requirement reads as an adjective rather than something observable; or when declaring what a component's behavior means. DO NOT invoke to judge whether a guard already written can fail — route that to ledger:proving-the-regression. DO NOT invoke to judge what an already-green signal proves — route that to ledger:what-counts-as-evidence.

tacticaldoll Bundle

Use when an agent needs to explore intent, requirements, and direction through dialogue before any building; holds a no-stakes, codebase-grounded thinking-partner stance that surfaces options and tradeoffs one question at a time and resists premature convergence, rather than implementing, designing component structure, or planning the work.

tacticaldoll Bundle

Use when an agent needs to design component boundaries for a feature or system before the code exists; partitions responsibilities into single-purpose components with minimal interfaces and an acyclic dependency direction, then pressure-tests the boundaries rather than editing code, splitting an existing tangled unit, or extracting a separate repository.

tacticaldoll Bundle

Use when an agent needs to turn a goal into an ordered, verifiable implementation plan before coding; slices the work into the smallest independently verifiable increments, sequences them by dependency and risk, and names each step's acceptance check rather than writing code, designing component structure, or planning a behavior-preserving split.

tkolleh Bundle

Trigger on: check contrast, WCAG contrast, accessible colors, readable text color, fix low-contrast, dimmed text color, palette accessibility, pastel color, textcolor for background, make this color readable, UI theme contrast, Neovim highlight contrast. Evaluate, fix, and generate accessible fg/bg pairs with the pastel CLI and color-accessibility/main.py (WCAG AA/AAA). Use whenever the user changes colors for UI, CSS, terminal, or editor themes — do not guess contrast; measure it.

trk Skill

Use when designing, structuring, or rendering HTML for ProcessWire Admin interfaces, custom Process modules, or Inputfields.

trk Skill

Use when creating independent frontend rendering systems explicitly extending the ProcessWire Markup module ecosystem.

vinvcn Skill

构建生产级 UI。当构建或修改面向用户的界面时使用。创建组件、实现布局、管理状态，或输出需要看起来和感觉上都是生产级而不是 AI 生成时使用。

vipincode Bundle

Write tests on demand for whatever the user points at — backend services, controllers, routes, and integration paths, or frontend components, hooks, schemas, and bound screens. Use this ONLY when the user explicitly asks for tests — "write tests for auth.service.ts", "test the product module", "add component tests for product-card.tsx", "cover the create-product form", "test the useProductsQuery hook", "test this binding", "write tests for the slice I just built". It is a standalone utility run manually — never auto-chained from module-planner or module-builder, though module-builder will suggest it once a slice lands. It infers the domain from the target's path, reads ARCHITECTURE.md for conventions (the real response envelope, error model, data-fetching approach) and MODULE_REGISTRY.md for which collaborators are real shared pieces worth mocking faithfully, detects the installed test framework and mocking setup from package.json rather than assuming one, and reads the slice's Testing checklist from _docs/fe

vipincode Bundle

Scaffold a new production-grade Next.js (App Router) + TypeScript + Tailwind + shadcn/ui frontend from scratch, wired to a separate API backend (e.g. Express) via a BFF proxy, with axios, Zod, TanStack Query, and React Hook Form. Use this whenever the user wants to start a new Next.js / React frontend, bootstrap a web client/UI, set up a shadcn starter, or initialize a frontend project — even if they only say "new frontend", "Next.js starter", "React app", "admin dashboard UI", or name the stack loosely. It scaffolds the infrastructure ONCE per project and emits the two source-of-truth files (ARCHITECTURE.md and MODULE_REGISTRY.md) that module-planner, module-builder, test-writer, and code-review depend on. Do NOT use this to add a feature/page to an existing project (that is module-planner + module-builder) or to write tests. This scaffolds a Next.js + React frontend specifically — do NOT use it to bootstrap a backend/API (that is express-ts-bootstrap) or projects in other frontend stacks (Vite/CRA/Remix/Vue

vipincode Bundle

Scaffold a new production-grade Express.js + TypeScript + Mongoose + JOSE backend from scratch. Use this whenever the user wants to start a new Node/Express API project, bootstrap a backend, set up an Express + TypeScript starter, or initialize a server-side project — even if they only say "new API", "Express starter", "backend boilerplate", or name the stack loosely. This skill scaffolds the infrastructure ONCE per project and generates the two source-of-truth files (ARCHITECTURE.md and MODULE_REGISTRY.md) that the module-planner, module-builder, and test-writer skills depend on. Do NOT use this to add a feature to an existing project (that is module-planner + module-builder) or to write tests (test-writer). This scaffolds an Express/Node + TypeScript backend specifically — do NOT use it to bootstrap projects in other stacks or languages (Django/Python, Rails, Spring, Go, Next.js, etc.); those are out of scope.

vipincode Bundle

Port a page, screen, or design language from ANY existing codebase into a production-grade Next.js + TypeScript + Tailwind + shadcn/ui page in the current project — the source being another repo/folder on disk (a static design mock, an old app, a legacy frontend — CSS Modules, styled-components, SCSS, plain CSS, Vue, older React/Next, or a Tailwind app with different conventions). Use this whenever the user points at an existing project as the design source — "copy the dashboard from <path/repo>", "port /admin/orders from our old app", "make this route match <project>", "rebuild this screen from <codebase>", "migrate these pages into the new frontend", "make our page look like project X". It reads the source READ-ONLY, derives a reusable translation map (source colors/fonts/spacing → the target's oklch theme tokens; source custom UI → shadcn/ui + shared components), lifts the source theme first when the target still has the stock shadcn theme, then builds dedup-first — scanning ARCHITECTURE.md + MODULE_REGIST

vipincode Bundle

Make any existing frontend ready for the frontend toolkit (frontend-feature-planner, frontend-module-builder, frontend-test-writer, frontend-code-review) by establishing its contract files. Use this as the entry point whenever the user points the frontend toolkit at a directory — "set up my existing Next.js app for these skills", "onboard this React frontend", "I want to use these skills on my current UI", "get this client ready", or starting work in a frontend folder that has no ARCHITECTURE.md / MODULE_REGISTRY.md yet. For an EXISTING frontend it scans the repo and generates a DESCRIPTIVE ARCHITECTURE.md plus a MODULE_REGISTRY.md seeded with all existing reusable components, hooks, schemas, lib utils, and feature modules, so feature work reuses what's there instead of duplicating it (DRY). For an EMPTY directory it hands off to nextjs-bootstrap. It is non-destructive — it never refactors existing code, only writes the contract files. After onboarding, plan/build/test/review happen through the dedicated fron

vipincode Bundle

Review backend / server-side code (Express, Node, TypeScript, Mongoose APIs) for correctness, security, convention adherence, and duplication. Use whenever the user asks to review, audit, critique, or sanity-check backend code — "review this service", "code review the auth module", "review my changes / this PR / the diff", "is this production-ready", "check this for issues". It reads ARCHITECTURE.md + MODULE_REGISTRY.md so it reviews against THIS project's conventions and flags code that duplicates existing registry entries (DRY). Standalone and read-only — run anytime, never auto-chained, and it does not modify source unless explicitly asked to apply fixes. Tuned for backend; not for frontend/React review. This is static code review only — it does NOT run the app or confirm a change behaves correctly at runtime; requests like "verify it works", "does it run", or "check that my change actually works" are run/verify intent (/verify or /run), not review.

vipincode Bundle

Review frontend / client-side code (Next.js App Router, React, TypeScript, Tailwind + shadcn/ui, axios + Zod + TanStack Query + RHF) for correctness, component duplication, API-binding conformance, convention adherence, accessibility, and performance. Use whenever the user asks to review, audit, critique, or sanity-check frontend code — "review this component", "code review the products binding", "review my changes / this PR / the diff", "is this screen production-ready", "check this React code for issues". It reads the frontend ARCHITECTURE.md + MODULE_REGISTRY.md so it reviews against THIS project's conventions and flags components/hooks/utils that duplicate existing shared pieces or registry entries (DRY), plus bindings that bypass the BFF/axios/Zod/Query standard. Standalone and read-only — run anytime, never auto-chained, and it does not modify source unless explicitly asked to apply fixes. Tuned for frontend; NOT for backend/Express/Mongoose review (that is backend-code-review). This is static code revi

vipincode Bundle

Write tests for frontend Next.js/React code on demand — components, hooks (incl. TanStack Query hooks), Zod schemas, and API-binding behavior. Use this ONLY when the user explicitly asks to test frontend code — "write tests for the products grid", "test the useProductsQuery hook", "add component tests for product-card.tsx", "cover the create-product form", "test this binding". It is a standalone utility, run manually whenever the user wants — never auto-chained from frontend-feature-planner or frontend-module-builder. It reads ARCHITECTURE.md (conventions), MODULE_REGISTRY.md (what to mock vs use), the target file(s), and the FEATURE_PLAN's testing checklist if present, detects the test framework + RTL setup from package.json, and writes matching test files. It never modifies source files and never touches the registry. It is NOT for backend tests (that is backend-test-writer). Frontend / Next.js / React / Vitest+RTL scope only.

vipincode Bundle

frontend-feature-planner

xrnavigation Bundle

Guides CSS patterns that affect accessibility — focus indicators, forced-colors mode, prefers-reduced-motion, prefers-contrast, color-only information avoidance, and target sizing. Auto-invokes when writing CSS for interactive elements, animations, transitions, media queries, or custom focus styles.

xrnavigation Bundle

Guides accessible data grid, interactive table, and sortable table implementation. Auto-invokes when creating data grids, spreadsheet interfaces, sortable tables, or interactive table cells. Critical distinction — most data tables do NOT need role="grid". Covers table vs grid decision, HTML table accessibility, sortable columns, and the APG grid pattern.

xrnavigation Bundle

Guides accessible application menu and menu button implementation per APG patterns. Auto-invokes when creating menus, menubars, context menus, action dropdowns, or menu buttons. Critical distinction — site navigation is NOT a menu. Covers menu/menubar/menuitem roles, menuitemcheckbox, menuitemradio, and the menu button pattern.

xrnavigation Bundle

Guides accessible tab interface implementation per APG patterns. Auto-invokes when creating tabs, tabbed panels, tab navigation, or tabbed content components. Covers required ARIA roles/states, keyboard interaction, automatic vs manual activation, and horizontal vs vertical orientation.

xrnavigation Bundle

Guides accessible tree view and treegrid implementation per APG patterns. Auto-invokes when creating tree views, file browsers, hierarchical lists, nested navigation trees, or treegrid components. Covers tree vs treegrid decision, required ARIA roles/states, keyboard interaction, and multi-select patterns.

xrnavigation Bundle

Guides comprehensive form accessibility beyond basic labels — error messaging and association, validation patterns, field grouping, accessible authentication (WCAG 2.2), redundant entry prevention, and autocomplete attributes. Auto-invokes when creating forms, validation logic, authentication flows, or multi-step form wizards.

xrnavigation Bundle

Runs automated accessibility scans with axe-core, pa11y, Lighthouse, or eslint-plugin-jsx-a11y. Interprets results, prioritizes violations, and generates fix recommendations. Use when asked to audit, scan, or check accessibility of a page, component, or codebase.

xrnavigation Bundle

Guides accessible modal and non-modal dialog implementation. Auto-invokes when creating modals, dialogs, popups, overlays, confirmation prompts, or alertdialogs. Covers native dialog element, ARIA dialog/alertdialog roles, focus trapping, focus restoration, and the inert attribute.

xrnavigation Bundle

Guides accessible listbox implementation for single and multi-select lists per APG patterns. Auto-invokes when creating listboxes, selection lists, option lists, or custom multi-select components. Covers required ARIA, keyboard interaction, single vs multi-select, and reorderable lists (WCAG 2.2 dragging alternatives).

xrnavigation Bundle

Guides ARIA live region usage for dynamic content announcements. Auto-invokes when creating notifications, toasts, status messages, loading indicators, search result counters, form validation summaries, or SPA route change announcers. Covers timing requirements, politeness levels, implicit live regions, and common pitfalls.

xrnavigation Bundle

Guides accessible combobox and autocomplete implementation per APG patterns. Auto-invokes when creating combobox, autocomplete, typeahead, select-with-search, or custom dropdown components. Covers required ARIA, keyboard interaction, and variant selection (select-only, editable, autocomplete modes).

xrnavigation Bundle

Guides accessible accordion and disclosure implementation. Auto-invokes when creating accordions, collapsible sections, expandable panels, or disclosure widgets. Covers native details/summary vs ARIA accordion, the APG accordion pattern, and the disclosure pattern.

xrnavigation Bundle

Guides cognitive accessibility patterns — clear actionable error messages, consistent navigation, predictable behavior, timeout handling with warnings, progress indicators for multi-step processes, consistent help placement (WCAG 2.2), and plain language. Auto-invokes when writing error messages, multi-step flows, session timeout logic, or navigation structures.

xrnavigation Bundle

Guides alt text decision-making beyond presence — the W3C decision tree for decorative vs informative vs functional vs complex images, context-dependent descriptions, SVG accessibility, CSS background image alternatives, and icon button labeling. Auto-invokes when adding images, SVGs, icons, or image-based components.

xrnavigation Bundle

Guides focus management for dynamic web applications — modal focus trapping, focus restoration, SPA route changes, dynamic content focus recovery, focus-not-obscured (WCAG 2.2), and skip navigation. Auto-invokes when creating modals, dialogs, SPAs, route handlers, or dynamically adding/removing DOM content.

xrnavigation Bundle

Guides accessibility testing strategy — what to test automatically vs manually vs with assistive technology. Provides keyboard testing checklists, screen reader testing basics, and acceptance criteria templates. Use when planning testing, writing acceptance criteria, or deciding how to verify accessibility.

xrnavigation Bundle

Prevents agents from recommending accessibility overlay widgets (accessiBe, UserWay, AudioEye, etc.). These products are opposed by the disability community, have been fined by the FTC, and make accessibility worse. Use when asked about quick accessibility fixes, overlay products, or accessibility widgets. The agent must never recommend an overlay.

xrnavigation Bundle

Guides correct ARIA usage by encoding the "first rule of ARIA" — use native HTML elements before reaching for ARIA roles. Auto-invokes when writing ARIA attributes, custom interactive elements, or role attributes. Prevents the most common LLM accessibility error: ARIA misuse and overuse.

xrnavigation Bundle

Generates accessibility-centered user stories, personas, and acceptance criteria that verify real assistive technology experiences. Use when writing user stories, sprint planning, defining acceptance criteria, or creating accessibility-specific test cases. Provides W3C, GOV.UK, and Microsoft persona frameworks plus Given/When/Then patterns for AT verification.