
Copy self-audit and ban-lists — filler verbs/hype adjectives, slop placeholder names, fake-precise numbers, Title Case headlines, humor in error copy ('Oops!'), em-dash crutch, one copy register per page.
The final quality gate before any design deliverable is reported done — two ISOLATED assessments (deterministic detection never in the same head as the subjective/visual read), P0-P3 findings with NO aggregate score ever, a bounded visual loop (max 2 fix cycles), and a mandatory in-loop challenger gate (fresh-context, blind PNG) before any 'done' claim.
iOS + macOS mockups and handoff specs — Dynamic Type scale, semantic colors, device viewports, Liquid Glass, macOS text/window/pointer conventions, device-framed HTML mockup, and a SwiftUI-ready handoff spec. Produces tokens + mockup only, never SwiftUI code.
Token-strategy core — OKLCH color rules, neutral tinting, accent-commitment levels, type scale, 8pt spacing grid, touch targets, and the canonical output format of design-system.md (the file the harness gates on). This is routing step 1 of design-method/SKILL.md — read it before design-web/design-webapp/design-ios/design-android, before picking or auditing a single color/type/spacing value.
Logged-in web apps — dashboards, auth flows, settings, onboarding, data tables, command palettes, modals, toasts. Register `product`: density and glance-speed over marketing polish, no hero/CTA-tricks, every data surface covers empty/loading/error explicitly, tables and dataviz follow preattentive-processing rules.
Marketing sites, landing pages, campaign pages — register `brand` (design IS the product). Structure comes from the register's POV + a macrostructure pick, never from copying an inspiration site's section flow. Hero discipline, deviated section order, asymmetric grids, and a silhouette lookalike-test gate before ship.
Motion pass on a settled layout — the animation-decision gate, transform/opacity-first materials, the 100/300/500 duration scale, exponential/emphasized easing (no bounce), mandatory reduced-motion, and the AI-motion-signature ban.
Android mockups and handoff specs — Material 3 Expressive type scale (baseline + emphasized), full color-role system (45 roles incl. surface-container ramp + dynamic color), elevation tokens, shape scale, window size classes, FAB tiers, motion, device-framed HTML mockup, and a Compose-ready handoff spec. Produces tokens + mockup only, never Compose code.
Core design method — Register resolution (brand vs product), the Design Read one-liner + the 3 dials (DESIGN_VARIANCE/VISUAL_DENSITY/MOTION_INTENSITY), the Gate 0 brief lock, Absolute bans, the 2-level AI-slop test, and routing to a move (generate/critique/audit/bolder/quieter/distill/harden/polish) and its target skill. Read this first, before design-system, any register/*.md, or any moves/*.md file.
Astro Starlight documentation theme — setup, sidebar config, Pagefind search, dark/light mode, plugins (DocSearch, blog, openapi, typedoc, versions), multi-language, Content Layer API, llms.txt, customization. Use for building documentation sites.
Design tokens and theming for shadcn/ui. Covers CSS variables, OKLCH colors, dark/light mode, and theme configuration for both Radix and Base UI primitives. Use when: defining or auditing shadcn/ui design tokens, OKLCH colors, or dark/light mode CSS variables.
Orientation map of the PHP framework ecosystem — NOT deep expertise. Use to know WHICH tool fits and WHERE to route: standalone Symfony components (Console, Process, HttpFoundation, EventDispatcher, Validator, Serializer) usable via Composer outside any framework, API Platform 4.3 (API-first on Symfony), and the Slim micro-framework. Do NOT use for implementation — Laravel routes to laravel-expert; deep full-stack Symfony has no dedicated expert (flag to the user).
Use when building framework-agnostic HTTP code in PHP — PSR-7 messages, PSR-15 middleware pipelines, PSR-17 factories, PSR-18 HTTP clients. Covers immutable Request/Response/Stream/Uri, RequestHandler + Middleware, factory interfaces, and reference implementations (nyholm/psr7, guzzlehttp/psr7, laminas-diactoros). Do NOT use for Laravel HTTP (use laravel-expert) or Symfony HttpFoundation (not PSR-7 — see references/implementations.md).
Use when implementing internationalization in Astro, configuring i18n routing, setting up locale strategies, using getRelativeLocaleUrl/getAbsoluteLocaleUrl, handling Astro.currentLocale, or adding hreflang tags with sitemap.
Design AI agents with recommended patterns and architectures. Use when: choosing between workflow vs agent patterns, structuring orchestrator/subagent pipelines, or writing a Claude Code agent template.
Security techniques and quality control for prompts and agents. Use when: implementing input/output guardrails, writing ethical guardrail templates, or auditing an agent/prompt for missing security controls.
Use when styling Astro components with scoped CSS, CSS Modules, Tailwind CSS, UnoCSS, or Sass. Covers class:list directive, global styles, CSS custom properties, and Vite-powered preprocessors.
Techniques and templates for creating optimal prompts following Anthropic conventions. Use when: writing a new system prompt from scratch, structuring it with Anthropic's 9-element format, or choosing emphasis levels and few-shot examples.
A/B testing and performance metrics for prompts. Use when: comparing two prompt variants, defining quality/efficiency/robustness metrics, or deciding whether to adopt a challenger prompt over a baseline.
Library of 18+ ready-to-use prompt templates and executable agents. Use when: looking for a ready-made agent or task template (code review, support, data analysis, translation, extraction, etc.) instead of writing one from scratch.
Use when choosing crates for a Rust project — serialization, CLI, async runtime, web, database, HTTP client, error handling, observability. Provides a domain→crate decision map of the de-facto 2026 standards, with selection criteria. Do NOT use for API usage details of a chosen crate (load the matching domain skill, or verify via fuse-browser fast-path on docs.rs/crates.io → Context7 → Exa).
Use when writing or reviewing modern PHP (8.1–8.5) outside a framework — property hooks, asymmetric visibility, the pipe operator, native attributes, enums, readonly, lazy objects. Covers language features that LLMs frequently get wrong or write in a pre-8.0 style. Do NOT use for coding style/PSR/autoloading (use php-standards) or Laravel-specific syntax (use the laravel plugin).
SOLID principles for React 19. Files < 100 lines, hooks separated, interfaces in src/interfaces/, JSDoc mandatory. Use for React architecture and code quality.
Use when designing Rust error handling — picking thiserror for libraries vs anyhow for applications, building typed error enums, converting errors with
Use when setting up a PHP package, choosing a coding style, wiring autoloading, or selecting PSR interfaces — PSR-4 autoloading, PER Coding Style 3.0 vs PSR-12, the active PSR catalog, and modern composer.json. Do NOT use for language syntax/features (use php-language-modern) or Laravel-specific conventions (use the laravel plugin).
Use when writing or reviewing idiomatic Rust — edition 2024 features, ownership/borrowing design, and correcting the pitfalls that show up in LLM-generated Rust (clone tax, unwrap infestation, String vs &str, indexed loops, over-annotated lifetimes). Do NOT use for error-type design (use rust-error-handling), async runtimes, or SOLID/file-layout rules (use fuse-solid:solid-rust).
Use when building a REST/HTTP backend in Rust — routing, extractors, shared state, middleware, error responses, database access, and structured logging. Covers the 2026 standard stack axum + tokio + sqlx + tracing, plus honest alternatives (sea-orm, diesel). Do NOT use for raw async/concurrency questions (rust-async-concurrency) or crate selection across domains (rust-ecosystem-crates).
Audit project dependencies for known vulnerabilities using ecosystem-specific tools (npm audit, composer audit, pip-audit, cargo audit, etc). Use when: running ecosystem-specific vulnerability scans across project dependencies, with optional auto-fix.
Use when structuring a Cargo workspace, wiring features, or building a Rust CI pipeline — fmt, clippy, cargo-deny, cargo-audit, nextest, doc-tests, coverage, MSRV. Covers the canonical CI gate order and supply-chain checks. Do NOT use for writing the tests themselves (use rust-testing-quality) or non-Rust CI.
Use when writing async Rust — spawning tasks, sharing state across tasks/threads, choosing channels vs mutexes, or hitting Send-bound errors with async traits. Covers tokio runtime, Mutex/RwLock/atomics, mpsc/oneshot/broadcast/watch, spawn_blocking, and the async-fn-in-traits Send problem. Do NOT use for HTTP service structure — routing, extractors, middleware (use rust-web-backend) — or sync-only ownership questions (use rust-core-language).
Verify and configure HTTP security headers (CSP, HSTS, CORS, X-Frame-Options, etc). Checks current configuration and generates framework-specific fixes. Use when: verifying or configuring HTTP security headers for a web application (Next.js, Laravel, Express, Django).
Main security scanning orchestration. Detects language, runs OWASP Top 10 patterns, identifies vulnerabilities, generates structured reports. Use when scanning for XSS, SQL injection, command injection, secrets, or any security vulnerability.
Analyze and improve existing prompts for better performance. Use when: auditing an existing prompt for clarity, structure, or completeness issues, fixing vague instructions, or producing a before/after optimization report.
Optimization guide for fuse-commit-pro commit workflow. Documents settings to reduce token usage.
TanStack Router - 100% type-safe routing, file-based routes, loaders, search params. Use when implementing routing in React apps (NOT Next.js).
Audit authentication and authorization patterns. Checks JWT, sessions, OAuth2, PKCE implementations for security best practices and common vulnerabilities. Use when: auditing JWT, session, OAuth2/PKCE, password, or MFA implementations for security vulnerabilities.
Multi-language SOLID detection rules. Project type detection, interface locations, file size limits per language. Use when: determining which language-specific SOLID skill to load, detecting project type from config files, or resolving interface directory conventions per language.
Configure shadcn/ui registries, components.json, and CLI commands. Covers default Radix registry, Base UI registry, and custom registries. Use when: configuring shadcn/ui registries, components.json, or CLI add/init commands.
SOLID principles for Go 1.23+. Files < 100 lines, interfaces separated, modular architecture. Modules MANDATORY. Use when: writing or refactoring Go code, structuring internal/modules/[feature]/ layers, or defining ports/ interfaces.
SOLID principles for C# 12/.NET 9. Files < 100 lines, interfaces separated, modular architecture. Contracts MANDATORY. Use when: writing or refactoring C#/.NET code, structuring Modules/[Feature]/ layers, or defining Contracts/ interfaces.
Detect whether a project uses Radix UI or Base UI as shadcn/ui primitives. Analyzes package.json, components.json, imports, and data attributes to determine the primitive library in use. Use when: determining which primitive a project uses before any shadcn component work or migration.
SOLID principles for generic TypeScript, Bun, and Node.js projects. Files < 100 lines, interfaces separated, JSDoc mandatory. Use when: building CLI tools, libraries, scripts, hooks, or non-framework TypeScript code.
Prisma 7 ORM with Rust-free client, 90% smaller bundles, TypedSQL, Omit API, and ESM-first architecture. Use when working with database, schema, migrations, queries, or relations.
Efficient fuse-browser usage: web fetch, crawl, SERP, browser session, screenshot, webapp testing, console errors. Read this BEFORE any mcp__fuse-browser__* tool call — it routes fetch/crawl/serp vs live session vs visual capture and enforces the 4 ZERO-TOLERANCE rules.
Expert Astro 7 framework (stable, 7.0.9) — routing, output modes, middleware, Vite Environment API, single Rust compiler, Content Security Policy, Live Collections, Fonts API. Use when building Astro sites, configuring output, or upgrading from Astro 5/6.
Use when configuring Content Security Policy (CSP) in Astro 7, setting security headers, managing script/style hashes, using nonces, or implementing experimentalStaticHeaders for adapter deployments.
Use when user requests creative work - creating features, building components, adding functionality, or modifying behavior. Activates BEFORE APEX Analyze phase to refine requirements through structured questioning.
Use when writing, organizing, or running Rust tests — unit, integration, doc-tests, property-based (proptest), benchmarks (criterion), or mutation testing (cargo-mutants). Covers test layout, the nextest doctest pitfall, and quality gates. Do NOT use for CI pipeline wiring (use rust-tooling-cicd) or non-Rust test suites.
Migration guide between Radix UI and Base UI primitives for shadcn/ui. Covers step-by-step migration, API transformations, and validation checklists. Use when: migrating a project between Radix UI and Base UI primitives, or validating a migration's API transformations.
Component patterns for shadcn/ui with both Radix UI and Base UI primitives. Covers API differences, mapping between primitives, and correct usage patterns. Use when: building or editing shadcn/ui components, mapping Radix vs Base UI APIs, or choosing composition patterns (asChild vs render).
Use when running SEO, GEO, schema, Core Web Vitals, sitemap, hreflang, E-E-A-T, AI Overviews, technical SEO, or structured data tasks. Covers full-site audits, single-page analysis, schema markup, content quality, AI search optimization, local SEO, sitemap/robots, internal linking, semantic clustering, and search experience.
Technical research methodology using Context7, Exa, and Sequential Thinking for documentation, best practices, and complex investigations.
Use when writing or configuring tests on a framework-agnostic PHP project and choosing between PHPUnit and Pest. Covers PHPUnit 12 attributes, Pest 4, test doubles, fixtures, and coverage. Do NOT use for Laravel test helpers (RefreshDatabase, HTTP tests → laravel-expert laravel-testing) or quality tooling (PHPStan/Rector/Fixer → php-quality-tooling).
Expert Astro Content Layer API — content.config.ts, glob/file loaders, custom loaders, getCollection, getEntry, render(), Zod schemas, MDX, Remark/Rehype plugins. Use when managing structured content, blog posts, or any typed data collections.
Image and asset optimization in Astro 7 — <Image />, <Picture />, getImage(), remote images, @astrojs/sharp, Fonts API, OG image generation with Satori, Cloudinary/Imgix. Use for any image optimization or asset handling task.
Astro DB — defineDb, defineTable, column types, CRUD with db.select/insert/update/delete, db/config.ts, db/seed.ts, Turso for production, type-safety, integration with Astro Actions. Use for any database operation in an Astro project.
Expert Astro UI framework integrations — @astrojs/react, @astrojs/vue, @astrojs/svelte, @astrojs/solid-js, @astrojs/preact, @astrojs/alpinejs, @astrojs/lit, @qwikdev/astro, @analogjs/astro-angular. Setup, multi-framework config, usage patterns.
Expert Astro Server Actions — defineAction, astro:actions, Zod validation, ActionError, HTML form actions, accept form, progressive enhancement, redirect patterns. Use when handling form submissions, mutations, or any server-side logic with type safety.
Use when applying SOLID principles and clean architecture to Astro projects. Enforces files < 100 lines, src/interfaces/ for types, JSDoc on all exports, modular directory structure, and DRY enforcement.
Use when setting up or tuning static analysis, automated refactoring, and code-style enforcement on a framework-agnostic PHP project. Covers PHPStan, Rector, PHP-CS-Fixer, composer scripts, and CI wiring. Do NOT use for Laravel projects (Pint + Larastan → laravel-expert), test frameworks (→ php-testing), or language syntax questions (→ php-language-modern).
Expert Astro Islands Architecture — client:load, client:idle, client:visible, client:media, client:only, server:defer (Server Islands), fallback slots, transition:persist, prop serialization. Use when adding interactivity to Astro pages or rendering dynamic server content.
SOLID principles for Java 21+. Files < 100 lines, interfaces separated, modular architecture. Modules MANDATORY. Use when: writing or refactoring Java code, structuring modules/[feature]/ layers, or defining interfaces/ contracts.
Sizing utilities Tailwind CSS v4.1. Width (w-*, w-screen, w-full, w-auto), Height (h-*, h-screen, h-full, h-dvh NEW), Min/Max (min-w-*, max-w-*, min-h-*, max-h-*), Aspect ratio (aspect-video, aspect-square). Use when: setting element width/height, constraining min/max dimensions, using dynamic viewport height (h-dvh), or fixing an aspect ratio.
Configuration and directives Tailwind CSS v4.1. @theme, @import, @source, @utility, @variant, @apply, @config. CSS-first mode without tailwind.config.js. Use when: configuring Tailwind CSS-first (no tailwind.config.js), defining theme tokens via @theme, scanning source files with @source, or creating custom utilities/variants. Do NOT use for: v3-to-v4 migration and breaking changes (use tailwindcss-v4), utility class lookup by category (use tailwindcss-layout/spacing/typography/backgrounds/borders/effects/sizing/interactivity/transforms).
SOLID principles for TanStack Start projects. Files < 100 lines, interfaces in src/interfaces/, JSDoc on all exports, modular structure around the Start route tree. Use when: organizing a Start codebase, splitting oversized routes/server functions, reviewing architecture, deciding where isomorphic vs server-only code lives. Do NOT use for: framework setup (use start-core), execution boundaries deep-dive (use start-execution-model), generic React SPA without a Start route tree (use solid-react).
TanStack Start setup and project anatomy — tanstackStart() Vite (and Rsbuild) plugin, getRouter() factory, root route document shell (HeadContent, Outlet, Scripts), routeTree.gen.ts, tsconfig, src/ layout. Use when: scaffolding a Start project from scratch, wiring the build tool, understanding where files go, debugging setup (blank page, hydration, no client JS). Do NOT use for: server-only vs isomorphic boundaries (use start-execution-model), SOLID/code organization (use solid-tanstack-start), plain React SPA without Start.
Use when publishing a TypeScript library — exports map, JSR vs npm, dual ESM/CJS, type validation, provenance. Covers modern package.json, jsr.json, and release CI. Do NOT use for application deployment (not a library) or framework build pipelines (use the framework expert's skills).
Tailwind CSS v4.1 accessibility utilities. focus-visible, sr-only, reduced-motion, WCAG enforcement, touch targets, contrast ratios. Use when: implementing keyboard-accessible components, screen-reader-only content, prefers-reduced-motion support, WCAG 2.2 AA/AAA compliance, or accessible touch targets.
SOLID principles for Ruby 3.3+ and Rails 8. Files < 100 lines, contracts separated, modular architecture. Modules MANDATORY. Use when: writing or refactoring Ruby/Rails code, structuring app/modules/[feature]/ layers, or defining contracts/ modules.
SOLID principles for Swift 6 and SwiftUI (iOS 26+). Files < 100 lines, protocols separated, @Observable, actors, Preview-driven development. Features Modular MANDATORY.
Effects utilities Tailwind CSS v4.1. Shadows (shadow-*, shadow-color, inset-shadow-* NEW), Opacity (opacity-*), Filters (blur, brightness, contrast, grayscale, sepia), Backdrop filters (backdrop-blur-*, backdrop-brightness-*), Masks (mask-* NEW). Use when: adding box/inset shadows, controlling opacity, applying CSS filters or backdrop filters (glassmorphism), or masking elements with mask-* utilities.
Border utilities Tailwind CSS v4.1. Border (border-width, border-color, border-style, border-radius, rounded-*), Outline (outline-*, outline-offset), Ring (ring-*, ring-offset), Divide (divide-*). Use when: styling element borders, rounded corners, focus outlines/rings, or divide-* separators between children.
Custom CSS authoring in Tailwind CSS v4.1 via @utility, @variant, @custom-variant, @apply, and @layer directives. Use when: creating a new named utility class, writing conditional/dark-mode variants, defining a custom variant selector, or applying utility classes inside custom CSS rules.
Use when: adding authentication/authorization to a TanStack Start app — protecting routes with beforeLoad + redirect, authorizing server functions, sessions/cookies (useSession, getRequest), CSRF, or wiring Auth.js. Do NOT use for: generic route guards unrelated to auth (react-tanstack-router) or non-Start Node auth.
Interactivity utilities Tailwind CSS v4.1. Cursor (cursor-*), Scroll (scroll-smooth, scroll-snap-*, overscroll-*), User select (select-*), Pointer events (pointer-events-*), Touch action, Resize, Caret color, Accent color. Use when: controlling cursor appearance, scroll snap/smooth behavior, text selection, pointer-events, touch actions, resize handles, or caret/accent colors on form controls.
Use when: building or deploying a TanStack Start app — Nitro/Vite build, official adapters (Cloudflare Workers, Netlify, Vercel, Node, Bun, Railway), static prerendering (tanstackStart prerender), production env vars, or a deploy checklist. Do NOT use for: app data/auth logic (see start-routing-data / start-auth) or generic Vite config unrelated to Start.
Background utilities Tailwind CSS v4.1. Colors (bg-{color}, palette OKLCH P3), Gradients (bg-linear-*, bg-radial-*, bg-conic-* NEW), Images (bg-cover, bg-contain, bg-repeat), Blend modes. Use when: styling background colors, building linear/radial/conic gradients, setting background images/position/size, or combining backgrounds with blend modes.
Tailwind CSS v4.1 core features: @theme namespaces, CSS-first configuration, custom directives (@utility, @variant, @custom-variant), v3-to-v4 breaking changes, and the upgrade tool. Use when: migrating a project from Tailwind v3 to v4, mapping @theme namespaces to generated utilities, or looking up renamed/removed v3 utilities. Do NOT use for: day-to-day CSS-first configuration reference — @theme/@utility/@variant details (use tailwindcss-core), utility class lookup (use the category skills).
Layout utilities Tailwind CSS v4.1. Flexbox (flex, justify, items, gap), Grid (grid-cols, grid-rows, place), Position (absolute, relative, fixed, sticky, inset, z-index), Container queries (@container). Use when: building flex or grid layouts, positioning elements (absolute/relative/fixed/sticky), managing z-index/inset, or writing container-query responsive styles.
Spacing utilities Tailwind CSS v4.1. Margin (m-*, mx-*, my-*, mt-*, mr-*, mb-*, ml-*, -m-* negative, m-auto), Padding (p-*, px-*, py-*, pt-*, pr-*, pb-*, pl-*), Space between (space-x-*, space-y-*). Use when: setting margin or padding on any side, centering with m-auto, applying negative margins, or spacing flex/grid children with space-x-*/space-y-*.
Transform & Animation utilities Tailwind CSS v4.1. Transform (scale-*, rotate-*, translate-*, skew-*, transform-origin), Transition (transition-*, duration-*, ease-*, delay-*), Animation (animate-*, @keyframes). Use when: scaling/rotating/translating/skewing an element, configuring transition duration/easing/delay, or applying built-in or custom @keyframes animations.
Typography utilities Tailwind CSS v4.1. Font (font-sans, font-serif, font-mono, font-size, font-weight), Text (text-color, text-align, text-wrap, text-shadow NEW), Letter/Line spacing, Decoration, Transform. Use when: setting font family/size/weight, aligning or wrapping text (balance/pretty), applying text-shadow or decoration, or adjusting letter/line spacing.
Responsive design utilities in Tailwind CSS v4: default breakpoints (sm/md/lg/xl/2xl), custom breakpoints via @theme, container queries (@container, @md, @lg), and mobile-first patterns. Use when: applying responsive variants at different screen widths, defining a custom breakpoint, or building container-query-based responsive components.
Use when running TypeScript on Bun — bunfig.toml, bun test (coverage, JUnit, preload), Bun.build and --compile, workspaces, and the Bun vs Node transpiler tradeoff. Covers Bun 1.3.x. Do NOT use for Node.js runtime setup (ts-runtime-node) or tsconfig details (ts-config).
Index of Tailwind CSS utility-class categories (layout, spacing, typography, colors, borders, effects, state variants). Use when: unsure which category skill covers a given utility class and need routing to the right one. Do NOT use for: concrete class lookup or worked examples — go directly to the category skill (tailwindcss-layout/spacing/typography/backgrounds/borders/effects/interactivity), this file only routes.
Use when creating type-safe RPC server logic in TanStack Start with createServerFn — GET/POST methods, .validator() (Zod or function), .handler(), useServerFn hook, FormData input, Response output, strict serialization, throw redirect()/notFound(), server context utilities, and CSRF protection. Do NOT use for: raw external HTTP endpoints (use start-server-routes), reusable middleware chains (use start-middleware), or Next.js/Remix "use server" patterns.
Use when writing or configuring TypeScript tests and choosing between bun test and Vitest. Covers runner selection, config, mocks, snapshots, and coverage. Do NOT use for framework-specific testing (React components → react-expert react-testing, Laravel → laravel-testing) or browser E2E suites.
Use when choosing and configuring a TypeScript linter/formatter — Biome 2.x (one binary, type-aware) vs ESLint 9 flat config + typescript-eslint (full typed linting). Includes the 2026 arbitrage and Oxlint note. Do NOT use for type checking itself (tsc, ts-config skill) or test-runner configuration (ts-testing).
Complete reference for Tailwind CSS utility classes, indexing the categorical skills (layout, spacing, typography, backgrounds, effects, borders, transforms). Use when: you need a single entry point to locate which categorical tailwindcss-* skill covers a given utility class. Router/index only: identifies WHICH category skill to load. Do NOT use for: actual utility class content (load the category skill it points to).
Use when composing cross-cutting server logic in TanStack Start with createMiddleware — request vs server function middleware, chaining via .middleware([...]), shared context with next({ context }), client↔server sendContext, client middleware (.client), global middleware via createStart in src/start.ts, middleware factories for authorization, and staticFunctionMiddleware. Do NOT use for: defining the RPC itself (use start-server-functions), raw HTTP endpoints (use start-server-routes), or route-level UX guards (use router beforeLoad).
TanStack Start execution model — isomorphic-by-default, environment boundary functions (createServerFn, createServerOnlyFn, createClientOnlyFn, createIsomorphicFn), <ClientOnly>, useHydrated(), server-only/client-only import markers, and env-var safety (VITE_/PUBLIC_ prefix vs process.env). Use when: deciding where code runs, fixing secret leaks, DB/filesystem in a loader, hydration mismatches, "process.env is undefined on the server". Do NOT use for: initial setup (use start-core), file/directory SOLID organization (use solid-tanstack-start).
Use when: loading data in TanStack Start routes with isomorphic loaders, wiring TanStack Query into a Start loader (ensureQueryData), running mutations via server functions, or tuning per-route SSR (ssr flag). Do NOT use for: generic TanStack Router/Query API — route trees, search params, useQuery/useMutation basics (use react-expert's react-tanstack-router).
Use when building raw HTTP API endpoints in TanStack Start — the server property on createFileRoute, method handlers (GET/POST/PUT/DELETE), the handler context (request, params, context), createHandlers for per-handler middleware, file-route conventions, dynamic/splat params, request body parsing, and Response helpers. Do NOT use for: internal type-safe RPC from your own app (use start-server-functions), reusable middleware chains (use start-middleware), or UI route rendering.
Use when: creating or migrating a tsconfig.json, choosing module/moduleResolution, or fixing TS 6.0 deprecation errors. Covers the two official 2026 config tracks (Bun/bundler vs pure Node.js) and the TS 6.0 → 7.0 deprecation cleanup. Do NOT use for: TypeScript language syntax and idioms (use ts-language-patterns), framework configs shipping their own tsconfig base (Next.js/Astro/Vite plugin skills), or non-TS build tooling.
Use when running TypeScript directly on Node.js without a build step — native type stripping, its limits, when to reach for tsx, ESM setup, watch mode, and node:test. Covers Node 24 LTS. Do NOT use for Bun runtime specifics (ts-runtime-bun) or tsconfig details (ts-config).
Use when: writing or reviewing modern TypeScript syntax and idioms — const type parameters, using / await using resource management, standard ECMAScript decorators, satisfies, or fixing LLM-authored anti-patterns (legacy enum/namespace, missing import type). Covers TS 6.0 language features and inference. Do NOT use for: tsconfig / compiler flags (use ts-config), SOLID structure and file-size rules (use solid-generic), or framework-specific APIs.
Use when converting existing code to modular architecture. Detects Laravel (FuseCore or standard) / Next.js / React and applies correct modular patterns. Triggers: "modularize", "convert to modules", "migrate to modular", "restructure modules".
Use ONE Bash script instead of N sequential Read calls when analyzing multiple files, auditing codebase, finding all matches, scanning dependencies, counting lines, or listing files matching a pattern. Replaces wasteful multi-Read loops with compact shell pipelines.
Research CVEs and security advisories for project dependencies. Uses Exa, NVD API, OSV.dev, and GitHub Advisory Database to find known vulnerabilities. Use when: checking a specific dependency or package version for known CVEs and security advisories.
Codebase exploration techniques for rapid discovery, architecture analysis, pattern detection, and dependency mapping.
Use when creating expert agents. Generates agent.md with frontmatter, hooks, required sections, and skill references.
SEO for Astro sites — meta tags, Open Graph, Twitter Cards, JSON-LD structured data, sitemap, RSS, robots.txt, canonical URLs, hreflang, Core Web Vitals. Use when optimizing search engine visibility or social sharing.
SOLID principles for Laravel 13 and PHP 8.3+. Files < 100 lines, interfaces separated, PHPDoc mandatory. Auto-detects Laravel and FuseCore architecture.
Auto-review skill for expert agents. After coding, expert applies elicitation techniques to self-correct before sniper validation. Inspired by BMAD-METHOD. Use when: an expert agent needs to self-review and self-correct code after the Execute phase, before sniper validation.
Systematic development workflow: Analyze → Plan → Execute → eLicit → eXamine. Use for ANY development task: features, bug fixes, refactoring, hotfixes. Triggers: "implement", "create", "build", "fix", "add feature", "refactor", "develop". Auto-detects project type (Laravel, Next.js, React, Swift) and loads framework-specific references. Enforces: files <100 lines, interfaces separated, SOLID principles, expert self-review, sniper validation. Modes: --auto (default), --manual, --skip-elicit
Use when marking a task as complete, finishing a feature, or claiming a bug is fixed. Ensures functional resolution is verified with evidence before closing. Do NOT use for: lint/type/code-quality validation (use code-quality / sniper AFTER functional verification passes).
Structure Go 1.22+ services — standard cmd/internal layout, constructor-based dependency injection, HTTP routing (net/http ServeMux vs chi vs echo/gin/fiber), and type-safe database access with sqlc + pgx. Use when laying out a new Go project, choosing a router or DB layer, or wiring dependencies. Do NOT use for goroutines/channels patterns (go-concurrency) or language idioms (go-core-idioms).
Adversarial verification protocol for claims, plans, and root causes -- refute by default, fresh-context intake, sources-backed, bounded rounds. Runs SYSTEMATICALLY, by claim TYPE (not a stakes judgment), before reporting to the owner any of: a root-cause conclusion, a done/verified claim, an irreversible action (commit/deploy/rm/push), or a 2nd-time fix -- WHETHER inside an APEX task OR in plain conversation. Also runs systematically at every APEX eLicit round and every Verify gate, exactly like sniper runs systematically at eXamine, NO EXCEPTIONS. Do NOT use for: code correctness/lint/type validation (use code-quality/sniper).
Write idiomatic Go tests and measure quality — table-driven tests, subtests with t.Run, testify assertions/mocks, native fuzzing, benchmarks, the race detector, coverage, and pprof/PGO profiling. Use when writing or reviewing Go tests, adding coverage, benchmarking, or profiling a Go program. Do NOT use for CI pipeline wiring — golangci-lint, govulncheck (go-tooling-security) — or non-Go test suites.
Expert Next.js 16 with Turbopack, App Router, Cache Components, proxy.ts, React 19. Use when building Next.js apps, routing, caching, server components, or migrating from v15. Do NOT use for: full-stack assembly and scaffolding with Prisma/Better Auth/shadcn/Zustand (use nextjs-stack), pure React SPA without next.config (use react-expert skills).
shadcn/ui for Next.js App Router with TanStack Form. Use when building UI components, forms, dialogs, tables, toasts, or accessible components.
Use when upgrading a Laravel 12 application to Laravel 13.0. Covers PHP 8.3 requirement, composer commands, breaking changes (PHPUnit 12, Pest 4, VerifyCsrfToken → PreventRequestForgery, cache prefixes, serializable_classes, pheanstalk 8.0+), Attributes migration (Eloquent + Queue), Symfony 7.4/8.0 upgrade, and Laravel Boost MCP automated upgrade.
React Server Components patterns for Next.js 16. Server vs Client boundaries, async components, data fetching, serialization rules, streaming with Suspense. Use when: deciding server vs client component boundaries, fetching data directly in components, or streaming UI with Suspense.
Write tests with Pest 4/PHPUnit 12, feature tests, unit tests, mocking, fakes, and factories. Use when testing controllers, services, models, or implementing TDD on Laravel 13.
This skill should be used when the user asks about "SOLID principles", "Next.js architecture", "modular structure", "code organization", "file size limits", "interface separation", or "JSDoc documentation". Enforces files < 100 lines with mandatory JSDoc and separated interfaces.
Use when: writing or reviewing idiomatic sequential Go — error handling (%w wrapping, errors.Join, errors.Is/As, errors.AsType), slog structured logging, generics, small consumer-side interfaces, naming/style, new(expr), go fix modernizers. Do NOT use for: goroutines/channels/errgroup/context concurrency (use go-concurrency), non-Go languages, framework-specific code.
Design Laravel app architecture with services, repositories, actions, and clean code patterns. Use when structuring projects, creating services, implementing DI, or organizing code layers.
TanStack Query v5 integration with Next.js 16. Server-side prefetching, hydration, useQuery, useMutation, cache management. Use when: implementing client-side data fetching with caching, server-side prefetching with hydration, or optimistic mutations in Next.js.
Next.js 16+ complete stack with App Router, Prisma 7, Better Auth, shadcn/ui, TanStack Form, Zustand. Use as the master reference combining all framework skills. Do NOT use for: core framework API details — routing, caching, Server Components internals, proxy.ts (use nextjs-16 and its references).
TanStack Form v1 for Next.js 16 with Server Actions, Zod validation, and shadcn/ui integration. Use when building forms, validation, multi-step wizards, or dynamic field arrays.
SOLID principles for Rust 2024+. Files < 100 lines, traits separated, modular architecture. Modules MANDATORY. Use when: writing or refactoring Rust code, structuring src/modules/[feature]/ layers, or defining traits.rs interfaces.
Use when: writing or reviewing Go concurrency — goroutines, channels, golang.org/x/sync/errgroup, context propagation and cancellation, sync.WaitGroup vs channels, the -race detector, or diagnosing goroutine leaks (incl. the 1.26 goroutineleak profile). Do NOT use for: sequential error handling / slog / generics / interface style (use go-core-idioms), non-Go languages, framework-specific code.
Use when: setting up Go modules/workspaces, configuring golangci-lint v2, scanning dependencies with govulncheck, modernizing code with go fix, or building a Go CI quality gate. Do NOT use for: writing Go application logic (use the Go expert), non-Go languages, SOLID/architecture refactoring (use solid-go), or generic dependency audits in other ecosystems.
Monitor community feedback on Claude Code via Exa search. Gathers sentiment, real-world usage patterns, bug reports, and feature requests from blogs, forums, and social media. Use when: gauging community sentiment, bug reports, or feature requests about Claude Code.
Scan Claude Code changelog for new versions, features, and changes. Fetches official docs, parses release notes, and generates structured update report. Use when: checking for new Claude Code versions, features, or changes since the last known release.
Enrich auto-generated .cartographer/ maps with full descriptions from source files. Use when: cartography index descriptions are truncated, a new plugin/skill was just added, or after SessionStart regenerates the map.
Audit React components for unnecessary useEffect patterns. Detects 9 anti-patterns from "You Might Not Need an Effect" and proposes fixes with severity levels. Use when: auditing React or Next.js components for unnecessary or unsafe useEffect usage.
Deploying Astro 7 apps — @astrojs/cloudflare (Workers, D1, KV, R2), @astrojs/vercel (Serverless/Edge, Image CDN), @astrojs/netlify (Edge Functions), @astrojs/node (standalone), ISR patterns, edge middleware, skew protection. Use for any deployment configuration.
Use when committing, branching, opening PRs, or deciding merge strategy. Covers GitHub Flow (default), trunk-based, branch naming conventions, squash vs rebase, branch lifecycle, and protected branch enforcement.
Detect breaking changes in Claude Code updates by comparing current API surface against changelog. Maps impacts to specific plugin files. Use when: checking whether a Claude Code update breaks our plugin ecosystem (hooks, agent frontmatter, manifest schema, or skill format).
Universal post-commit actions. CHANGELOG update for all repos (git tag is created POST-MERGE, not here — see `commit` command Step 8). Plugin version bumping for marketplace repos. Triggered after any code commit (except wip/amend/undo).
Use when writing production code that needs tests - new features, bug fixes, refactoring. Enforces RED-GREEN-REFACTOR cycle before any implementation.
Code quality validation with linters, SOLID principles, DRY detection, error detection, and architecture compliance across all languages. Use when: validating code quality after modifications — SOLID compliance, DRY duplication, linter errors, or architecture violations. Do NOT use for: verifying the original problem is functionally resolved (run verification FIRST — code-quality validates quality AFTER functional verification passes).
SOLID principles for Python 3.12+. Files < 100 lines, interfaces separated, modular architecture. Modules MANDATORY. Use when: writing or refactoring Python code, structuring modules/[feature]/ layers, or defining Protocol-based interfaces.
shadcn/ui for React with TanStack Form. Use when building UI components, forms, dialogs, tables, toasts, or accessible components.
Use when generating detailed SEO content briefs. Covers target keywords, search intent, outline (H2/H3), word count, internal links, schema requirements, GEO readiness checklist.
Use when building semantic keyword clusters from SERP overlap. Covers seed keyword expansion, Jaccard SERP overlap, intent grouping, pillar/cluster content architecture.
Use when optimizing local SEO. Covers Google Business Profile, NAP consistency, citations, reviews acquisition, Local Pack ranking, location pages, LocalBusiness schema.
Use when designing internal linking strategy. Covers pillar/cluster architecture, anchor text optimization, link distribution, orphan page detection, click depth, broken link audit.
Phase 1: Browse 4 catalog sites via fuse-browser, write CSS-precise observations (oklch values, font-size clamp, grid ratios, border-radius, shadows), declare reference site + 3 elements. Feed specs to Gemini context.
Use when analyzing content quality. Covers E-E-A-T scoring (Experience, Expertise, Authoritativeness, Trustworthiness), anti-cannibalization, keyword distribution, AI content disclosure, search intent matching.
Phase 6: Serve via python3 -m http.server 8899, screenshot light mode (fullPage), screenshot dark mode via browser_screenshot colorScheme:dark, compare 3 declared elements [expected vs present], fix gaps with modify_frontend (max 2 cycles), report.
Use when optimizing entity-based / semantic SEO 2026. Covers entity maps, Google Knowledge Graph resolution, salience scoring, passage-level ranking, about/sameAs/knowsAbout schema, Cloud Natural Language API validation.
Use when optimizing search experience (SXO). Covers intent matching, user personas, user stories, page-type analysis, dwell time, scroll depth, pogo-sticking prevention.
Phase 3: Map design-system.md to 7 Gemini XML blocks (aesthetics, style_reference, typography, color_system, spacing, states, forbidden), call create_frontend, add component variants (Glass/Outline/Flat via CVA).
Use when optimizing for AI search engines (Generative Engine Optimization 2026). Covers Google AI Overviews, ChatGPT, Perplexity, Claude, Gemini, Copilot, LLM-readiness scoring 0-100, llms.txt.
Use when optimizing images for SEO. Covers alt text, descriptive filenames, modern formats (WebP/AVIF), lazy loading, responsive sizing (srcset), ImageObject schema.
Build RESTful APIs with Laravel using API Resources, Sanctum authentication, rate limiting, and versioning. Use when creating API endpoints, transforming responses, or handling API authentication.
Implement real-time WebSocket communication with Laravel Reverb. Use when adding live updates, chat, notifications, or presence features.
Use when integrating AI agents, tool calling, embeddings, structured output, or streaming in Laravel 13 via the `laravel/ai` package. Covers 14+ providers (OpenAI, Anthropic, Gemini, Azure, Groq, DeepSeek, Ollama, Mistral, xAI, Cohere, ElevenLabs, Jina, VoyageAI, OpenRouter).
Laravel 13 database migrations - Schema Builder, columns, indexes, foreign keys, seeders, pgvector. Use when designing database schema or managing migrations.
Use when building JSON:API compliant endpoints in Laravel 13 using the first-party `JsonApiResource` base class. Covers sparse fieldsets, inclusion, links, and response headers.
Integrate Stripe and Paddle payments with Laravel Cashier. Use when implementing subscriptions, invoices, payment methods, webhooks, or billing portals.
Use when migrating Eloquent models, Jobs, Console commands, Controllers, API Resources, Validation, Factories or Seeders to native PHP 8.3 attributes introduced in Laravel 13. Covers all 7 categories of first-party attributes.
Create Blade templates with components, slots, layouts, and directives. Use when building views, reusable components, or templating.
Spatie Laravel Permission - roles, permissions, middleware, Blade directives, teams, wildcards, super-admin, API, testing. Use when implementing RBAC, role-based access control, or user authorization.
Laravel 13 background jobs - PHP Attributes (#[Queue],
FuseCore Modular Architecture - Laravel 13 modular monolith with auto-discovery, React 19 integration, and SOLID principles. Use when creating modules, understanding FuseCore structure, or implementing features in FuseCore projects.
Use when implementing user authentication, API tokens, social login, or authorization. Covers Sanctum, Passport, Socialite, Fortify, policies, and gates for Laravel 13.
Laravel localization - __(), trans_choice(), lang files, JSON translations, pluralization, middleware, formatting. Use when implementing translations.
Livewire 4 reactive components on Laravel 13 - wire:model, actions, events, Volt, Folio. Use when building reactive UI without JavaScript.
Build marketplaces and platforms with Stripe Connect. Use when implementing multi-vendor payments, seller onboarding, commissions, payouts, or split payments.
Use when implementing semantic / vector search in Laravel 13 with PostgreSQL + pgvector. Covers schema setup, embedding workflow, and the new query builder methods (`whereVectorSimilarTo`, `selectVectorDistance`, etc.).
Use when auditing technical SEO. Covers robots.txt, sitemap.xml, Core Web Vitals (LCP/INP/CLS), mobile-first indexing, crawlability, indexability, HTTPS, redirects chains.
Use when optimizing for position 0 featured snippets and AI Overviews. Covers paragraph, list, table, and video snippet recipes with format-specific HTML patterns.
Implement full-text search with Laravel Scout. Use when adding search to Eloquent models with Meilisearch, Algolia, or database driver.
Use when building a strategic SEO roadmap by business type. Covers SaaS, local, e-commerce, publisher, agency playbooks and 90-day prioritized roadmaps.
Use when auditing or generating hreflang for i18n SEO. Covers HTML link tags, HTTP headers, XML sitemap hreflang, self-referencing, return tags, x-default, ISO 639-1 + ISO 3166-1 code validation.
Use when optimizing e-commerce SEO. Covers product schema with AggregateRating, faceted navigation rules, category page intro, out-of-stock handling, internal search, marketplace SEO (Amazon, Etsy, eBay).
Use when planning redirects or site migration. Covers 301 vs 302 vs 307/308, migration plans, redirect chains, link equity preservation, www/non-www, HTTP→HTTPS, 404 monitoring.
Use when detecting, validating, or generating Schema.org JSON-LD markup. Covers Article, Product, LocalBusiness, Organization, BreadcrumbList, FAQPage, VideoObject, Event, Recipe.
Use when analyzing a single page via /seo page. Covers meta extraction, schema validation, header hierarchy, content quality, and GEO readiness for one URL or local file.
Use when optimizing video SEO. Covers VideoObject schema, YouTube metadata, transcripts, chapters, SeekToAction, Clip schema for key moments, BroadcastEvent for live streams.
Use when running a full-site SEO audit via /seo audit. Covers parallel sub-agent orchestration, business-type detection, SEO Health Score 0-100, prioritized action plan.
Use when analyzing or generating XML sitemaps. Covers sitemap.xml, sitemap-news.xml, sitemap-image.xml, sitemap-video.xml, robots.txt, URL coverage checks, sitemap index pattern.
Complete Vite bundling for Laravel - assets, HMR, SSR, frameworks, optimization. Use when configuring frontend build pipeline.
Complete Eloquent ORM for Laravel 13 - PHP Attributes (#[Table],
watchOS platform-specific development with complications, workouts, HealthKit, and Watch Connectivity. Use when building Apple Watch apps, health features, or iPhone-Watch communication.
react-i18next for React 19 - useTranslation hook, TypeScript Selector API, namespaces, pluralization, lazy loading, Suspense integration. Use when implementing translations in React apps (not Next.js).
Use when creating new skills, restructuring existing skills, or improving skill documentation. Generates SKILL.md + references/ structure with proper patterns.
Zustand v5 state management for Next.js 16 App Router. Use when implementing global state, stores, persist, hydration, or client-side state in Client Components.
Optimization guide for fuse-commit-pro commit workflow. Documents settings to reduce token usage.
Zustand v5 state management for React. Use when implementing global state, stores, persist, or client-side state.
SwiftUI fundamentals for all Apple platforms. Use when building views, navigation, data persistence, or state management with SwiftUI across iOS, macOS, iPadOS, watchOS, visionOS.
iOS platform-specific development with XcodeBuildMCP tools for simulator, device, UI automation, and debugging. Use when building iPhone apps, testing on simulator/device, or automating UI interactions.
macOS platform-specific development with menu bar apps, window management, AppKit integration, and notarization. Use when building Mac apps, creating menu bar extras, or distributing outside App Store.
tvOS platform-specific development with focus system, large screen UI, Siri Remote, and media playback. Use when building Apple TV apps, video streaming, or living room experiences.
Summarize current pull request with diff, comments, and changed files. Use when reviewing PRs or before merging.
SEO/SEA/GEO 2026 complete methodology for organic, paid, and AI search optimization.
MCP tools for Xcode automation and Apple documentation access. XcodeBuildMCP for builds, apple-docs for WWDC and API docs. Use when building projects, searching documentation, or accessing WWDC content.
React 19.2 features - use(), useOptimistic, useActionState, useEffectEvent, Activity component, React Compiler. Use when implementing React 19 patterns.
Detects optimal commit type from git changes. Use when analyzing commits, determining commit type, or before committing.
Phase 5: Verify contrast >= 4.5:1 text / 3:1 UI in both light+dark, check no Inter/Roboto/Arial/Open Sans, confirm all colors are OKLCH from design-system.md, validate hover/focus/disabled/loading states, run anti-AI-slop checklist.
Testing Library for React 19 - render, screen, userEvent, waitFor, Suspense. Use when writing tests for React components with Vitest.
TanStack Form v1 - type-safe forms with Zod/Yup/Valibot validation, async validation, arrays, nested fields, React 19 Server Actions
Phase 4: Add Framer Motion scroll reveals (IntersectionObserver), hover scale/opacity transitions, focus ring states, loading skeletons, glassmorphism blur layers, gradient orb backgrounds — all via modify_frontend.
Next.js 16 internationalization with next-intl or DIY. Use when implementing i18n, translations, localization, multilingual, language switch, locale routing, or formatters.
Systematic development workflow: Analyze → Plan → Execute → eLicit → eXamine. Use for ANY development task: features, bug fixes, refactoring, hotfixes. Triggers: "implement", "create", "build", "fix", "add feature", "refactor", "develop". Auto-detects project type (Laravel, Next.js, React, Swift) and loads framework-specific references. Enforces: files <100 lines, interfaces separated, SOLID principles, expert self-review, sniper validation. Modes: --auto (default), --manual, --skip-elicit
Expert Astro 6 framework — routing, output modes, middleware, Vite Environment API, Rust compiler, Content Security Policy, Live Collections, Fonts API. Use when building Astro sites, configuring output, or upgrading from Astro 5.
Use when validating code quality after modifications. Runs sniper agent in isolated forked context for clean, fast validation.
Phase 0: Read sector template (creative/fintech/ecommerce/devtool), generate OKLCH palette with chroma > 0.05, pick approved typography pair (never Inter/Roboto/Arial), define spacing base unit + motion profile.
Phase 2: Write microcopy guide: CTA labels, error messages, empty states, form placeholders — all aligned with identity personality and audience from Phase 0.
visionOS platform-specific development with spatial computing, RealityKit, immersive spaces, and volumes. Use when building Vision Pro apps, 3D experiences, or mixed reality features.
Complete Better Auth - 40+ OAuth providers, 20+ plugins, all adapters, all frameworks. Use when implementing authentication, login, OAuth, 2FA, magic links, SSO, Stripe, SCIM, or session management.
Swift 6 fundamentals for all Apple platforms. Use when implementing concurrency, architecture, testing, i18n, or performance optimization across iOS, macOS, iPadOS, watchOS, visionOS.
App build, code signing, TestFlight, and App Store distribution for all Apple platforms. Use when preparing releases, configuring signing, uploading to TestFlight, or submitting to App Store.
iPadOS platform-specific development with adaptive layouts, keyboard shortcuts, multitasking, and Stage Manager. Use when building iPad apps with split views, external keyboard support, or multi-window features.