ma

Plugin ma from marketplace marcus-friction-plugins in marcus-friction/agents. Commands read from the repo's manifest — 1 month ago.

Skills (43)

• adversarial-review

  Independently challenge elevated or significant architecture, security, data, migration, permission, deployment, or production changes. Use after a primary or deep review, or when explicitly requested; routine changes do not require it.

• architecture-review

  Review code or plans when a change affects component boundaries, dependencies, contracts, data ownership, layering, or adopted project architecture decisions.

• build-start-scripts

  Standards and patterns for building reliable local dev startup scripts (serve.sh, start.sh). Use this skill when creating, modifying, or reviewing any shell script that boots Docker containers, Laravel Sail, Nuxt dev servers, or background services. Also use when the user mentions "serve script", "s

• code-review-excellence

  Guide specific, actionable, evidence-backed code review feedback without style noise. Use as the method layer inside a multi-angle review or when improving review quality.

• compound

  Assess solved problems for reusable project knowledge and, when authorized, capture only high-relevance learnings. Use after substantial troubleshooting or tricky implementation, when the user asks to document a solution or accepts a proposed durable handoff, or during an explicit wrap.

• contribute-back

  Compare local agent-distribution improvements with a named upstream repository and prepare a safe contribution proposal. Use only when the user asks to contribute, upstream, or open a pull request; publication requires a separate exact batch approval.

• copy-editing

  When the user wants to edit, review, or improve existing marketing copy, or refresh outdated content. Also use when the user mentions 'edit this copy,' 'review my copy,' 'copy feedback,' 'proofread,' 'polish this,' 'make this better,' 'copy sweep,' 'tighten this up,' 'this reads awkwardly,' 'clean u

• copywriting

  Write clear, user-centered marketing and interface copy for landing pages, UI microcopy, CTAs, emails, product descriptions, feature announcements, and release notes.

• deploy

  Prepare, deploy, verify, and troubleshoot Laravel and Laravel + Nuxt applications on Laravel Cloud using the official Cloud CLI. Use for a first deployment, redeployment, Cloud readiness check, or failed Cloud release; also when deploy is explicitly requested. Preserve read-only requests and existin

• end2end

  Plan and run browser-based end-to-end tests when the user asks to test an app, verify a UI, check a user flow, or interact with an application in a browser. Distinguishes test-only work from explicitly authorized test-and-fix work and reports evidence progressively.

• laravel-best-practices

  Apply this skill whenever writing, reviewing, or refactoring Laravel PHP code. This includes creating or modifying controllers, models, migrations, form requests, policies, jobs, scheduled commands, service classes, and Eloquent queries. Triggers for N+1 and query performance issues, caching strateg

• migrate-project

  Plan a legacy rewrite or migration into the project's adopted target components while preserving domain behavior and data. Use whenever the user asks to rewrite, port, or migrate an existing application, script, or service.

• nitro

  Nitro is the framework-agnostic server toolkit (powering Nuxt) for building and deploying web servers anywhere. Use when working with nitro.config, server routes/event handlers, route rules, caching, storage, tasks, websockets, or deploying to Node/Bun/Deno/Cloudflare/Vercel.

• nuxt

  Nuxt full-stack Vue framework with SSR, auto-imports, and file-based routing. Use when working with Nuxt apps, server routes, useFetch, middleware, or hybrid rendering.

• onboard-project

  Safely establish or refresh project context for an existing repository without losing documentation or local agent rules. Use when setting up a cloned or mature codebase, fixing agent blindness, reconciling new .agents/templates, establishing architecture baselines, or asking "what is this codebase"

• path-to-10

  Evaluate an output, plan, architecture decision, or implementation against its accepted intent and project evidence. Use when the user asks for a path to 10, quality score, gap-to-excellent analysis, or rigorous quality assessment.

• performance-review

  Review code or plans when a change can materially affect latency, throughput, capacity, database work, memory, network, rendering, or cache behavior.

• pinia

  Pinia official Vue state management library, type-safe and extensible. Use when defining stores, working with state/getters/actions, or implementing store patterns in Vue apps.

• plan

  Create evidence-backed implementation plans. Use when the user asks for a plan, implementation plan, or execution strategy, or when multi-step, cross-boundary, or high-risk work must be scoped before implementation.

• playwright

  Apply when writing, reviewing, or debugging Playwright tests, fixtures, or configuration. Use as the browser-testing method layer for end-to-end work, with stable locators, isolated data, and web-first assertions.

• release

  Prepare, publish, verify, and recover source or package releases when the user explicitly requests a release or wrap routes an adopted release disposition. Use for release relevance, version/artifact preparation, immutable publication, partial-state resume, and release verification. Invocation alone

• review-plan

  Challenge an implementation plan for scope, architecture, design, security, and verification gaps. Use after drafting any implementation plan or when asked whether a plan is ready.

• review

  Perform a scoped multi-angle code review of local changes, an explicit path set, or a branch or pull-request diff before merging or when the user asks for review. Defaults to non-mutating review, records actionable work in an already-authorized plan tracker, and supports only explicitly selected det

• security-review

  Review code and plans for proportionate, evidence-backed security controls. Use for security-sensitive changes or the security pass of a scoped code review.

• seo-review

  Comprehensive SEO, Core Web Vitals, and Semantic HTML review. Use when building any user-facing page, deploying new routes, or auditing search performance. Proactively suggest when new pages or dynamic routes are added to the project, but run only when explicitly requested or accepted. Review a supp

• skill-creator

  Create or improve an agent skill and evaluate it proportionately. Use when a user asks to create, edit, optimize, validate, benchmark, or improve the triggering description of a skill.

• stack-architecture-review

  Scoped, report-only Architecture Persona for multi-agent reviews of adopted Laravel/Nuxt boundaries.

• stack-performance-review

  Scoped, report-only Performance Persona for multi-agent reviews of adopted Laravel/Nuxt runtime boundaries.

• stack-security-review

  Scoped, report-only Security Persona for multi-agent reviews of adopted Laravel/Nuxt trust boundaries.

• start-project

  Start a new project through a focused product interview, the adopted Laravel/Nuxt core stack, a complete project-document baseline, and a persisted executable first-increment plan. Use for new products, empty or scaffold-only repositories, or an explicit start-project request; use onboard-project on

• systematic-debugging

  Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

• tailwind-v4-shadcn

  Tailwind v4 + shadcn/ui setup (@theme inline + CSS variables). Fixes tw-animate-css, @apply, dark mode.

• terminal-blindness-fix

  Diagnose and fix "Terminal Blindness" in local VS Code only when the user explicitly requests it or command output has been observed blank, unreadable, or missing because capture failed. Do not run during routine project setup.

• test-driven-development

  Use when implementing testable feature or bug behavior. Write a failing test for the intended observable change before changing production behavior; characterize existing code instead of discarding it.

• update-agents

  Refresh upstream-managed agent skills, inactive documentation candidates, and discovery adapters while preserving project-owned files. Use when asked to update, sync, or pull the latest agent rules in one or more projects.

• vite

  Vite build tool configuration, plugin API, SSR, and Vite 8 Rolldown migration. Use when working with Vite projects, vite.config.ts, Vite plugins, or building libraries/SSR apps with Vite.

• vitest

  Vitest fast unit testing framework powered by Vite with Jest-compatible API. Use when writing tests, mocking, configuring coverage, or working with test filtering and fixtures.

• vue-best-practices

  MUST be used for Vue.js tasks. Strongly recommends Composition API with script setup and TypeScript as the standard approach. Covers Vue 3, SSR, Volar, vue-tsc. Load for any Vue, .vue files, Vue Router, Pinia, or Vite with Vue work. ALWAYS use Composition API unless the project explicitly requires O

• vue-router-best-practices

  Use when configuring Vue Router 4 routes, navigation guards, route-param changes, or route-component lifecycle cleanup.

• vue-testing-best-practices

  Use for Vue.js testing. Covers Vitest, Vue Test Utils, component testing, mocking, testing patterns, and Playwright for E2E testing.

• vue

  Vue 3 Composition API, script setup macros, reactivity system, and built-in components. Use when writing Vue SFCs, defineProps/defineEmits/defineModel, watchers, or using Transition/Teleport/Suspense/KeepAlive.

• vueuse-functions

  Apply VueUse composables in projects that already use VueUse, or when the user explicitly asks to evaluate or adopt it, when they materially simplify established Vue.js or Nuxt behavior. Do not add VueUse or optional integrations without approval.

• wrap

  Complete and report an accepted increment, and when the user explicitly asks to wrap, commit, push, integrate, or finish delivery, prepare a provider-neutral lifecycle preview through release and safe cleanup. A generic wrap is read-only for Git and external effects; every mutation requires separate