agents

Structured brainstorming for exploring new features or solving complex problems

Scope, architect, and plan new tasks

Multi-angle code review before merging

Summarize the day's work and put it in context

Wrap up work — atomic commits and push to origin

Full end-to-end (E2E) testing skill utilizing the browser. Make sure to use this skill whenever the user asks to "test the app", "run end to end tests", "verify the UI", "check if the app works", or wants you to use the browser to interact with and test the application flow. This skill orchestrates creating a test plan, getting user approval, navigating the application using the browser, independently fixing obstacles, and generating a progressive test report.

Analyzes the current project repository and workflows to provide a high-level status report. Use this skill when the user asks for a status update, wants to know "what's next", asks where development left off, or needs a summary of recent work to regain context. Do NOT use this skill if the user is asking you to actually implement the next feature, commit code, or search the codebase for specific files.

Interactive onboarding and project planning. Make sure to use this skill whenever the user mentions setting up a new project, wanting to brainstorm a new idea, creating a new product from scratch, or asks to start the project workflow.

Pulls the latest agent rules and skills from the remote repository without wiping local project customizations. Use this skill when the user asks to "update agents", "sync agents", or "pull the latest agent rules".

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 strategies, authorization and security patterns, validation, error handling, queue and job configuration, route definitions, and architectural decisions. Also use for Laravel code reviews and refactoring existing Laravel code to follow best practices. Covers any task involving Laravel backend PHP code patterns.

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 Options API.

Design consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates a preview page artifact. Creates .agents/rules/11_design.md as your project's design source of truth.

YC Office Hours — two modes. Startup mode: six forcing questions that expose demand reality, status quo, desperate specificity, narrowest wedge, observation, and future-fit. Builder mode: design thinking brainstorming for side projects, hackathons, learning, and open source. Saves a design doc. Use when asked to "brainstorm this", "I have an idea", "help me think through this", "office hours", or "is this worth building". Proactively suggest when the user describes a new product idea or is exploring whether something is worth building — before any code is written.

Rigorous "Mega Review" pre-landing pipeline. Enforces Scope Drift Detection, ASCII Test Flow generation, and Fix-First Auto-Fixing. Requires task.md and implementation_plan.md. Use when you're about to merge, land, or push code to main, even if you think the changes are small. Proactively suggest this skill before any branch merge or PR submission.

Perform a destructive "Red Team" review of the current changes to eliminate shared blind spots. Best used with a secondary model. Use after any code review or plan review, and before deploying to production. Proactively suggest when merging significant changes.

Architecture compliance checklist for code review

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, Sail, dev servers, or background services. Also use when the user mentions "serve script", "startup script", "docker compose up", "sail up", or asks to fix orphaned containers, port conflicts, or flaky local environments. Proactively suggest when you see startup-related issues in scripts being edited.

Create engaging changelogs summarizing recent merges to the main branch

Meta-level code review guidance — how to review well, not just what to check

Document a recently solved problem as structured, searchable knowledge so future work benefits from past solutions. Use this skill after solving non-trivial bugs, debugging sessions, or tricky implementations. Proactively suggest this skill when a session involved significant troubleshooting, dead-end investigation, or a fix that others would likely encounter again.

Scan local agent ecosystem (.agents/) for modifications or new skills, propose them to the user, and automatically create a Pull Request to the central marcus-friction/agents repository.

The Seven Sweeps framework for reviewing and enhancing existing copy. Focuses on clarity, voice/tone, benefits, proof, specificity, emotion, and risk reversal.

Writing principles and best practices for clear, compelling, and user-centric marketing and UI copy. Use this skill when generating landing pages, writing UI microcopy, crafting CTAs, composing emails, writing product descriptions, feature announcements, or changelog entries.

Make sure to use this skill whenever the user mentions setting up a fresh project, cloning a new repo, fixing agent blindness, establishing baselines, or asking 'what is this codebase'. It ensures the agent has the necessary architectural context and rules tailored to the tech stack.

A rigorous meta-workflow designed to enforce a ruthless 10/10 quality standard on agent outputs, plans, and architectural decisions. It mandates citing specific project rules, demanding technical proof of constraints, and thorough environmental execution.

Performance analysis checklist for code review

Meta-level guidance for reviewing and challenging implementation plans using the Mega Plan Review pipeline. Use whenever you've drafted an implementation plan or design doc and need to evaluate it for completeness, scope gaps, and architectural flaws before proceeding to implementation. Proactively suggest this skill after any /plan workflow or when the user says "review my plan" or "is this plan solid".

Security audit checklist for code 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.

Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.

Structured debugging methodology — reproduce, isolate, hypothesize, verify, fix

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

Fixes "Terminal Blindness" in local VS Code environments where shell integration prevents the agent from reading terminal output. Run this skill when setting up a new project or if terminal outputs from commands appear blank.

TDD workflow — write failing tests first, then implement, then refactor

UI quality, responsiveness, and accessibility review checklist for Nuxt/Tailwind