pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Essential workflow guidelines for AI agents working on development tasks. Use at the start of every task to ensure proper workflow, skill discovery, port detection, testing methodology, and verification. Consolidates critical prompt updates for consistent agent behavior across all tasks.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Integrate external assets (PixelLab, ElevenLabs) into projects with proper error handling, fallback mechanisms, and testing patterns. Use when generating assets, downloading files, or integrating assets into game code. Standardizes workflow and reduces integration time by 25-35%.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Establish authenticated session for browser-based E2E: register/login via API (curl with cookie jar), then load cookie/state into browser context if supported, or document manual login / test-only bypass and use API verification. Include fallback when cookie/state injection is not supported; revert mocks and document.…
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Canonical flow for starting and verifying a backend dev server. Use before running API tests: check port, start from correct directory, confirm readiness via short-timeout health request. Prevents 60–90+ second curl timeouts and port-conflict misdiagnosis.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Patterns for reliable browser automation, including timeout handling, retry logic, and fallback strategies. Use when browser automation commands hang, timeout, or fail. Provides configurable timeouts, exponential backoff retry logic, and fallback verification methods for Phaser games and web applications.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Comprehensive guide to agent-browser usage patterns, test seam planning workflow, browser testing optimization patterns, and when to use agent-browser vs alternatives. Use when working with web applications, frontend tasks, or when development servers are running.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Document when to use test seams vs. DOM inspection, provide patterns for batching related test commands, create reusable test helper functions, and document efficient waiting strategies. Use when testing Phaser games or web applications to reduce execution time and improve reliability.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Persist with browser testing operations that may take 30-90 seconds. Use when browser testing fails or takes longer than expected. Provides expected wait times, timeout configurations, retry logic, and fallback strategies. Improves verification completeness from 60% to 95%.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Setup and patterns for a Vite + React frontend with Capacitor and Ionic React, plus a separate Next.js backend in a monorepo. Use when creating or modifying a Capacitor mobile app with a Vite frontend and Next.js API, or when adding Capacitor to an existing Vite app with a Next.js backend.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Protocol enforcement and validation patterns for completion marker output. Use when marking tasks complete to ensure 100% protocol compliance. Provides validation patterns, system-level workarounds, and recovery strategies for completion marker protocol violations.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Efficient completion marker generation to prevent timeouts and improve task completion reliability. Use when marking tasks complete to ensure atomic completion marker output. Prevents timeout issues and reduces completion time by 10-15 seconds.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Configurable API base URL in frontend (e.g. Vite): single env variable (e.g. VITEAPIURL), shared API client that reads it, and all call sites use that client. Do not hardcode host/port in multiple files; do not create or commit .env—only .env.example and documentation. Use when adding or changing frontend API calls.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Cookie-based auth from a different origin (e.g. frontend on 3001, backend on 3000) requires Access-Control-Allow-Credentials true and a specific Access-Control-Allow-Origin (not ). If framework middleware does not apply to API routes, add CORS headers in the route handler. Use when debugging cross-origin…
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
When running create-next-app in an existing directory (e.g. backend/): remove or rename existing package.json if the tool refuses to overwrite; prefer absolute path for target; for API-only setups, strip UI (layout, page, globals, public) and clear .next before re-running type-check. Use when scaffolding Next.js in an…
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Create Cursor rules for persistent AI guidance. Use when the user wants to create a rule, add coding standards, set up project conventions, configure file-specific patterns, create RULE.md files, or asks about .cursor/rules/ or AGENTS.md.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Guides users through creating effective Agent Skills for Cursor. Use when the user wants to create, write, or author a new skill, or asks about skill structure, best practices, or SKILL.md format.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Create custom subagents for specialized AI tasks. Use when the user wants to create a new type of subagent, set up task-specific agents, configure code reviewers, debuggers, or domain-specific assistants with custom prompts.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Run a command with a time limit in a cross-platform way. Do not rely on GNU timeout (coreutils)—it is not default on macOS. Use when agents may run on macOS or when timeout 10s npm run dev fails.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Standardized patterns for detecting, starting, monitoring, and maintaining development server connections. Use when connecting to dev servers, managing server lifecycle, or when connection losses occur during browser automation. Eliminates 2-3 minutes of server management overhead per task.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Automatically detect development server ports from configuration files, running processes, or terminal output. Use when starting browser testing, connecting to dev servers, or when port configuration is unclear. Checks vite.config.ts, package.json, running processes, and terminal output to find the actual port in use.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Patterns for handling ElevenLabs API file outputs, including path management and file relocation. Use when generating audio with ElevenLabs tools, when files are written to unexpected locations, or when outputdirectory parameter is ignored. Files are always written to $HOME/Desktop regardless of outputdirectory…
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Generate speech, transcribe audio, create voice agents, compose music, and manage voices using ElevenLabs MCP Server. Use when working with text-to-speech, speech-to-text, voice cloning, conversational AI agents, or music composition.
pmarashian/cursor-agent-skills
Skill Claude CodeCodex
Rules for .env file handling, .env.example template format, and what's allowed vs forbidden. Use when working with environment variables, API keys, or configuration files.