AI agent skills: architect (PRD planner) + ralph (autonomous dev subagent)
Agent Claude Code
Software architect for system design, technical decision-making, API design, and architecture documentation. Use when you need high-level design before implementation, or to evaluate technical approaches. Triggered by: 'design the system', 'architecture review', 'technical design', 'API design', 'system diagram'.
Agent Claude Code
Site Reliability Engineer for monitoring setup, alerting, incident response, performance optimization, and reliability improvements. Use for uptime issues, performance bottlenecks, and observability. Triggered by: 'monitoring', 'alerting', 'incident', 'reliability', 'performance', 'SLA', 'observability'.
Agent Claude Code
Board member: Technical Lead. Evaluates technical feasibility, stack decisions, scalability bottlenecks, build vs. buy decisions, and integration complexity. Used by the visionary skill during the Board of Directors phase.
Agent Claude Code
Mobile QA specialist for Expo/React Native apps. Validates the app works on simulator and device using: Expo Doctor preflight, Jest + RNTL integration tests, and Maestro E2E YAML flows mapped to USER-JOURNEY.md. Does NOT use Stagehand or Playwright (browser-only). E2E runs via EAS nightly. Use after ralph-mobile…
Agent Claude Code
QA specialist that PROVES the app works by actually running it with playwright-cli. Opens a real browser, navigates, clicks, fills forms, takes screenshots, checks console errors. Uses the globally installed playwright-cli — no setup needed. NEVER skips UI testing. Use after ralph implements a feature. Triggered by…
Agent Claude Code
Use this agent when you need to design, create, or improve UI/UX for any feature or component in the project. This includes creating or updating the Semantic Design System, generating UI designs for web or mobile, implementing components with proper design patterns, or reviewing existing UI for improvements. This…
Agent Claude Code
Maps all user flows for a product with extreme clarity — acquisition, auth, onboarding, core usage, payments, support, churn — for every persona. Produces Mermaid flowcharts and a USER-JOURNEY.md that becomes the north star: if the system doesn't fulfill this journey, it's incomplete. Use after a vision/epic is…
Agent Claude Code
Board member: User Representative. Advocates for the end user — maps jobs-to-be-done, pain points, delight moments, and onboarding friction. Used by the visionary skill during the Board of Directors phase.
Agent Claude Code
Strategic vision decomposition. Convenes a Board of Directors agent team to analyze a business vision from all angles (business, marketing, UX, risk, tech, compliance), then produces an EPIC document with bounded domains, integration contracts, and a prioritized PRD roadmap. Triggers user-journey mapping. Use when the…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: