code-review-expert
Structured code review checklists: SOLID, security, performance, boundary conditions, removal planning. Injected into code-reviewer agent.
integration-rules
Ultra Builder Pro system integration rules
security-rules
Ultra Builder Pro security rules
testing-rules
Ultra Builder Pro testing discipline rules
ultra-review
Parallel code review orchestration with 7 specialized agents + coordinator. Zero context pollution - all output via JSON files.
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
ai-collab-base
Shared collaboration protocol, modes, and prompt templates for AI collab skills. Consumed by gemini-collab, codex-collab, and ultra-verify as a shared foundation.
codex-collab
Dual-AI collaboration with Codex. Use for architecture opinions, comparative verification, project understanding. For code review, use the official /codex:review plugin directly — this skill no longer wraps it. Triggers: 'ask Codex', 'Codex opinion', 'let Codex check', 'compare with Codex'.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
gemini-collab
This skill should be used when the user asks to 'ask Gemini', 'Gemini review', 'let Gemini check', 'Gemini analysis', 'dual AI', or mentions 'gemini' in any collaborative context for code review, project analysis, architecture opinions, or comparative verification.
ultra-research
Think-Driven Interactive Discovery - Deep research with step-file architecture for high-density output
ultra-verify
This skill should be used when the user asks to 'ultra-verify', 'cross-verify', 'triple review', 'all AIs check', 'multi-AI verify', 'three-way check', or wants independent analysis from all three AI models (Claude + Gemini + Codex).
use-railway
>