MigrationBox-v4

Use this agent when you need to analyze and provide architectural guidance for your codebase. This includes reviewing project structure, identifying architectural patterns, suggesting improvements, and providing recommendations for code organization. For example: <example>Context: The user wants to understand the overall architecture of their Azure analyzer project and get recommendations for improvements.<user>Architect my code</user><assistant>I'll use the code-architect agent to analyze your project architecture and provide detailed guidance.</assistant></example>

Use this agent when you need to test and review code that has been recently written. For example, after a developer finishes implementing a feature or fixing a bug, call this agent to run comprehensive tests and review the code quality. Example: <example>Context: The user has just written a new function that processes user authentication. user: "Here's the authentication function I just wrote:" + function code + assistant: "Let me use the code-tester-reviewer agent to test and review this authentication code." </example>

Use when a user asks to search, install, list, or remove skills with the Context7 ctx7 skills CLI (including npx ctx7) and needs correct subcommands or client flags.

Guide for performing Chromium version upgrades in the Electron project. Use when working on the roller/chromium/main branch to fix patch conflicts during `e sync --3`. Covers the patch application workflow, conflict resolution, analyzing upstream Chromium changes, and proper commit formatting for patch fixes.

Use this agent when you need to build, review, or architect full-stack applications. This includes tasks like creating frontend components with React/Vue, building backend APIs with Node.js/Python, designing database schemas, implementing authentication/authorization, setting up deployment pipelines, and reviewing code for security, performance, and maintainability. Example: User says 'Build a REST API with user authentication and a React dashboard' - this agent would handle the complete stack development from database to frontend. Example: User says 'Review this Node.js endpoint for security issues' - this agent would analyze the code for vulnerabilities, injection attacks, and best practices.

A service mesh is an infrastructure layer that provides transparent service-to-service communication with built-in observability, traffic management, and security features without requiring application code changes.

Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).

Use this skill when the user asks to save, remember, recall, or organize memories. Triggers on: 'remember this', 'save this', 'note this', 'what did we discuss about...', 'check your notes', 'clean up memories'. Also use proactively when discovering valuable findings worth preserving.

Auto-activate when ANY error message, crash, failure, timeout, disconnection, or degraded performance is detected across Claude Desktop, Claude Code, or Cowork. Triggers on: MCP server errors, connection failures, ENOENT/EACCES/ETIMEDOUT errors, 'server disconnected', 'spawn failed', 'Required parameter error', JSON parse failures, extension install failures, Docker container errors, Node.js version mismatches, PATH resolution failures, OAuth/SSO errors, keychain errors, memory/CPU spikes, tool not available, transport mismatch, and any stderr output from MCP logs. Also use proactively when performing health checks, system diagnostics, or preventive maintenance on Claude product ecosystems.

Intelligent MCP server dependency analyzer and resolver. Auto-detects requirements, pre-installs dependencies (UV, Node, Python packages), validates compatibility, and prevents installation failures BEFORE they occur.

Intelligent MCP server dependency analyzer and resolver. Auto-detects requirements, pre-installs dependencies (UV, Node, Python packages), validates compatibility, and prevents installation failures BEFORE they occur.

Convert 'Applied intelligently' Cursor rules (.cursor/rules/*.mdc) and slash commands (.cursor/commands/*.md) to Agent Skills format (.cursor/skills/). Use when the user wants to migrate rules or commands to skills, convert .mdc rules to SKILL.md format, or consolidate commands into the skills directory.