VividKit Crystal clear AI coding
VI
Choose Your Setup Get Started with AgentKit Continue with ClaudeKit Migrate from ClaudeKit to AgentKit Clean cutover from ClaudeKit What Is AgentKit? How AgentKit Works AgentKit Kits, Skills, Agents & Hooks AgentKit Runtime Support AgentKit Desktop App AgentKit Configuration AgentKit CLI Quick Reference AgentKit Skills Cheatsheet AgentKit Workflows AgentKit Statusline Update AgentKit CLI & Kits AgentKit Helper Clean reinstall of AgentKit AgentKit Troubleshooting What is ClaudeKit? ClaudeKit CLI Guide Command Finder Commands Cheat Sheet Workflow Recipes CLI Quick Reference Claude Mechanics Permission Modes ClaudeKit Hooks Coexistence ClaudeKit x Codex CK → Other coding tools How ClaudeKit Works Inside ClaudeKit Finding Your Unknowns Session Recovery Fix from Logs UI/UX Guide Accounts Switcher IDE Config Remote Control Codex App System Diagramming UI Review Gate Promotions Support VividKit

Quick Ref / Command

Marketing Kit

/ak:claude-code

Claude Code reference navigator

Answers Claude Code setup, commands, skills, MCP, hooks, plugins, IDE, CI/CD, enterprise, troubleshooting, and advanced-feature questions from topic references.

01

Identify topic

02

Load references

03

Explain concepts

04

Provide examples

Rule 01

Answer from the relevant topic reference instead of giving generic Claude Code advice.

Rule 02

Load multiple references when a question spans setup, extensibility, workflow, and troubleshooting.

Rule 03

Separate core concepts: subagents, skills, slash commands, hooks, MCP servers, and plugins have different roles.

Execution Map

Core lanes from input to output, aligned with the command's real execution path.

01

Start

Input, scope, route

  1. 1 Identify topic Read the question and classify it as setup, slash commands, skills, MCP, hooks, IDE, CI/CD, enterprise, troubleshooting, API, or best practices.
  2. 2 Load references Open the relevant reference file from the guide table; load multiple files for complex questions.
02

Work

Agent / skill execution

  1. 3 Explain concepts Map the answer to Claude Code concepts: subagents, skills, slash commands, hooks, MCP servers, and plugins.
  2. 4 Provide examples Give specific setup, command, configuration, or workflow examples from the loaded reference material.
03

Verify

Gate, review, validation

  1. 5 Troubleshoot path For auth, MCP, performance, or debug-mode issues, route to troubleshooting references before proposing fixes.
  2. 6 Cite sources Use the documented official docs, Context7 topic search, GitHub, and support sources when deeper current detail is needed.

Sample Prompt

Concrete invocations for each flag, subcommand, mode, or route available in the live workflow.

Install and authenticate Recommended 
/ak:claude-code installation and authentication
Use when:
Use when setting up Claude Code for the first time.
Expected:
Guidance from the getting-started reference.
Create a skill 
/ak:claude-code creating Agent Skills
Use when:
Use when building or packaging a SKILL.md with bundled resources.
Expected:
Skill structure and metadata guidance from the Agent Skills reference.
MCP setup 
/ak:claude-code MCP server configuration
Use when:
Use when connecting Claude Code to external tools.
Expected:
Configuration and authentication advice for MCP integrations.
Troubleshooting 
/ak:claude-code troubleshooting authentication failures
Use when:
Use when Claude Code auth, performance, or debug behavior is failing.
Expected:
A reference-backed diagnosis path, not a guess.

Handled Scope

  • Installation
  • Slash commands
  • Agent Skills
  • MCP servers
  • Hooks
  • Plugins
  • IDE integration
  • CI/CD
  • Enterprise deployment
  • Troubleshooting

Next