claude-expert

Raphael67's avatarfrom Raphael67

Expert in Claude prompting, skill creation, hooks management, MCP configuration, and sub-agents. Use when writing prompts, creating Claude Code skills, configuring hooks, setting up MCP servers, creating custom sub-agents, or asking about Claude Code architecture.

⭐0stars🔀0forks📁View on GitHub🕐Updated Jan 10, 2026
[Prompt Templates and Packaging]

When & Why to Use This Skill

This Claude skill serves as a comprehensive technical authority for developers building on the Claude Code platform. It provides expert guidance on prompt engineering, skill development, and agent architecture, enabling users to create, configure, and optimize complex AI workflows. By mastering XML-based prompting, Model Context Protocol (MCP) integrations, and sub-agent orchestration, it streamlines the process of extending Claude's native capabilities.

Use Cases

  • Advanced Prompt Engineering: Designing high-performance prompts using XML tags, Chain-of-Thought (CoT), and few-shot examples to ensure structured and reliable AI outputs.
  • Custom Skill Creation: Developing and packaging new Claude Code skills via SKILL.md files to automate repetitive developer workflows and enhance environment-specific functionality.
  • MCP Infrastructure Setup: Configuring Model Context Protocol servers to connect Claude with external tools, databases, and local resources for real-time data interaction.
  • Multi-Agent System Design: Architecting sub-agents with specific tool permissions and instructions to handle complex, parallelized tasks within a secure framework.
  • Workflow Security & Hooks: Implementing PreToolUse hooks and validation logic to monitor, block, or confirm sensitive tool executions for improved safety and auditing.
nameclaude-expert
descriptionExpert in Claude prompting, skill creation, hooks management, MCP configuration, and sub-agents. Use when writing prompts, creating Claude Code skills, configuring hooks, setting up MCP servers, creating custom sub-agents, or asking about Claude Code architecture.
user-invocabletrue

Claude Expert Skill

Expert guidance for Claude prompting techniques, Claude Code extensibility, and agent architecture.

Quick Reference

Topic File Use When
Prompting PROMPTING.md Writing effective prompts, XML tags, CoT, few-shot
Skills SKILLS.md Creating or editing Claude Code skills
Workflows WORKFLOWS.md Building multi-step workflow prompts
Commands COMMANDS.md Creating /commands for quick invocation
Hooks HOOKS.md Setting up PreToolUse, validation, notifications
MCP MCP.md Adding MCP servers, tools, resources
Sub-agents SUBAGENTS.md Creating custom agents, Task tool config

Core Principles

Prompting

  • Use XML tags for structure (<context>, <instructions>, <constraints>)
  • Be explicit rather than implicit
  • Specify format to get formatted output
  • Provide examples for complex tasks

Skills

  • Skills = markdown files that extend Claude's capabilities
  • Description is critical for auto-discovery
  • Keep SKILL.md < 500 lines, split into reference files
  • Use semantic XML tags in content

Hooks

  • PreToolUse hooks validate before execution
  • Can block, allow, or ask for confirmation
  • Exit codes: 0=allow, 2=block, JSON output for ask

MCP

  • Servers defined in ~/.claude/.mcp.json
  • Provide external tools and resources
  • Use stdio, SSE, or HTTP transport

Sub-agents

  • Defined in .claude/agents/ or ~/.claude/agents/
  • YAML frontmatter + markdown instructions
  • Can specify model, tools, allowed-tools

Workflows

  • Variables at top for constants
  • Instructions for rules/constraints
  • Step-by-step workflow section
  • Report template at end

Commands

  • Quick-access prompts in .claude/commands/
  • Can restrict tools and specify model
  • Support argument passing

When to Read Reference Files

Read PROMPTING.md when:

  • User asks to write a prompt or system message
  • Optimizing an existing prompt
  • Structuring complex instructions

Read SKILLS.md when:

  • Creating a new skill
  • Editing skill YAML frontmatter
  • Debugging skill discovery
  • Understanding cookbook/prompts patterns

Read WORKFLOWS.md when:

  • Building multi-step workflow prompts
  • Defining variables and instructions
  • Creating orchestrated workflows
  • Handling parallel execution

Read COMMANDS.md when:

  • Creating /command shortcuts
  • Setting up prime or install commands
  • Understanding command vs skill differences

Read HOOKS.md when:

  • Setting up security validation
  • Adding notifications or logging
  • Configuring PreToolUse patterns

Read MCP.md when:

  • Adding external tool servers
  • Configuring MCP resources
  • Troubleshooting MCP connections

Read SUBAGENTS.md when:

  • Creating custom agents
  • Configuring agent tools/permissions
  • Understanding Task tool options
  • Setting up parallel agent execution
  • Managing multi-agent safety