prompt-engineering

Prompt Type Quick Reference

.claude/commands/<name>.md

/command-name

references/command.md

.{.super-agent,.claude}/agents/<name>.md

@agent-name

references/agent.md

.claude/CLAUDE.md

references/context-file.md

• references/orchestration.md

  - Orchestrator design for calling subagents

• references/permission-syntax.md

  - Permission syntax for allowed-tools

• references/hooks.md

  - Lifecycle hook configuration

Core Principles

1. Single Responsibility

• ✅ Environment setup only / Code implementation only

2. Independence from Caller

• ✅ "Analyze the provided code and identify issues..."

3. Conciseness

4. Noise Avoidance

• Avoid examples in multiple languages (choose the primary language)
• Avoid hypothetical file paths (CONTRIBUTING.md, etc.)
• Omit detailed steps that the LLM can infer

Formatting Rules

• No h1 headings: Do not start with

  #

• Language:

  description

  in the project's primary language; body can also be in primary language
• XML tags: Use for structuring when there are multiple sections

Orchestration

1. Invocation template required: Include complete Task tool usage example
2. Responsibility separation: Subagents should be generic; task-specific details go in templates

Special Rules for Context Files

• 80% rule: Only information needed by 80% of tasks
• Index-first: Reference details via pointers
• Scrutinize commands: Only commands the LLM will autonomously execute
• Target under 200 lines