prompt-engineering

Advanced prompt engineering techniques including Anthropic's official best practices and research-backed persuasion principles.

Includes:

• Few-Shot Learning - Teach by showing examples

• Chain-of-Thought - Step-by-step reasoning

• Prompt Optimization - Systematic improvement through testing

• Template Systems - Reusable prompt structures

• System Prompt Design - Global behavior and constraints

Persuasion Principles (from Prompting Science Report 3):

Principle	Use For	Example
Authority	Discipline enforcement	"YOU MUST", "No exceptions"
Commitment	Accountability	"Announce skill usage", "Choose A, B, or C"
Scarcity	Preventing procrastination	"IMMEDIATELY", "Before proceeding"
Social Proof	Establishing norms	"Every time", "X without Y = failure"
Unity	Collaboration	"our codebase", "we both want quality"

Key Concepts:

• Context Window Management - The window is a shared resource; be concise

• Degrees of Freedom - Match specificity to task fragility

• Progressive Disclosure - Start simple, add complexity when needed