prompt-engineering

Installation
Summary

Advanced techniques for maximizing LLM reliability, consistency, and output quality through systematic prompt design.

  • Five core patterns: few-shot learning with 2-5 examples, chain-of-thought reasoning for multi-step logic, systematic optimization through A/B testing, reusable template systems with variables, and system prompts for persistent global behavior
  • Progressive disclosure approach starts simple and adds complexity only when needed, with four escalation levels from direct instructions to full example-driven prompts
  • Covers instruction hierarchy, error recovery strategies, and production best practices including versioning, performance monitoring, and edge case testing
  • Identifies common pitfalls like over-engineering, example pollution, context overflow, and ambiguous instructions with concrete guidance on avoiding each
SKILL.md

Prompt Engineering Patterns

Advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability.

Core Capabilities

1. Few-Shot Learning

Teach the model by showing examples instead of explaining rules. Include 2-5 input-output pairs that demonstrate the desired behavior. Use when you need consistent formatting, specific reasoning patterns, or handling of edge cases. More examples improve accuracy but consume tokens—balance based on task complexity.

Example:

Extract key information from support tickets:

Input: "My login doesn't work and I keep getting error 403"
Output: {"issue": "authentication", "error_code": "403", "priority": "high"}

Input: "Feature request: add dark mode to settings"
Related skills

More from davila7/claude-code-templates

Installs
499
GitHub Stars
27.2K
First Seen
Jan 25, 2026