prompt-engineering

Comprehensive prompt engineering techniques for Claude models. Use this skill when crafting, optimizing, or debugging prompts for Claude API, Claude Code, or any Claude-powered application. Covers system prompts, role prompting, multishot examples, chain of thought, XML structuring, long context handling, extended thinking, prompt chaining, Claude 4.x-specific best practices, and agentic orchestration including subagents, agent loops, skills, MCP integration, and multi-agent workflows.

$ Installer

git clone https://github.com/cuba6112/researchagent /tmp/researchagent && cp -r /tmp/researchagent/.claude/skills/prompt-engineering ~/.claude/skills/researchagent

// tip: Run this command in your terminal to install the skill