Use when prompts produce inconsistent or unreliable outputs, need explicit structure and constraints, require safety guardrails or quality checks, involve multi-step reasoning that needs decomposition, need domain expertise encoding, or when user mentions improving prompts, prompt templates, structured prompts, prompt optimization, reliable AI outputs, or prompt patterns.
Install
npx skills add lyndonkl/claude --skill meta-prompt-engineeringnpx skills add lyndonkl/claude --skill meta-prompt-engineering -a claude-code -gnpx skills add lyndonkl/claude --skill meta-prompt-engineering -a codex -ggemini skills install https://github.com/lyndonkl/claude.git --path skills/meta-prompt-engineeringgh skill install lyndonkl/claude meta-prompt-engineeringgit clone --depth 1 https://github.com/lyndonkl/claude /tmp/lyndonkl__claude
mkdir -p ~/.claude/skills ~/.agents/skills
cp -R /tmp/lyndonkl__claude/skills/meta-prompt-engineering ~/.claude/skills/meta-prompt-engineering # Claude Code
cp -R /tmp/lyndonkl__claude/skills/meta-prompt-engineering ~/.agents/skills/meta-prompt-engineering # Codex, Cursor, Gemini CLI, Copilot, OpenCode