This is a comprehensive reference for prompt engineering techniques that goes beyond basic "write clear instructions" advice. It covers chain-of-thought reasoning, few-shot example selection strategies, template systems with variable interpolation, and systematic optimization workflows. You'd reach for this when building production LLM features that need consistent outputs, debugging flaky prompts, or implementing RAG systems with proper context handling. The included template library and optimization scripts are practical, though the real value is in the structured patterns like progressive disclosure and instruction hierarchy. It treats prompts as code worth versioning and testing, which is the right mindset if you're doing anything beyond one-off ChatGPT queries.
npx -y skills add sickn33/antigravity-awesome-skills --skill prompt-engineering-patterns --agent claude-codeInstalls into .claude/skills of the current project.
Select a file.
sickn33/antigravity-awesome-skills
moizibnyousaf/ai-agent-skills
github/awesome-copilot