prompt-engineering-models

Effective system prompts for Claude models require structured input, few-shot examples, and chain-of-thought reasoning to guide responses. This Skill teaches model-specific prompt engineering techniques for Opus 4.6, Sonnet 4.6, and Haiku 4.5 to improve output quality and consistency.

Agentic AI workflows require patterns for building autonomous agents, managing state, and ensuring safety. This Skill provides prompting techniques and agentic workflow best practices to help you structure prompts for reliable autonomous behavior.

Optimizing API configuration for Claude models involves adjusting parameters based on whether you use Opus 4.6, Sonnet 4.6, or Haiku 4.5. This Skill offers per-model guidance on API configuration and prompt design to maximize efficiency.

Prompt engineering differs significantly between Claude Opus and Haiku due to varying capabilities and latency. This Skill delivers tailored advice for Opus 4.6, Sonnet 4.6, and Haiku 4.5, covering model-specific guidance for system prompts and structured input.

Claude returns inconsistent output when prompts lack clear structure or context, which few-shot examples can resolve. This Skill teaches you how to use few-shot examples and chain-of-thought reasoning to get consistent code generation and reliable results.

Chain-of-thought reasoning in AI prompting is needed for complex tasks requiring logical step-by-step deduction. This Skill covers when to apply chain-of-thought techniques alongside structured input and system prompt design for Claude's model family.