Prompt Engineering skills for AI agents
8 practitioner-grade prompt engineering skills, each a focused Markdown document your agent loads into context on demand. Search them from Claude Desktop, Cursor or any MCP client, or pull one with the CLI.
All 8 skills
- Chain of Thought
Chain-of-thought prompting to elicit step-by-step reasoning from language models
150 lines - Evaluation
Prompt evaluation and testing methodologies for measuring and improving prompt quality
324 lines - Few Shot Learning
Few-shot example prompting to guide model behavior through demonstration
172 lines - Prompt Chaining
Multi-step prompt chains that decompose complex tasks into sequential LLM calls
288 lines - Retrieval Augmented
RAG prompt patterns for grounding model responses in retrieved context documents
238 lines - Role Prompting
Role and persona prompting to shape model expertise, tone, and perspective
175 lines - Structured Output
Techniques for reliably extracting structured JSON and typed data from language models
236 lines - System Prompts
System prompt design for establishing persistent model behavior and constraints
198 lines