prompt-engineering-patterns
Advanced prompt patterns: chain-of-thought, few-shot, structured templates for production LLMs.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for prompt-engineering-patterns, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
An Agent Skill that loads advanced prompt-engineering techniques when the agent optimizes or designs prompts. It covers chain-of-thought, tree-of-thought, dynamic few-shot selection, and reusable templates with variable interpolation. The skill injects patterns to improve LLM reliability and controllability.
Key features and capabilities
- Chain/tree-of-thought reasoning patterns
- Dynamic few-shot example selection
- Reusable prompt templates with interpolation
Use cases
- Optimizing production prompts
- Designing structured prompt templates