The Agent Skills Directory

[NO_CODE]: The skill consists entirely of documentation and prompt templates in Markdown format. There are no executable scripts, binaries, or configuration files that could perform operations on the host system.
[SAFE]: The provided techniques (CO-STAR framework, Chain-of-Thought, Few-Shot learning) are standard architectural patterns for interacting with Large Language Models.
[SAFE]: References to prompt injection and instruction overriding are included as educational examples and defensive strategies to help developers build more secure applications.
[SAFE]: No credentials, sensitive file paths, or network operations were detected in the skill content.

prompt-engineering