The Agent Skills Directory

[SAFE]: The content is purely informational, providing guidance on prompt engineering patterns such as few-shot learning and chain-of-thought.
[NO_CODE]: There are no scripts or executable components associated with this skill. All examples are provided as static text for educational purposes.
[PROMPT_INJECTION]: No patterns attempting to override agent behavior or bypass safety filters were found. The skill explicitly advises treating input data as untrusted and delimiting user-supplied text.

prompt-engineering