The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and code examples designed to guide an AI agent's behavior during coding tasks. It does not include any executable scripts, network operations, or tool invocations. The provided Python code snippets in the examples are for illustrative purposes and do not represent active attack vectors. The guidelines emphasize caution, surgical changes, and explicit verification, which are generally positive for the reliability and safety of agent-generated code.

karpathy