The Agent Skills Directory

[SAFE]: The skill provides structured guidelines and LaTeX templates for mathematical derivations, proofs, and statistical analysis. All operations are confined to text generation based on user input.
[NO_CODE]: The skill consists entirely of Markdown files. There are no scripts, binaries, or configuration files that trigger code execution.
[INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided context ($1) to perform mathematical tasks. While this represents an attack surface for indirect prompt injection, the skill possesses no dangerous capabilities such as file system writes, network requests, or subprocess execution that could be leveraged for an attack.

math-reasoning