The Agent Skills Directory

[SAFE]: The skill's instructions and metadata are entirely consistent with its stated purpose of document auditing. No malicious patterns or security vulnerabilities were identified during analysis.
[NO_CODE]: This skill contains no executable code, shell scripts, or binaries. It is a prompt-only skill that defines a persona and workflow for the AI agent.
[PROMPT_INJECTION]: There are no instructions designed to bypass system safety guidelines, override previous instructions, or extract system prompts.
[EXTERNAL_DOWNLOADS]: The skill does not reference external URLs, remote scripts, or third-party package repositories.

consistency-auditor