The Agent Skills Directory

[SAFE]: The skill's primary function is academic revision, governed by a priority system (C0-C7) that emphasizes semantic preservation and terminology identity. It specifically includes stop conditions to prevent requests involving detector evasion or policy circumvention.
[SAFE]: Included Python diagnostics (scripts/metrics.py and scripts/terminology_audit.py) are used for descriptive text analysis. These scripts rely on standard Python libraries and do not perform network operations, access sensitive credentials, or modify the host system outside of the intended local file processing.
[SAFE]: The skill implements robust data handling through 'locked spans' and 'semantic gates' which protect formulas, citations, and specific terminology from unintended modification. It includes regex-based masking to ignore non-prose content such as code blocks and mathematical equations during analysis.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected in the instructions or the accompanying scripts. The skill operates on user-authorized local files for scholarly editing purposes.

academic-humanizer