The Agent Skills Directory

[SAFE]: The skill is a well-structured editorial tool consisting of markdown instructions and a Python utility script. All identified behaviors align with the stated purpose of text humanization.
[COMMAND_EXECUTION]: The included script scripts/measure.py is a standalone tool for calculating linguistic metrics like Type-Token Ratio (TTR) and burstiness. It uses only standard Python libraries (math, re, statistics, collections) and does not perform network operations, file system modifications, or execute arbitrary subprocesses.
[EXTERNAL_DOWNLOADS]: The skill references several external resources for research and documentation purposes, including Wikipedia, GitHub repositories, and academic benchmarks. These are informational links and do not involve the automated download or execution of untrusted third-party code.
[PROMPT_INJECTION]: The instructions establish specific operating modes and personas for the agent to use when editing text. These instructions do not attempt to override system safety filters or bypass administrative constraints.
[DATA_EXFILTRATION]: No patterns of sensitive data access or external transmission were found. The skill does not request access to credentials, environment variables, or private files.

human-ai