The Agent Skills Directory

[SAFE]: The skill's primary function is managing documentation (policy rules) via a structured interview and file-merge process. All operations are localized to the repository's documentation directory (<docs-dir>/review/policies/).
[COMMAND_EXECUTION]: The skill includes a Python script (scripts/validate_policy_rule.py) for validating YAML schema within markdown files. This script uses standard libraries (re, sys, pathlib) and performs safe string parsing and regex matching. It does not invoke subshells or execute arbitrary code.
[DYNAMIC_EXECUTION]: The script uses a simple YAML-like parser implemented via line-splitting and regex rather than potentially unsafe deserialization libraries (like full yaml.load()). This follows best practices for local data validation.
[DATA_EXPOSURE_AND_EXFILTRATION]: No network operations, hardcoded credentials, or access to sensitive system paths (e.g., .ssh, .aws, .env) were detected. The skill only interacts with documentation files specified in its instructions.

review-policy-rule-builder