The Agent Skills Directory

[SAFE]: No security vulnerabilities were detected across any threat categories. The skill is instructional in nature and uses standard markdown for process documentation.
[PROMPT_INJECTION]: The skill contains no instructions designed to bypass safety filters, override agent behavior, or extract system prompts.
[DATA_EXFILTRATION]: There is no evidence of sensitive data access or network exfiltration patterns. No hardcoded credentials or sensitive file paths are present.
[REMOTE_CODE_EXECUTION]: The skill does not download, reference, or execute any external scripts, binaries, or unverified packages.
[COMMAND_EXECUTION]: No shell commands, privilege escalation attempts, or system-level operations are included in the instructions or templates.
[NO_CODE]: The skill consists entirely of Markdown files (SKILL.md and a reference guide) and contains no executable scripts in Python, Node.js, or other languages.

documentation-strategy