The Agent Skills Directory

[SAFE]: The skill is designed for documentation management and project synchronization within a local repository environment. It defines clear boundaries and focuses on maintaining metadata, tags, and artifacts.
[COMMAND_EXECUTION]: The skill utilizes standard shell commands such as bash, ls, grep, and wc, along with project-specific npm scripts like npm run build and npm run sync:skills to perform administrative tasks. These operations are logically restricted to the local filesystem and project directory structure (.claude/skills/, website/).
[EXTERNAL_DOWNLOADS]: No unauthorized external downloads or remote script executions were identified. The tool operates on local files and uses established project build processes.
[DATA_EXFILTRATION]: There is no evidence of data exfiltration. The skill processes documentation metadata and does not access sensitive system paths (such as ~/.ssh or ~/.aws) or hardcode any credentials.
[PROMPT_INJECTION]: The instructions do not contain any patterns typical of prompt injection, safety bypasses, or behavior overrides. It uses instructional language solely for process enforcement and formatting standards.

skill-documentarian