The Agent Skills Directory

[SAFE]: No security issues detected. The skill provides instructions for read-only analysis of documentation files (docs/roadmap/, docs/specs/, docs/adr/) to categorize roadmap status and dependencies.
[COMMAND_EXECUTION]: The skill instructs the agent to use standard local search tools (grep, find, ls) on the repository's documentation and code files. These operations are used purely for information gathering and specifically include exclusions for build and dependency directories.
[DATA_EXPOSURE_AND_EXFILTRATION]: Analysis confirms the skill does not access sensitive system paths (e.g., .ssh, .aws, .env) and lacks any network capabilities (no curl, wget, or API calls). It identifies roadmap-related files based on project IDs and technical specifications without interacting with secrets.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts or packages. All processing logic is performed locally using the agent's built-in file system tools.

brief-road