The Agent Skills Directory

[SAFE]: The skill is entirely instruction-based and does not include any executable scripts, shell commands, or external dependencies.
[DATA_EXPOSURE]: The skill instructions include a directive to read ../../CLAUDE.md to retrieve 'scenario-level configuration' such as investment standards and strategic priorities. This is a localized file read for context and does not involve exfiltration or access to sensitive system paths like SSH keys or environment secrets.
[COMMAND_EXECUTION]: No shell commands or subprocess calls are present in the skill definition.

investment-evaluation