The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to utilize standard application commands such as /help, /skills, and /config to retrieve authoritative information about the environment.
[COMMAND_EXECUTION]: The skill mentions the use of codewhale-tui doctor for environment diagnostics. The instructions explicitly state this tool reports credential presence but never actual values, which is a standard security practice for diagnostic utilities.
[SAFE]: The skill implements strict boundary instructions, such as 'Do not guess', 'Do not answer from memory', and 'One surface per question', which are designed to reduce hallucinations and ensure the agent only provides verified information from the local environment.
[SAFE]: No remote code execution, external downloads, obfuscation, or data exfiltration patterns were detected. The skill's file access is scoped to the local docs/ directory within a Codewhale checkout.

help