The Agent Skills Directory

[SAFE]: The skill requests access to standard file system tools (Read, Glob, Grep) to analyze the user's project and a specific configuration file (.claude/ship.local.md) for the purpose of providing relevant feedback.
[SAFE]: There are no network operations, data exfiltration patterns, or external downloads identified.
[SAFE]: The skill explicitly instructs the agent not to proceed with implementation or code generation, focusing solely on generating textual questions, which significantly reduces the risk of malicious execution or automated changes.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were detected.

ship-think