The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute the zsxq-cli binary to perform various operations including authentication, configuration checks, and API calls.
Evidence: Commands such as zsxq-cli auth login, zsxq-cli doctor, and zsxq-cli api call are documented in SKILL.md for interacting with the service.
[SAFE]: The skill incorporates security best practices by explicitly instructing the agent to protect authentication tokens and requiring user confirmation before performing write or delete operations.
Evidence: The 'Security Rules' section in SKILL.md prohibits plaintext output of tokens and mandates user intent confirmation for posts or comments.
[SAFE]: The authentication mechanism utilizes a standard OAuth 2.0 device authorization flow, and tokens are stored in the system Keychain rather than exposed in insecure configuration files.

zsxq-shared