The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the lark-cli binary to interact with the Lark Task API. All shell commands are scoped to specific task management actions such as creating, searching, updating, and commenting on tasks.
[SAFE]: The skill is provided by the official vendor (larksuite) and interacts with official API resources. It includes robust safety instructions for the agent, such as requiring user confirmation for every write operation (creation, deletion, updates) and enforcing strict constraints on file uploads (relative paths only, 50MB limit). The use of lark-cli auth status to retrieve user identity is a standard and safe practice for this toolset.

lark-task