The Agent Skills Directory

[SAFE]: The skill provides instructional guidance rather than executable code. It does not perform unauthorized network operations, file system modifications, or credential harvesting.
[SAFE]: The framework includes security-conscious steps such as identifying destructive constraints and requiring manual confirmation for high-risk operations like financial transactions or database migrations.
[SAFE]: The use of a discovery phase to establish a concrete 'contract' before execution helps prevent the agent from acting on ambiguous or potentially malicious user input.

goal