The Agent Skills Directory

[SAFE]: The skill is designed for developing automation workflows on the Terse platform. It uses official platform tools including the terse CLI and the terse-sdk library. All external references, such as documentation links (e.g., https://docs.useterse.ai), point to the vendor's official infrastructure.
[COMMAND_EXECUTION]: The instructions direct the agent to perform standard development tasks using the terse CLI, such as terse init, terse generate, and terse deploy. These operations are consistent with the skill's stated purpose of building and managing SDK jobs.
[DATA_EXPOSURE]: The skill includes security-positive guidance for secret management, specifically advising the use of --fields-stdin instead of command-line arguments when connecting integrations with sensitive keys.
[SAFE]: The skill involves processing events from external sources (GitHub, Slack, etc.) which constitutes an indirect prompt injection surface. However, this is the primary functionality of the SDK, and the skill provides a structured framework for handling these events safely through deterministic steps and scoped agent skills.

create