The Agent Skills Directory

[SAFE]: The skill provides a standard interface to the DX (getdx.com) CLI tool. All commands and workflows, such as entity management and scorecard configuration via YAML, are consistent with the tool's primary purpose of engineering productivity management.
[PROMPT_INJECTION]: Potential surface for indirect prompt injection through catalog data ingestion.
Ingestion points: Data retrieved from the Software Catalog (entity names, descriptions, properties) via dx catalog entities info or list, and arbitrary SQL results from dx studio query.
Boundary markers: None explicitly defined in the skill instructions; the agent relies on its own instruction-following capabilities when processing retrieved data.
Capability inventory: The agent can perform shell commands via the dx CLI, including creating, updating, and deleting entities, managing scorecards, and performing authentication.
Sanitization: No specific sanitization of external catalog content is described before the data is presented to the agent's context.

dx-cli