The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional text and design principles. No executable commands, network operations, or file system modifications are present.
[NO_CODE]: There are no scripts, configuration files, or command-line instructions included in this skill. It operates purely as a natural language instruction set for the agent.
[PROMPT_INJECTION]: The skill defines a potential ingestion surface for indirect prompt injection by asking the agent to process external context. 1. Ingestion points: The skill instructs the agent to read current deployment practices, SLA requirements, and team operational maturity from the environment. 2. Boundary markers: Absent; the skill does not provide delimiters or instructions to ignore embedded commands in the source data. 3. Capability inventory: None; the skill does not contain any scripts, tools, or shell access that could be leveraged to execute actions on the system. 4. Sanitization: None; there is no logic provided to filter or escape the ingested content.

deployment-topology