The Agent Skills Directory

[COMMAND_EXECUTION]: The skill makes extensive use of the gcx CLI and jq to interact with Grafana APIs, list resources, and perform dashboard operations. These are standard management tasks associated with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from live Grafana environments which could potentially contain malicious instructions if the source dashboards are compromised.
Ingestion points: Reads live dashboard configurations and resource manifests using gcx dashboards get and gcx resources get (SKILL.md, Step 2).
Boundary markers: None present. The instructions do not specify delimiters for the data extracted from JSON fields.
Capability inventory: The agent has the ability to write files, push resources to Grafana, and execute gcx commands (SKILL.md, Steps 5 and 6).
Sanitization: Relies on jq for structured extraction but does not explicitly validate the content within the extracted fields.
[DYNAMIC_EXECUTION]: The skill supports a code-generation workflow (gcx dev generate) for projects using resources-as-code patterns. This involves generating Go source code from templates, which is a standard feature of the developer toolset.

create-dashboard