The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of the surrealkit CLI to manage database schemas, perform migrations, and run declarative tests, which requires access to the filesystem and database endpoints.
[EXTERNAL_DOWNLOADS]: The skill documents how to install the tool via cargo and docker, and describes the surrealkit init --from command which clones external Git repositories to scaffold projects. These downloads are directed towards vendor repositories or user-defined sources.
[INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted content from local project files, including SurrealQL source files, configuration TOMLs, and host application code for static analysis and testing purposes.
Ingestion points: Host code files (.ts, .svelte, .vue, .astro), schema files (.surql), and test suites (.toml) are read from the project directory by the check and test commands.
Boundary markers: There are no instructions for the agent to use specific delimiters or to ignore embedded instructions within the source files it analyzes.
Capability inventory: The surrealkit CLI can execute database queries, perform file system writes during initialization and type generation, and initiate HTTP requests for API testing.
Sanitization: The skill does not provide methods for sanitizing the contents of the files before they are processed by the CLI tool.

surrealkit