The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill references and fetches additional documentation and configuration guides from PlanetScale's official GitHub repository to provide up-to-date best practices.
[COMMAND_EXECUTION]: Provides detailed instructions and examples for using the pscale CLI to manage database infrastructure, including commands for authentication (pscale auth login), branch management (pscale branch create), and schema deployment. It also includes instructions for setting up service tokens for CI/CD environments.
[INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by teaching the agent to ingest and process untrusted external data, such as database query insights, schema linting results, and performance logs.
Ingestion points: Data enters the agent's context through tools like planetscale_get_insights, planetscale_get_branch_schema, and pscale api reports (documented in references/ps-insights.md and references/ps-cli-api-insights.md).
Boundary markers: The instructions do not define specific delimiters or "ignore" instructions for the data being processed.
Capability inventory: The skill documents capabilities to execute administrative shell commands (pscale branch delete) and SQL queries (pscale shell, planetscale_execute_read_query).
Sanitization: The skill mitigates risk by explicitly instructing the agent to confirm with a human before performing any destructive actions, such as dropping indexes, detaching partitions, or terminating database backends.

postgres