The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses npx @cloudcannon/cli to automatically detect site settings, generate configuration baselines, and validate the resulting cloudcannon.config.yml. It also provides examples of using jq and node to query configuration schemas.
[EXTERNAL_DOWNLOADS]: Fetches JSON schemas from the vendor's official GitHub repository (github.com/cloudcannon/configuration-types). These schemas are used as the authoritative source for configuration keys to prevent agent hallucinations.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied project files (Markdown, JSON, YAML) to derive a CloudCannon configuration.
Ingestion points: Reads site source files, SSG-specific configuration files (e.g., astro.config.mjs), and content schemas.
Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are suggested for the agent to use when interpolating data into configuration files.
Capability inventory: Includes the ability to execute shell commands (npx, curl, jq) and write configuration files to the repository root.
Sanitization: The instructions do not explicitly detail sanitization or escaping of data extracted from source files before its inclusion in the configuration output or schema queries.

cloudcannon-configuration