The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides instructions for executing Vercel CLI commands, such as vercel, vercel link, and vercel env pull, to manage deployments, environment variables, and domains.
[DYNAMIC_EXECUTION]: The scripts/verify.sh script executes embedded JavaScript and Python snippets using Node.js or Python to perform linting and validation on local vercel.json files.
[EXTERNAL_DOWNLOADS]: The skill references Vercel's official JSON schema from https://openapi.vercel.sh/vercel.json for configuration validation and autocomplete in editors.
[INDIRECT_PROMPT_INJECTION]: The skill processes project-level configuration files (vercel.json and vercel.ts), which represent a potential attack surface if an attacker provides a malicious configuration file that the agent interprets.
Ingestion points: vercel.json and vercel.ts files within the project directory (referenced in SKILL.md and scripts/verify.sh).
Boundary markers: No specific delimiters or warnings for embedded instructions are provided in the skill instructions.
Capability inventory: The skill allows for local file reading/writing and execution of Vercel CLI commands.
Sanitization: No explicit sanitization of configuration content is performed beyond the provided linting script.

vercel