The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use standard Command Line Interface (CLI) tools, specifically git and vercel. It mandates the use of vercel build and vercel deploy --prebuilt to ensure that deployment artifacts are generated locally rather than on remote hosted CI environments. These operations are essential to the skill's stated purpose of managing deployment workflows.
[INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes project files and conversation history to determine when to trigger its optimization logic.
Ingestion points: The agent reads repo documentation, the current conversation thread, and CI job logs to identify "process weight" (inefficiencies).
Boundary markers: The skill does not define specific delimiters for untrusted data processed during these checks.
Capability inventory: The skill possesses shell execution capabilities through the git and vercel tools.
Sanitization: While the skill does not explicitly sanitize data, it includes a safety protocol that blocks deployments if sensitive environment variables cannot be materialized safely on the local machine.

plimsoll