The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and act upon repository content, such as Playwright test specifications and fixtures, which serves as an ingestion point for untrusted data.
Ingestion points: The agent reads and processes files within the repository (e.g., e2e/specs/skeleton/customerAccount.spec.ts) to perform reviews or debugging.
Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard embedded instructions within the code being analyzed.
Capability inventory: The skill utilizes shell commands (pnpm exec), environment variable configuration, and local script execution.
Sanitization: No sanitization or filtering of the ingested code content is specified.
[COMMAND_EXECUTION]: The skill provides instructions for executing various shell commands and scripts related to testing and vendor authentication.
Evidence: Shell commands including pnpm exec shopify auth login, pnpm exec shopify hydrogen link, and pnpm exec playwright test are used for project operations.
Evidence: The skill references the execution of a repository-local script: ./scripts/setup-ejson-private-key.sh.

playwright-tests