The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to install dependencies, start a local development server, and run Playwright test suites within SKILL.md.
[EXTERNAL_DOWNLOADS]: The skill downloads the @playwright/test package and Chromium browser binaries from official registries as part of the setup process in SKILL.md. These are industry-standard development resources.
[INDIRECT_PROMPT_INJECTION]: The skill processes terminal output and log files from the application being tested, which creates a surface where the agent could ingest instructions embedded in external output.
Ingestion points: Terminal output from Playwright tests and application logs stored in /tmp/dev.log mentioned in SKILL.md.
Boundary markers: No specific delimiters or safety instructions are provided to separate tool output from instructions.
Capability inventory: The skill has access to the Bash and Write tools as defined in the frontmatter of SKILL.md.
Sanitization: No filtering or sanitization steps are defined for the ingested log content.

browser-test-loop