The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands including npx playwright test, jq, find, and unzip to interact with the testing framework and report files. These commands are essential for generating and parsing the diagnostic data required for debugging.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface as it ingests untrusted data from test outputs, such as JSON reports and HTML snapshots, which could be influenced by the application under test. * Ingestion points: playwright-report/results.json, trace.trace, and snapshot.html. * Boundary markers: None. * Capability inventory: Shell command execution and file reading. * Sanitization: No sanitization is performed on test output before it is processed by the agent.

playwright-debugger