The Agent Skills Directory

[SAFE]: The skill implements a structured characterization testing workflow using established industry tools including Vitest, Playwright, and Mock Service Worker (MSW).- [SAFE]: The skill includes security-conscious guidance for authentication testing, specifically recommending environment checks (e.g., process.env.NODE_ENV === 'production') to prevent test-only routes or bypasses from being active in production environments.- [INDIRECT_PROMPT_INJECTION]: The skill inherently processes untrusted user code to generate and run tests, which represents an indirect prompt injection attack surface. However, this is consistent with the primary purpose of a testing tool and is mitigated by the task-specific instructions.
Ingestion points: The skill reads target codebase files in Step 2: Establish The Baseline and Step 4: Add Tests One Vertical Slice At A Time.
Boundary markers: The skill does not explicitly define delimiters or specific 'ignore instructions' warnings when processing target code.
Capability inventory: The skill performs file writes (writing test scripts) and command execution (running test suites via vitest and playwright).
Sanitization: No specific input sanitization for the codebase content is described.

testing