The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill provides instructions for agents to analyze and modify external test files, which represents an indirect prompt injection surface. If an agent uses these conventions to review external code, malicious instructions within that code could potentially influence its behavior. Ingestion points: Test files (e.g., *.spec.ts, *.test.js) ingested for review or refactoring as described in the SKILL.md and evaluation tasks. Boundary markers: The instructions do not define specific delimiters or 'ignore' instructions for the code being processed. Capability inventory: The skill's evaluation tasks include file write operations and local command execution (npm test). Sanitization: No explicit sanitization or input validation is specified for the code being reviewed.
[COMMAND_EXECUTION]: The evaluation components of the skill utilize npm test to verify the success of refactoring tasks. This involves executing the node --test command in the local environment, which is standard for the development context of this skill.
[EXTERNAL_DOWNLOADS]: The documentation includes links to external educational resources and documentation from trusted sources such as Martin Fowler's website, Testing Library, Playwright, and Cucumber for reference purposes.

test-code-conventions