The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands like yarn format and nx run to automate code formatting and test execution. These operations are standard for development workflows and are used to verify the generated test files.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it reads and analyzes the content of external component files and existing test specifications.
Ingestion points: Reads the source code of the component provided in $ARGUMENTS and existing .spec.ts files.
Boundary markers: None are defined to isolate the content of the files from the agent's internal instructions.
Capability inventory: The skill can read local files and execute shell commands (yarn, nx).
Sanitization: No specific sanitization or filtering of the ingested file content is mentioned before the agent processes it for code generation.

create-test