The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes standard test runners including go test, pytest, jest, and vitest and shell utilities like grep to verify code fixes and audit test suite quality.\n- [EXTERNAL_DOWNLOADS]: Reference documentation suggests installing reputable testing utilities such as pytest-repeat and pytest-randomly from official package registries to aid in detecting non-deterministic test behavior.\n- [PROMPT_INJECTION]: The skill processes project files which could contain indirect prompt injection. Ingestion points: Test files and CLAUDE.md are read via file system tools. Boundary markers: No explicit delimiters or instructions are provided to the agent to disregard instructions within analyzed files. Capability inventory: Access to subprocess execution and file modification. Sanitization: No validation is performed on ingested code. This surface is inherent to code analysis tools.

testing-preferred-patterns