The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires the agent to execute a bundled shell script to detect environment variables and run generated tests locally.
Evidence: Instructions in SKILL.md state: Run scripts/detect_test_setup.sh from the project root.
Evidence: Instructions in SKILL.md state: Run the new tests — they must pass.
Evidence: scripts/detect_test_setup.sh uses node -e to dynamically parse package.json for test scripts.
[INDIRECT_PROMPT_INJECTION]: The skill's workflow depends on reading potentially untrusted code and test files from the user's project, which could contain adversarial instructions.
Ingestion points: SKILL.md instructs the agent to open and read existing target code and test files near the code under test.
Boundary markers: The skill does not define specific delimiters or "ignore instructions" warnings for the data it processes.
Capability inventory: The skill has file system access (read/write) and shell command execution capabilities.
Sanitization: No explicit sanitization or content validation is applied to project files before they are processed by the AI model.

test-writer