The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill analyzes project source code and a specific pattern cache file to generate tests. This creates a surface where malicious instructions embedded in the codebase could potentially influence the agent's behavior during the test creation process.
Ingestion points: Project source code files (read via Read, Grep, and Glob tools) and the configuration file at .claude/cache/test-patterns.json.
Boundary markers: No specific delimiters or instructions to ignore embedded commands within the analyzed code are explicitly mentioned in the instructions.
Capability inventory: The agent has access to Bash (for executing tests), and Write/Edit (for creating test files).
Sanitization: There is no mention of sanitization or filtering of the content read from the project files before it is processed by the agent.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute standard test runners and coverage tools, such as npm test, pytest, phpunit, go test, and detox. These commands are used to verify the generated tests and check code coverage targets.

test-writer