The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/lint_runner.py script executes ecosystem-standard linting tools to validate code quality.
Supported tools include npm, npx, ruff, mypy, and bandit.
Commands are executed using subprocess.run with argument lists, which is a secure pattern to prevent shell injection vulnerabilities.
[INDIRECT_PROMPT_INJECTION]: The skill processes project files which may contain untrusted content to generate metrics.
Ingestion points: scripts/type_coverage.py reads content from .ts, .tsx, and .py files using glob patterns within the target directory.
Boundary markers: Analysis results are printed directly to the console without explicit delimiters or instructions to ignore embedded content.
Capability inventory: The skill utilizes subprocess.run for tool execution and Path.read_text for file access.
Sanitization: File content is processed via regular expressions to calculate statistics (e.g., usage of 'any' types) and is not executed or directly interpreted as agent instructions.

lint-and-validate