The Agent Skills Directory

[COMMAND_EXECUTION]: The skill includes scripts/test_skill.py, which uses subprocess.run() to execute the internal maintainability scanner and validation tools for regression testing during development.- [EXTERNAL_DOWNLOADS]: Reference documentation in references/source-notes.md and references/commenting.md includes links to official documentation and repositories from trusted organizations, including GitHub, Google, and the Python Software Foundation.- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as its primary function involves the agent ingesting and analyzing untrusted source code.\n
Ingestion points: Project source code files processed by the agent or the included analysis scripts as instructed in SKILL.md.\n
Boundary markers: Absent; the instructions do not specify delimiters to isolate ingested code from the agent's internal reasoning.\n
Capability inventory: The agent is empowered to refactor code, write to the filesystem, and execute local analysis tools.\n
Sanitization: The skill does not provide mechanisms for sanitizing or escaping the contents of the analyzed source code.

maintainable-code