The Agent Skills Directory

[SAFE]: The skill implements a structured software development workflow focused on modernization and testing using standard Python ecosystem tools and libraries.\n- [COMMAND_EXECUTION]: The skill executes shell commands via uv run to invoke standard development utilities such as pytest, ruff, and mypy. These operations are performed on project files to ensure code quality and correctness, which is the primary purpose of the skill.\n- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes external project artifacts (plans, definitions, and tests) to guide its implementation phase.\n
Ingestion points: Modernization plans, interface definitions, and failing test files loaded in Step 1 of SKILL.md.\n
Boundary markers: Absent; artifacts are loaded into the agent's context without specific delimiters or isolation instructions.\n
Capability inventory: The agent has the ability to execute shell commands and modify file system contents.\n
Sanitization: Absent; the agent is expected to act directly on the contents of the ingested project files.

snakepolish