The Agent Skills Directory

[DYNAMIC_EXECUTION]: The utility script scripts/python-order.mts embeds a Python script as a hardcoded string template which is then executed using the python3 -c command at runtime. This execution is used for static analysis of Python source code and uses the -I flag to isolate the execution environment from user-defined environment variables and local paths.
[COMMAND_EXECUTION]: The script scripts/python-order.mts invokes the system Python interpreter via spawnSync to execute its bundled analysis logic. This represents a controlled execution of shell commands intended for linting and code quality checks.
[INDIRECT_PROMPT_INJECTION]: The skill is intended to review and process project source code to apply readability and layout standards. Since the code being analyzed is untrusted external data, there is a potential risk that malicious instructions embedded in the code could influence the agent's behavior during the review process.
Ingestion points: Project source code files (Python, TypeScript, Go, Rust) processed by the agent in accordance with SKILL.md instructions.
Boundary markers: No specific delimiters or safety instructions are defined in the skill to isolate code content from agent instructions.
Capability inventory: The agent has the capability to execute the bundled python-order.mts script and perform standard file system operations.
Sanitization: The skill does not define procedures for sanitizing or escaping code content before it is processed by the AI model.

code-standards