The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill directs the agent to read files throughout the project directory to resolve configuration and requirements, which can introduce untrusted instructions into the agent's context.
Ingestion points: The SKILL.md file instructs the agent to "read every applicable AGENTS.md from the repository root down" and to read pyproject.toml.
Boundary markers: No specific delimiters or "ignore" instructions are prescribed for processing the content of these external files.
Capability inventory: The skill enables the agent to execute shell commands via uv, pytest, ruff, and ty.
Sanitization: The instructions do not require sanitization or validation of the data ingested from the project files.
[COMMAND_EXECUTION]: The skill provides explicit shell command templates for the agent to use when managing dependencies, linting, and testing.
Evidence: references/dev-toolchain.md contains multiple command patterns for uv run pytest, uv run ruff, and uv run ty to be executed in the development environment.

ptlam-code-style-python