The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the execution of code and tests that may originate from untrusted sources, creating a surface for indirect prompt injection attacks.
Ingestion points: Processes Python source code and test files within the local project environment (e.g., tests/test_<module>.py).
Boundary markers: No explicit boundary markers or instructions to ignore instructions embedded in the code under test are provided.
Capability inventory: The skill utilizes command execution via uv run pytest to execute the project's test suite.
Sanitization: No sanitization or validation of the code or test logic is performed prior to execution.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the uv tool for project setup (uv init), dependency management (uv add), and test execution (uv run pytest). These are standard development operations but grant the agent the ability to execute code in the local environment.
[EXTERNAL_DOWNLOADS]: The skill references external resources and community best practices for TDD and uv.
Evidence: Links to documentation repositories on GitHub including github.com/mattpocock/skills, github.com/nizos/tdd-guard, and github.com/s2005/uv-skill.

python-tdd-with-uv