The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data by scanning and reading the contents of files within the local repository to classify tests.
Ingestion points: The scripts/test-mix-inventory.py script uses Path('.').rglob('*') and path.read_text() to process all files in the repository.
Boundary markers: The skill does not employ explicit delimiters or instructions to ignore embedded prompts within the processed files.
Capability inventory: The skill leverages npm test and npx playwright test for runtime measurements.
Sanitization: No sanitization is performed on the file content before it is analyzed for heuristic patterns like test(, it(, or def test_.
[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands (npm test, npx playwright test) to measure test runtimes. While these are standard developer workflows, they involve executing code derived from the local environment and project configuration.

test-pyramid-balancer