The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local repository scripts and validation tests using the uv tool. Evidence: Executes uv run python src/nemotron/steps/index.py and uv run pytest tests/steps -q (SKILL.md).
[PROMPT_INJECTION]: The skill processes user-supplied data to generate documentation files, creating a surface for indirect prompt injection if those files are later parsed by an agent. Ingestion points: User-provided responses regarding pattern details, triggers, and content (SKILL.md). Boundary markers: Absent; there are no specific instructions to wrap or delimit user-provided content in the generated files. Capability inventory: The skill has the ability to write files to the repository and execute shell commands (SKILL.md). Sanitization: Absent; the skill does not specify any sanitization or validation for the content provided by the contributor.

nemotron-add-pattern