The Agent Skills Directory

COMMAND_EXECUTION (LOW): The skill executes multiple shell commands including nx generate, nx test, nx build, and nx lint. While standard for development, these commands execute code defined in generators (local or external) and project scripts.
EXTERNAL_DOWNLOADS (LOW): Uses npx and nx commands, which may trigger the download and installation of packages or plugins from the npm registry if they are not already cached locally.
DYNAMIC_EXECUTION (LOW): Employs node -e to dynamically resolve file paths for generator configurations. This is a common development pattern but involves runtime execution of a generated string.
INDIRECT_PROMPT_INJECTION (LOW): Processes user-provided input for generator names and configuration options.
Ingestion points: User instructions for creating or modifying code via nx-generate.
Boundary markers: Absent. The skill relies on natural language context.
Capability inventory: Full command execution via shell for project generation, testing, and building (SKILL.md).
Sanitization: The skill includes a mandatory 'Pre-Execution Checklist' that requires the agent to 'Read Generator Source Code' and 'Fetch Generator Schema' before running any commands, serving as a human-in-the-loop or agent-audit safety mechanism.

nx-generate