The Agent Skills Directory

[PROMPT_INJECTION]: The skill metadata contains deceptive information by claiming the author is "Angular Team @ Google". This contradicts the actual skill source and could mislead users into ascribing official status to the instructions provided.
[PROMPT_INJECTION]: The skill instructs the agent to load external configuration data into its active memory (context) without sanitization or boundary markers.
Ingestion points: The contents of the configuration file specified via the --ai-config flag are loaded into memory.
Boundary markers: None specified for the loaded configuration content.
Capability inventory: The skill has access to shell execution via npx ng for building, generating code, and adding dependencies.
Sanitization: No validation or escaping is applied to the content loaded from the configuration file.
[COMMAND_EXECUTION]: The skill executes multiple shell commands to check for environments and perform project scaffolding.
Evidence: Uses which ng, where ng, and gcm ng to detect the CLI, followed by npx ng new, npx ng build, and npx ng generate for application lifecycle management.
[EXTERNAL_DOWNLOADS]: The skill triggers the installation of external packages from the NPM registry.
Evidence: Facilitates installation of @angular/cli and tailwindcss using npm and npx.

angular-new-app