The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses shell commands to manage the development lifecycle of template repositories.
Evidence: Execution of git clone, npm install, and nx run-many to build and test code.
Verification: The run-all-templates.sh script executes npx create-nx-workspace to verify template integrity.
[DYNAMIC_EXECUTION]: The skill leverages dynamic code execution to perform migrations and scaffolding.
Evidence: Runs npx nx migrate --run-migrations which executes migration logic defined within the repositories.
Context: These operations are performed using the official Nx CLI and target the vendor's own verified repositories.
[INDIRECT_PROMPT_INJECTION]: The skill processes content from external repositories and user inputs, creating a surface for indirect instructions.
Ingestion points: Reads package.json from cloned repositories and accepts a target version string from user input.
Boundary markers: No explicit boundary markers are used when interpolating file content into commands, though operations are scoped to the tmp/cnw-templates directory.
Capability inventory: Includes full bash execution, file system write access, and authenticated network operations (GitHub PR creation).
Sanitization: The skill validates the target version using npm view nx@<version> version and checks repository availability via the GitHub API before processing.

update-cnw-templates