The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to run standard development commands such as npm init, npm install, and pip install to set up a project environment. These are expected behaviors for a project initialization tool.
[DATA_EXPOSURE]: The skill correctly implements security best practices by instructing the agent to create a .env.example with placeholders and specifically directs that the actual .env file containing secrets should be added to .gitignore to prevent accidental credential leakage.
[EXTERNAL_DOWNLOADS]: The skill references and downloads official packages from well-known and trusted registries, including npm (for @anthropic-ai/claude-agent-sdk) and PyPI (for claude-agent-sdk). It also uses standard documentation from docs.agents.com and console.anthropic.com.

new-sdk-app