The Agent Skills Directory

[DATA_EXPOSURE]: The skill manages and retrieves configuration data, including API keys, from the local file ~/.claude/.env. This is a standard and recommended practice for secret management in the platform's development environment.
[COMMAND_EXECUTION]: The skill uses local shell commands for administrative tasks such as appending entries to a local execution log (~/.claude/LIFEOS/MEMORY/SKILLS/execution.jsonl), sending notifications to a local service via curl, and setting executable permissions on generated files using chmod +x.
[INDIRECT_PROMPT_INJECTION]: The skill translates user-provided requirements into functional code, which creates a potential surface for indirect prompt injection. However, the templates are structured to follow strict architectural principles to mitigate the risk of accidental execution of embedded instructions.
[EXTERNAL_DOWNLOADS]: The skill facilitates the installation of established libraries like commander from the official NPM registry using bun add when upgrading tool complexity.

CreateCLI