The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using the git utility and the vendor-specific entire CLI tool (entire search, entire explain, entire version).
[COMMAND_EXECUTION]: The skill includes explicit security instructions to sanitize user-supplied input before execution. It mandates shell-quoting the <topic> argument and stripping or escaping dangerous characters like backticks, subshells $(...), and semicolons to prevent command injection.
[EXTERNAL_DOWNLOADS]: The skill directs users to download the required CLI tool from the vendor's official documentation site at https://entire.io/docs/cli if it is not already present.
[PROMPT_INJECTION]: The skill implements defenses against indirect prompt injection by instructing the agent to treat all repository content, command output, and user-supplied strings as untrusted data and to never follow instructions found within them.

teach