The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses standard shell commands including mkdir, ln, test, and readlink to create and verify directory structures and symlinks. These operations are limited to the skill's intended purpose of bootstrapping new modules.
[EXTERNAL_DOWNLOADS]: The skill uses WebFetch to retrieve schema and naming conventions from https://agentskills.io. This is an informational fetch used to ensure the generated skill follows the latest standards.
[DATA_EXFILTRATION]: No sensitive file access or unauthorized network transmissions were detected. File operations are restricted to .agents/skills and .claude/skills within the project or home directory, which is consistent with the skill's stated functionality.
[PROMPT_INJECTION]: The instructions do not contain attempts to override safety filters, extract system prompts, or bypass agent constraints. It includes validation steps to ensure user input (skill names) follows a safe format (kebab-case).

create-skill