The Agent Skills Directory

[SAFE]: No malicious patterns or security vulnerabilities were identified in the skill definition. The skill focuses on documentation and discussion.
[PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass AI safety guardrails or override system prompts. The logic is purely instructional for task completion.
[DATA_EXFILTRATION]: No network activity or unauthorized access to sensitive local files (such as SSH keys or credentials) was found. The skill only writes to a local project directory (.turbo/spec.md).
[REMOTE_CODE_EXECUTION]: There are no remote downloads or execution of external scripts. The skill does not utilize any package managers.
[COMMAND_EXECUTION]: The skill does not use subprocesses or system commands. Its capability is limited to natural language interaction and generating a markdown file.

create-spec