The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the Bash, Grep, and Glob tools to explore the codebase. These tools are used for legitimate purposes, such as reading documentation, source code, and configuration files to answer the user's questions during the clarification process.
[DATA_EXPOSURE]: The instructions direct the agent to 'read any docs, code, or config' within the repository. While this is expected behavior for a repository assistant, users should ensure that sensitive secrets or credentials are not stored in plain text within the files being scanned.
[PROMPT_INJECTION]: The skill provides structured instructions for refining user requirements. It does not contain any patterns designed to bypass agent safety filters, override system instructions, or extract system prompts.

clarify