The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to perform local environment discovery using commands like ghq list and by reading configuration files (e.g., package.json, Makefile, mise.toml) to ensure the generated prompt contains accurate repository paths and build instructions.
[COMMAND_EXECUTION]: Includes functionality to copy the final generated prompt to the system clipboard using the pbcopy utility or to save it to a local file for the user's convenience.
[PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface by ingesting untrusted data from the local repository (such as error logs, specifications, or source code) into the generated prompt. This risk is mitigated by explicit instructions for the agent to present the final prompt in a code block for user review before it is used in a new session.

fable-prompt