The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes shell commands such as git, gh, and bun to perform repository operations, handle pull request feedback, and execute validation scripts as part of its primary function.\n- [DYNAMIC_EXECUTION]: The skill instructions include the use of bun run to execute test suites (bun test) and evaluation drivers (bun run test:skill-eval-cell). This dynamic execution is scoped to the skill's primary purpose of repository maintenance and prompt quality assurance.\n- [INDIRECT_PROMPT_INJECTION]: As a tool for reviewing and authoring skills, it processes content from markdown and YAML files. It addresses the inherent risks of indirect prompt injection by enforcing a structured review process and outcome-oriented design principles.\n- [SAFE]: The skill promotes security best practices by explicitly prohibiting the use of dynamic context injection (the !command syntax) in its authoring standards, ensuring that skills do not execute unauthorized shell commands during initialization.

ce-skill-work