The Agent Skills Directory

[SAFE]: No malicious patterns or behaviors were identified in the skill. All operations are aligned with the stated goal of analyzing and improving code performance.\n- [COMMAND_EXECUTION]: The skill interacts with the local shell to perform Git operations (checking, creating, and switching branches) and to run existing test suites. These actions are transparently documented as part of the optimization workflow.\n- [DATA_EXFILTRATION]: While the skill reads local files and directories for analysis, there are no network operations or indicators that data is being sent to external servers.\n- [PROMPT_INJECTION]: The skill's instructions do not contain any attempts to bypass safety filters or override system prompts.

code-optimizer