The Agent Skills Directory

[SAFE]: No malicious patterns or security risks were detected in the skill's instructions or metadata.
[COMMAND_EXECUTION]: The skill instructs the agent to create, modify, and manage local files (component files and export files) as part of its core refactoring logic. These actions are limited to the local development environment and are consistent with the skill's primary purpose.
[PROMPT_INJECTION]: The instructions do not contain any attempts to bypass safety filters, override agent behavior, or extract sensitive system information. Phrases such as 'IMPORTANT:' are used appropriately for instructional clarity.
[DATA_EXPOSURE]: The skill reads from .temp.json and .temp.md files located in the workspace. These files are used as context for code generation and do not involve access to sensitive user credentials or system secrets.
[SAFE]: No network operations, external downloads, or third-party dependencies were found in the analyzed files.

implement-split