The Agent Skills Directory

[SAFE]: The skill performs standard file management operations (reading and writing YAML/Markdown files) within a restricted plugin directory path (~/.claude/plugins/config/claude-for-legal-zh/).
[SAFE]: No network operations, external requests (curl, wget), or remote script execution patterns were detected.
[SAFE]: The workflow includes built-in safeguards, such as validating matter existence in _log.yaml before proceeding and implementing a role check from CLAUDE.md to ensure non-lawyers are warned of the legal implications of closing a case.
[SAFE]: The skill requires explicit user confirmation before writing final changes to the filesystem, providing an opportunity for human review of the generated content.
[SAFE]: No obfuscation, prompt injection, or persistence mechanisms were found in the instructions or metadata.

matter-close