from dgk-claude16
Run an automated, background code review using a Z.AI (GLM) model to surface security issues, style problems, and PR diffs for staged or uncommitted changes.
This skill runs a GLM-based code review (default: glm-4.7-flash) on the current session's changes. It can review staged changes, uncommitted diffs, or PR diffs, producing prioritized findings and suggested fixes. The recommended execution calls the glm-review CLI in background mode so reviews run asynchronously and results can be validated and acted on afterward.
Use this skill after making code changes when you want an automated review before committing or merging: for security checks, stylistic suggestions, PR diff reviews, or a focused audit (e.g., "보안 집중"). It is especially useful in multi-agent or CI-assisted workflows where diffs must be collected reliably.
glm-review CLI)--diff-file, --mode pr|staged), and the required background flags (run_in_background=true, dangerouslyDisableSandbox=true).Agents that can call shell/CLI tools (Claude Code, Cursor, Codex-style agents) can use this skill. It is intended for environments that support running glm-review and background execution.
This skill has not been reviewed by our automated audit pipeline yet.
