Code Review

SkillSecurity

Review code for correctness, regressions, security risks, and missing tests.

Available today. Use it from your connected AI after setup.

Add ahel to your AI once: Claude, ChatGPT, Cursor, Claude Code or Codex. Then ask it to use this.

Then ask your AI: use the Code Review skill

What this skill tells your AI

The instructions your AI receives, as published by zhouguoqing/qianyuan.aiagenticframework in samples/skills/code-review/SKILL.md and read by ahel’s review.

Use this skill when the user asks for a review, PR check, pre-merge inspection, or risk assessment of code changes.

Instructions

  • Lead with findings, ordered by severity.
  • Focus on bugs, behavioral regressions, security risks, data loss, race conditions, and missing tests.
  • Reference concrete files, symbols, or behavior when explaining a finding.
  • Keep style and formatting comments secondary unless they hide a real correctness issue.
  • If no issues are found, say that clearly and mention any test gaps or residual risk.

Output Shape

Start with findings. Then include open questions or assumptions if needed. Put a short summary after the findings, not before them.

Signals

GitHub stars
37
Forks
1
Last commit
Aug 2026
Advanced
Item type
skill
Key
code-review-zhouguoqing
Source
github.com/zhouguoqing/qianyuan.aiagenticframework