Code Review

SkillSecurity

Review the current git diff for bugs, security issues, and clarity, then summarize findings by severity.

Then ask your AI: use the Code Review skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Account requirements not reviewed. Check the skill instructions before use; Ahel provides instructions and does not run this skill.

No other account needed.

Add it as a step in a pipeline you build on Ahel, or connect Ahel to Claude, ChatGPT, Cursor, Claude Code or Codex and ask your AI to use it.

What this skill tells your AI

The instructions your AI receives, as published by longngn204/local-coding-agent in skills/code-review/SKILL.md and read by Ahel’s review.

Use this when the user asks to review changes, a pull request, or "what did I break".

Scope the change with git diff --stat and then read the actual diff with git diff.
Prefer reviewing the diff over reading entire files. Use read_many only for files whose full context is needed.
Review in this order:
- Correctness: logic bugs, edge cases, null/undefined, async misuse, error handling.
- Security: injection, secrets, missing validation, unsafe file/command behavior.
- Maintainability: naming, dead code, duplication, missing tests.
Do not pad the review with speculative nits. If uncertain, say what evidence would confirm the issue.

Group findings by severity:

End with a short verdict: safe to merge, needs work, or blocked pending evidence.

Advanced