메뉴
Use when the user wants a code review instead of implementation. Prioritizes correctness bugs, behavioral regressions, missing tests, and risky assumptions.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Use when evaluating whether a proposed change fits the existing architecture. Prevents layer violations, dependency cycles, and accidental coupling.
Use when reviewing documentation for accuracy, completeness, and alignment with source code. Catches doc-code drift before it confuses readers.
Use when making changes that should be committed. Enforces atomic commits, meaningful messages, and clean history.
Use when investigating slow execution, high memory usage, or excessive token consumption. Systematic measurement before optimization.
Use when improving code structure without changing behavior. Ensures each refactoring step preserves all existing tests.
Use when reviewing code for security vulnerabilities. Covers prompt injection, path traversal, command injection, and agent-specific attack vectors.
| name | code-review |
| description | Use when the user wants a code review instead of implementation. Prioritizes correctness bugs, behavioral regressions, missing tests, and risky assumptions. |
| version | 1.1.0 |
| author | Aixlarity (adapted from Hermes Agent requesting-code-review) |
| license | Apache-2.0 |
| metadata | {"aixlarity":{"tags":["code-review","quality","verification","pre-commit"],"related_skills":["tdd","systematic-debugging","security-audit"],"origin":"Hermes Agent requesting-code-review skill"}} |
No agent should verify its own work. A code review uses a fresh perspective to find what the author missed.
For each finding:
[SEVERITY] Description
File: path/to/file.rs:line
Why: explanation of the risk
Fix: suggested change (if obvious)
Severity levels: CRITICAL, WARNING, INFO.