Menú
Use when improving code structure without changing behavior. Ensures each refactoring step preserves all existing tests.
Instalar con Codex o Claude Copia este prompt, pégalo en Codex, Claude u otro asistente, y deja que revise la página de la skill y la instale por ti.
Basado en la clasificación ocupacional SOC
Use when evaluating whether a proposed change fits the existing architecture. Prevents layer violations, dependency cycles, and accidental coupling.
Use when the user wants a code review instead of implementation. Prioritizes correctness bugs, behavioral regressions, missing tests, and risky assumptions.
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 reviewing code for security vulnerabilities. Covers prompt injection, path traversal, command injection, and agent-specific attack vectors.
| name | refactoring |
| description | Use when improving code structure without changing behavior. Ensures each refactoring step preserves all existing tests. |
| version | 1.0.0 |
| author | Aixlarity |
| license | Apache-2.0 |
| metadata | {"aixlarity":{"tags":["refactoring","code-quality","maintainability"],"related_skills":["tdd","code-review","writing-plans"]}} |
Refactoring changes structure, not behavior. If any test breaks, you changed behavior. Stop and revert.
Each refactoring step follows this sequence:
Do NOT combine multiple refactoring steps in one commit.
tools.rs → tools/ directory.pub.