Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add laolaoshiren/claude-code-skills-zh --skill refactor-advisorgit clone --depth 1 https://github.com/laolaoshiren/claude-code-skills-zhWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/laolaoshiren/claude-code-skills-zh/refactor-advisor)<a href="https://agentmods.dev/skills/laolaoshiren/claude-code-skills-zh/refactor-advisor"><img src="https://agentmods.dev/badge/skills/laolaoshiren/claude-code-skills-zh/refactor-advisor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/laolaoshiren/claude-code-skills-zh/refactor-advisor"><img src="https://agentmods.dev/badge/skills/laolaoshiren/claude-code-skills-zh/refactor-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.01046 |
| Opus 5.5 | $0.00009 | $0.00418 |
| Sonnet 5.5 | $0.00004 | $0.00209 |
| Haiku 4.5 | $0.00002 | $0.00105 |
Grade A, and why
refactor-advisor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
代码重构顾问
触发条件
当用户要求重构代码、优化代码结构、改善代码质量、消除技术债务时激活此技能。
工作流程
第 1 步：扫描代码库
- 使用
grep/rg扫描目标目录，识别潜在坏味道 - 统计文件行数、函数长度、参数数量等指标
- 查找重复代码块（相似度 > 80%）
第 2 步：分类坏味道
按严重程度分类发现的问题：
| 等级 | 含义 | 说明 |
|---|---|---|
| 🔴 严重 | 必须立即修复 | 影响可维护性和稳定性 |
| 🟡 中等 | 建议尽快修复 | 降低代码可读性 |
| 🟢 轻微 | 可择机优化 | 不影响功能但有改进空间 |
第 3 步：优先级排序
按以下维度综合排序：
- 影响范围 — 被引用/调用次数越多，优先级越高
- 变更频率 — git log 频繁改动的文件优先
- 修复成本 — 成本低且收益高的优先处理
第 4 步：输出重构方案
常见坏味道检测
| 坏味道 | 特征 | 重构手法 | 等级 |
|---|---|---|---|
| 长方法 | 函数超过 50 行 | 提取方法 (Extract Method) | 🔴 |
| 大类 | 类超过 300 行 | 提取类 (Extract Class) | 🔴 |
| 重复代码 | 相似代码块出现 3+ 次 | 提取公共方法 | 🔴 |
| 过长参数 | 函数参数超过 4 个 | 引入参数对象 | 🟡 |
| 嵌套过深 | if/for 嵌套 3+ 层 | 卫语句 (Guard Clause) | 🟡 |
| 魔法数字 | 硬编码的数字 | 提取为常量 | 🟢 |
| 过长链式调用 | a.b.c.d.e | 提取中间变量 | 🟢 |
| 全局可变状态 | 全局变量被多处修改 | 封装为模块/引入依赖注入 | 🔴 |
| 过度耦合 | 模块间相互依赖 | 依赖反转、引入接口 | 🟡 |
输出格式
完整报告模板
# 代码重构报告
## 概要
- 扫描文件数：XXX
- 发现问题数：XX（🔴 X / 🟡 X / 🟢 X）
- 预估工作量：X 天
## 问题列表
### 问题 1：[问题标题]
- **📍 位置**：`src/services/user.ts:45-120`
- **🔍 问题**：该函数长达 75 行，包含 3 层嵌套，职责不单一
- **🛠️ 重构方案**：
- 提取 `validateUserData()` 方法
- 提取 `saveToDatabase()` 方法
- 使用卫语句替代嵌套 if
- **⚠️ 风险评估**：
- 该函数被 12 处调用，需全面回归测试
- 建议先添加单元测试再重构
- **Before**：
```typescript
function processUser(data) { /* 75行... */ }
- After：
function processUser(data) { const validated = validateUserData(data); return saveToDatabase(validated); }
重构路线图
| 阶段 | 内容 | 优先级 | 预估 |
|---|---|---|---|
| P1 | 修复 🔴 严重问题 | 高 | 2天 |
| P2 | 处理 🟡 中等问题 | 中 | 3天 |
| P3 | 优化 🟢 轻微问题 | 低 | 1天 |
## 注意事项
- 重构前确保有足够的测试覆盖
- 每次重构尽量小步提交，便于回滚
- 重构不应改变外部行为（行为保持）
- 大规模重构建议分阶段进行，每阶段独立可验证
- 关注重构过程中的性能回退风险
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 99 lines · 22 tokens per session scan A 79e57f70f0bf
refactor-advisor is a skill published in the GitHub repository laolaoshiren/claude-code-skills-zh (893 stars, last pushed yesterday), licensed MIT. It adds 22 tokens to every session and 1,046 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
design-smell-review
Lightweight design smell review for modules and APIs—coupling, cohesion, naming, boundaries, and unnecessary complexity. Use before large refactors or when code feels hard to change. Complements gstack/review (diff-focused).
github-comment-triage
Triage and address GitHub PR review comments systematically—classify, respond, fix or defer with rationale. Use when a PR has review feedback, requested changes, or unresolved threads.
code-simplification
Simplify working code while preserving behavior—remove dead paths, flatten nesting, clarify names, reduce duplication. Use after features work but code feels over-engineered.
doubt-driven-review
Adversarial fresh-context review for non-trivial decisions before they stand. Use for production-impacting logic, security-sensitive changes, unfamiliar code, or high-blast-radius architecture choices.
swing-review
An adversarial review guide for deliberately looking for hidden flaws in code, system designs, pull requests, and important decisions. A pull request is a proposed code change awaiting review.
ai-engineering-toolkit
6 production-ready AI engineering workflows: prompt evaluation (8-dimension scoring), context budget planning, RAG pipeline design, agent security audit (65-point checklist), eval harness building, and product sense coaching.