Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Get Started Free →

Laolaoshiren/Zh Code Reviewer — measured AI agent skill | DecimalAI

laolaoshiren/zh-code-reviewer

NewSkillScoreMaintained

中文代码审查专家 - 生成详细的中文代码审查报告

Code Reviewby laolaoshiren

Links this skill to your agents and keeps it current with the author’s updates.

Automatic

Coding pack

1 · One-time — install the CLI (docs ↗)

pip install decimalai

2 · Get the skill — writes .claude/skills/laolaoshiren-zh-code-reviewer/SKILL.md

decimalai skills pull laolaoshiren-zh-code-reviewer --out .claude/skills/

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/laolaoshiren-zh-code-reviewer/SKILL.md https://app.decimal.ai/s/laolaoshiren-zh-code-reviewer/SKILL.md

Raw file: /s/laolaoshiren-zh-code-reviewer/SKILL.md ↗ · machine-readable summary at /s/laolaoshiren-zh-code-reviewer.json ↗

In productionGlobal

how this skill behaves on real traffic · last 30 days

No production data for this skill yet — usage numbers appear here once agents start running it.

Anonymized aggregate across every org using this skill — proof from real production use, not a demo.

Does this skill help? · Benchmark: with vs. withoutsign in to run this on your agents

23 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 2h ago

—-7% tokens0% turns57% of whole cases pass with skill (13/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-04	✗→✓	▲ Improved	7%	0%
case-13	✗→✓	▲ Improved	12%	0%
case-01	✓→✗	▼ Worse	6%	0%
case-03	✓→✗	▼ Worse	-52%	0%
case-07	✓→✗	▼ Worse	-85%	0%

Showing 5 of 23 cases

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

laolaoshiren / claude-code-skills-zh

skills/zh-code-reviewer/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1

Skill contents

SKILL.md

中文代码审查专家

触发条件

当用户要求审查代码、code review、代码检查、代码质量评估时激活此技能。

工作流程

读取目标文件 — 使用 Glob 和 Read 工具获取要审查的代码
分析代码质量 — 从以下维度评估：

代码规范（命名、格式、注释）
潜在 Bug（空指针、越界、并发问题）
性能问题（N+1 查询、内存泄漏、不必要的循环）
安全漏洞（SQL 注入、XSS、硬编码密钥）
设计模式（是否合理使用、是否有更好的方案）

生成审查报告 — 使用中文输出结构化报告

输出格式

## 📋 代码审查报告

### 📊 总体评分：X/10

### 🔴 严重问题（必须修复）
- [文件:行号] 问题描述
  💡 修复建议：...

### 🟡 建议改进（推荐修复）
- [文件:行号] 问题描述
  💡 改进建议：...

### 🟢 亮点
- 做得好的地方

### 📝 总结
一段总结性评价

注意事项

技术术语保留英文（如 null pointer、SQL injection）
代码示例保持原语言
对于中文变量名/注释，也要检查是否恰当

Want to see if laolaoshiren/zh-code-reviewer would activate on your phrasing? Try it before you install — no LLM call, no signup.

Other measured skills in the registry, with their headline benchmark lift.