Ready to supercharge your AI agents?

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

Get Started Free →

Code Review — measured AI agent skill | DecimalAI

jackyst0/code-review

NewSkillScoreMaintained

Smart code review skill that helps review code quality, identify potential issues, and provide improvement suggestions.

Code Reviewby jackyst0

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/jackyst0-code-review/SKILL.md

decimalai skills pull jackyst0-code-review --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/jackyst0-code-review/SKILL.md https://app.decimal.ai/s/jackyst0-code-review/SKILL.md

Raw file: /s/jackyst0-code-review/SKILL.md ↗ · machine-readable summary at /s/jackyst0-code-review.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 6h ago

Yes — +78% lift+11% tokens0% turns96% of whole cases pass with skill (22/23)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-02	✗→✓	▲ Improved	1%	0%
case-03	✗→✓	▲ Improved	-13%	0%
case-04	✗→✓	▲ Improved	-13%	0%
case-05	✗→✓	▲ Improved	-5%	0%
case-06	✗→✓	▲ Improved	10%	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

jackyst0 / awesome-agent-skills

examples/code-review/SKILL.md

View on GitHub ↗

License CC0-1.0Imported 8/3/2026Version v1

Skill contents

SKILL.md

Code Review

> 智能代码审查技能，帮助审查代码质量、发现潜在问题、提供改进建议。 > > Smart code review skill that helps review code quality, identify potential issues, and provide improvement suggestions.

When to Use

当用户请求以下操作时使用此 skill：

审查代码 / Review code
检查代码质量 / Check code quality
寻找代码中的问题 / Find issues in code
请求代码改进建议 / Request improvement suggestions

Instructions

审查步骤 / Review Steps

阅读代码 - 仔细阅读提供的代码
检查问题：

语法错误 / Syntax errors
逻辑问题 / Logic issues
安全隐患 / Security vulnerabilities
性能问题 / Performance issues
代码风格 / Code style

提供建议 - 给出具体的改进建议
输出报告 - 使用标准格式生成审查报告

输出格式 / Output Format

markdown
## 代码审查报告 / Code Review Report

### 概述 / Summary
[简要总结 / Brief summary]

### 发现的问题 / Issues Found
- [ ] 问题 1 / Issue 1
- [ ] 问题 2 / Issue 2

### 改进建议 / Suggestions
1. 建议 1 / Suggestion 1
2. 建议 2 / Suggestion 2

### 评分 / Score
- 代码质量 / Code Quality: X/10
- 可读性 / Readability: X/10
- 可维护性 / Maintainability: X/10

Examples

输入 / Input

python
def calc(x,y):
    return x+y

输出 / Output

代码审查报告

概述

简单的加法函数，存在命名和格式问题。

发现的问题

] 函数名 calc 不具描述性
] 缺少类型提示
] 缺少文档字符串
] 运算符周围缺少空格

改进建议

将函数重命名为 add_numbers
添加类型提示：def add_numbers(x: int, y: int) -> int:
添加 docstring 说明函数用途
遵循 PEP 8 格式规范

评分

代码质量: 6/10
可读性: 7/10
可维护性: 5/10

Want to see if jackyst0/code-review 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.