Ready to supercharge your AI agents?

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

Get Started Free →

Tencentblueking/代码评审专家 — measured AI agent skill | DecimalAI

tencentblueking/代码评审专家

NewSkillScoreMaintained

基于 Google Code Review 指南的代码评审技能

Code Reviewby tencentblueking

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/tencentblueking-54a295/SKILL.md

decimalai skills pull tencentblueking-54a295 --out .claude/skills/

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

curl -fsSL --create-dirs -o .claude/skills/tencentblueking-54a295/SKILL.md https://app.decimal.ai/s/tencentblueking-54a295/SKILL.md

Raw file: /s/tencentblueking-54a295/SKILL.md ↗ · machine-readable summary at /s/tencentblueking-54a295.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

22 test cases from the publisher’s eval.yaml · each run twice on gemini-3.6-flash — with the skill injected, then without · last run 3h ago

Yes — +36% lift-13% tokens0% turns86% of whole cases pass with skill (19/22)

Test case	Without → With	Effect	Δ tokens	Δ turns
case-11	✗→✓	▲ Improved	-35%	0%
case-02	✗→✓	▲ Improved	27%	0%
case-06	✗→✓	▲ Improved	-4%	0%
case-10	✗→✓	▲ Improved	-60%	0%
case-17	✗→✓	▲ Improved	-55%	0%

Showing 5 of 22 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

tencentblueking / bk-bcs

bcs-services/bcs-project-manager/.cursor/skills/code-review/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/3/2026Version v1

Skill contents

SKILL.md

代码评审专家

⚠️ 核心规则

追求持续改进，而非完美 - 倾向于批准能提升代码健康状态的变更
对事不对人 - 有建设性的反馈，保持礼貌尊重
解释为什么 - 帮助开发者理解原因

快速开始

bash
/code-review              # 智能评审（自动检测变更范围）
/code-review staged       # 评审暂存区（提交前检查）
/code-review last-commit  # 评审最近一次提交

> 默认按优先级检测：暂存区 → 工作区 → 最近提交

问题分级

| 前缀 | 含义 | 处理 | |------|------|------| | [必须] | 严重问题 | 阻止合入 | | [建议] | 改进建议 | 讨论后决定 | | [Nit] | 小问题 | 可忽略 |

检查维度

| 维度 | 核心检查项 | |------|-----------| | 设计 | 代码归属、系统集成、无过度工程 | | 功能 | 行为符合预期、边缘情况已处理 | | 复杂度 | 代码可简化、易于理解 | | 测试 | 有自动化测试、测试设计良好 | | 安全 | 无 XSS、输入校验、敏感数据安全 | | 性能 | 无内存泄漏、大列表虚拟滚动 |

📦 按需加载资源

| 资源 | URI | |-----|-----| | 完整检查清单 | skill://code-review/references/checklist.md | | Git 场景指南 | skill://code-review/references/git-scenarios.md | | 常见错误规则 | skill://code-review/references/scoring-standard.md |

📦 可用资源

skill://code-review/references/checklist.md
skill://code-review/references/git-scenarios.md
skill://code-review/references/report-examples.md
skill://code-review/references/report-format.md
skill://code-review/references/scoring-standard.md
skill://code-review/references/writing-guidelines.md
skill://code-review/assets/pre-commit-review.sh

> 根据 SKILL.md 中的 IF-THEN 规则判断是否需要加载

Want to see if tencentblueking/代码评审专家 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.