ql-link/linkrag-service/code-review-and-quality

Claude Code and agent skill by ql-link/linkrag-service

Trust tier 3
  • community
Source check pending

Checking that the SKILL.md file is still in the repository.

实现和测试完成后，提交或合并前执行质量门禁。

Install

npx vskill@latest install ql-link/linkrag-service/code-review-and-quality

SKILL.md

Code Review And Quality

必读

  1. AGENTS.md
  2. .specs/<需求名>/brief.md
  3. .specs/<需求名>/acceptance.feature
  4. .specs/<需求名>/technical_design.md
  5. .specs/<需求名>/implementation_report.md（若存在）
  6. 实际 git diff
  7. 测试结果

审查流程

步骤 1：先核对测试证据
  • 对照 acceptance.feature 中的 Scenario，确认每条都有对应测试且通过。
  • 若关键 Scenario 无测试覆盖，直接记为 Required 问题，不继续往下走。
步骤 2：六维审查
维度检查要点
Correctness是否满足所有 Scenario，异常路径是否可用
Tests是否覆盖主流程、异常、边界、幂等，回归是否通过
Architecture是否遵循 Maven 模块边界和组件复用约定
Security认证、权限、敏感信息、内部接口防护
Performance无界查询、N+1、同步阻塞、缓存误用
ContractsAPI、MySQL、MQ、Redis、OSS 文档是否已同步

问题分级

  • Critical：阻塞合并（安全漏洞、数据风险、核心功能错误）
  • Required：必须修复后再合并（需求偏差、关键测试缺失、明显架构违规）
  • Suggestion：可优化项，不阻塞当前交付

结论输出 APPROVE 或 REQUEST_CHANGES。

阶段门禁输出

审查结束必须输出状态块：

text
PHASE: 最终审核与提交/合并
AI_REVIEW: PASS | FAIL
HUMAN_REVIEW: APPROVED | PENDING
NEXT_PHASE: 提交/合并 | BLOCKED
BLOCK_REASON: <阻塞原因；无则写 NONE>

判定规则：

  • 存在 Critical 或 Required 未关闭 → AI_REVIEW=FAIL
  • 无阻塞问题且结论为 APPROVE → AI_REVIEW=PASS
  • 仅当 AI_REVIEW=PASS 且 HUMAN_REVIEW=APPROVED 才允许进入提交/合并

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewPassed

See the full security report

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

See evaluation results

Source

Popularity

Repository stars
5
Repository forks
1
7-day trend score
14

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/ql-link/linkrag-service/code-review-and-quality/badge)](https://verified-skill.com/skills/ql-link/linkrag-service/code-review-and-quality)

Something wrong with this skill or its page? Tell us.