code-review

- Determine scope — identify what to review:

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "code-review" with this command: npx skills add woowooyong/curl-ticket/woowooyong-curl-ticket-code-review

Code Review

Process

  • Determine scope — identify what to review:

  • PR number given → gh pr diff <number>

  • "my changes" / no target specified → git diff HEAD (unstaged + staged)

  • Specific files mentioned → read those files directly

  • Read each changed file fully before reviewing

  • Load references/checklist.md and apply sections matching the changed file paths:

Path pattern Checklist sections

server/api/**

API Route, Security, Error Handling

app/components/** , app/pages/**

Vue Component, Security

server/database/schema/**

Database & Schema

shared/schemas/** , shared/constants.ts

Validation & Types

app/composables/**

Vue Component (data fetching), Performance

server/utils/** , server/middleware/**

API Route (auth), Security, Error Handling

  • Always apply Security Review regardless of file type

  • Report findings using the output format below

Instant Red Flags

Flag these on sight — the most frequent mistakes in this codebase:

  • server/api/projects/[projectId]/** route missing getAccessibleProject() call

  • Raw string where a shared constant exists ('Open' instead of IssueStatus.Open )

  • v-html with user-controlled content

Output Format

Code Review: [brief description]

Summary

[1-2 sentence overview and assessment]

Findings

🔴 Critical

  • [file:line]: [description and fix]

🟡 Suggestions

  • [file:line]: [description and suggestion]

🟢 Good Patterns

  • [positive patterns worth noting]

Verdict

[APPROVE / REQUEST_CHANGES / COMMENT — with brief rationale]

Omit empty severity sections. If no issues found, state the code looks good with brief justification.

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

Coding

Sharedintellect Quorum

Multi-agent validation framework — 6 independent AI critics evaluate artifacts against rubrics with evidence-grounded findings.

Registry SourceRecently Updated
3670Profile unavailable
Coding

Cortex Engine

Persistent cognitive memory for AI agents — query, record, review, and consolidate knowledge across sessions with spreading activation, FSRS scheduling, and...

Registry SourceRecently Updated
331Profile unavailable
Coding

Claude Code Controller

控制和管理 Claude Code 编码助手,支持项目感知编码、代码审查、重构和功能实现。使用 ACP 运行时在隔离会话中执行 Claude Code 任务,或在主会话中管理配置和项目上下文。

Registry SourceRecently Updated
1260Profile unavailable
Coding

QA Reviewer

提供代码审查、单元测试、覆盖率分析和问题追踪,支持C++/Python/JavaScript,确保项目质量和文档完整度。

Registry SourceRecently Updated
1882Profile unavailable