Back to list
AsiaOstrich

code-review-assistant

by AsiaOstrich

Universal, language-agnostic development standards for software projects. Includes coding standards, git workflows, testing guidelines, documentation structure, and AI collaboration rules.

20🍴 3📅 Jan 23, 2026

SKILL.md


name: code-review-assistant description: | Systematic code review checklist and pre-commit quality gates for PRs. Use when: reviewing pull requests, checking code quality, before committing code. Keywords: review, PR, pull request, checklist, quality, commit, 審查, 檢查, 簽入.

Code Review Assistant

Language: English | 繁體中文

Version: 1.0.0 Last Updated: 2025-12-24 Applicability: Claude Code Skills


Purpose

This skill provides systematic checklists for code review and pre-commit verification.

Quick Reference

Comment Prefixes

PrefixMeaningAction Required
❗ BLOCKINGMust fix before merge🔴 Required
⚠️ IMPORTANTShould fix, but not blocking🟡 Recommended
💡 SUGGESTIONNice-to-have improvement🟢 Optional
❓ QUESTIONNeed clarification🔵 Discuss
📝 NOTEInformational, no action⚪ Informational

Review Checklist Categories

  1. Functionality - Does it work?
  2. Design - Right architecture?
  3. Quality - Clean code?
  4. Readability - Easy to understand?
  5. Tests - Adequate coverage?
  6. Security - No vulnerabilities?
  7. Performance - Efficient?
  8. Errors - Properly handled?
  9. Docs - Updated?
  10. Dependencies - Necessary?

Pre-Commit Checklist

  • Build succeeds (zero errors, zero warnings)
  • All tests pass
  • Code follows project standards
  • No security vulnerabilities
  • Documentation updated
  • Branch synced with target

Detailed Guidelines

For complete standards, see:

AI-Optimized Format (Token-Efficient)

For AI assistants, use the YAML format file for reduced token usage:

  • Base standard: ai/standards/code-review.ai.yaml

Example Review Comments

❗ BLOCKING: Potential SQL injection vulnerability here.
Please use parameterized queries instead of string concatenation.

⚠️ IMPORTANT: This method is doing too much (120 lines).
Consider extracting validation logic to a separate method.

💡 SUGGESTION: Consider using a Map here instead of an array for O(1) lookup.

❓ QUESTION: Why are we using setTimeout here instead of async/await?

📝 NOTE: This is a clever solution! Nice use of reduce here.

Core Principles

  1. Be Respectful - Review code, not the person
  2. Be Thorough - Check functionality, not just syntax
  3. Be Timely - Review within 24 hours
  4. Be Clear - Explain WHY, not just WHAT

Checkin Quality Gates (YAML Compressed)

# === MANDATORY CHECKLIST ===
build:
  - code_compiles: "zero errors, zero warnings"
  - dependencies: "all installed, versions locked"
  verify: "run build locally, exit code 0"

test:
  - existing_pass: "100% pass rate (unit/integration/e2e)"
  - new_code_tested: "features→tests, bugfix→regression"
  - coverage: "not decreased, critical paths tested"
  verify: "run all suites, review coverage report"

quality:
  - standards: "naming, formatting, comments"
  - no_smells: "methods≤50 lines, nesting≤3, complexity≤10, no duplication"
  - security: "no hardcoded secrets, no SQLi, no XSS, no insecure deps"
  verify: "run linter, static analysis, security scanner"

docs:
  - api_docs: "public APIs documented"
  - readme: "updated if needed"
  - changelog: "user-facing changes → [Unreleased]"

workflow:
  - branch_naming: "feature/, fix/, docs/, chore/"
  - commit_message: "conventional commits format"
  - synced: "merged/rebased with target branch"

# === NEVER COMMIT WHEN ===
blockers:
  - "Build has errors"
  - "Tests failing"
  - "Feature incomplete (would break functionality)"
  - "Contains WIP/TODO in critical logic"
  - "Contains debugging code (console.log, print)"
  - "Contains commented-out code blocks"

# === COMMIT TIMING ===
good_times:
  - "Completed functional unit"
  - "Specific bug fixed with regression test"
  - "Independent refactor (all tests pass)"
  - "Runnable state"

bad_times:
  - "Build failures"
  - "Test failures"
  - "Incomplete features"
  - "Experimental code with TODOs"

# === GRANULARITY ===
ideal_size:
  files: "1-10 (split if >10)"
  lines: "50-300"
  scope: "single concern"

split_principle:
  combine: ["feature + its tests", "tightly related multi-file"]
  separate: ["Feature A + Feature B", "refactor + new feature", "bugfix + incidental refactor"]

Configuration Detection

This skill supports project-specific configuration.

Detection Order

  1. Check CONTRIBUTING.md for "Disabled Skills" section
    • If this skill is listed, it is disabled for this project
  2. Check CONTRIBUTING.md for "Code Review Language" section
  3. If not found, default to English

First-Time Setup

If no configuration found and context is unclear:

  1. Ask the user: "This project hasn't configured code review language. Which option would you like? (English / 中文)"
  2. After user selection, suggest documenting in CONTRIBUTING.md:
## Code Review Language

This project uses **[chosen option]** for code review comments.
<!-- Options: English | 中文 -->

Configuration Example

In project's CONTRIBUTING.md:

## Code Review Language

This project uses **English** for code review comments.
<!-- Options: English | 中文 -->

### Comment Prefixes
BLOCKING, IMPORTANT, SUGGESTION, QUESTION, NOTE


Version History

VersionDateChanges
1.0.02025-12-24Added: Standard sections (Purpose, Related Standards, Version History, License)

License

This skill is released under CC BY 4.0.

Source: universal-dev-standards

Score

Total Score

75/100

Based on repository quality metrics

SKILL.md

SKILL.mdファイルが含まれている

+20
LICENSE

ライセンスが設定されている

+10
説明文

100文字以上の説明がある

+10
人気

GitHub Stars 100以上

0/15
最近の活動

1ヶ月以内に更新

+10
フォーク

10回以上フォークされている

0/5
Issue管理

オープンIssueが50未満

+5
言語

プログラミング言語が設定されている

+5
タグ

1つ以上のタグが設定されている

+5

Reviews

💬

Reviews coming soon