davidcoachdev/dcfiles/code-review-plus
Claude Code and agent skill by davidcoachdev/dcfiles
- community
Checking that the SKILL.md file is still in the repository.
Enhanced code review with local + PR modes, security scanning, and quality gates. Blocks commits on CRITICAL/HIGH issues.
Install
npx vskill@latest install davidcoachdev/dcfiles/code-review-plusSKILL.md
The same SKILL.md was published earlier as davidcoachdev/dcfiles/code-review-plus.
Absorbed:code-reviewer(v1 — general code review framework, severity levels, best practices)
Code Review Plus
Enhanced code review system with local uncommitted changes review and GitHub PR review modes. Comprehensive security and quality scanning.
Modes
Local Review Mode
Reviews uncommitted changes (git diff).
PR Review Mode
Reviews GitHub PR (pass PR number or URL).
Workflow
Phase 1 — GATHER
If no changed files → Stop with "Nothing to review."
Phase 2 — SECURITY SCAN
Check for CRITICAL issues:
- Hardcoded credentials, API keys, tokens
- SQL injection vulnerabilities
- XSS vulnerabilities
- Missing input validation
- Insecure dependencies
- Path traversal risks
Phase 3 — QUALITY SCAN
Check for HIGH issues:
- Functions > 50 lines
- Files > 800 lines
- Nesting depth > 4 levels
- Missing error handling
- console.log statements
- TODO/FIXME comments
Check for MEDIUM issues:
- Mutation patterns (prefer immutable)
- Emoji usage in code
- Missing tests for new code
- Accessibility issues (a11y)
Phase 4 — REPORT
Generate structured report:
- Severity: CRITICAL, HIGH, MEDIUM, LOW
- File location and line numbers
- Issue description
- Suggested fix
Phase 5 — GATE
Block commit if CRITICAL or HIGH issues found. Never approve code with security vulnerabilities.
Usage
Severity Decision Matrix
| Severity | Action | Block Commit | |
|---|---|---|---|
| CRITICAL | Fix required | YES | |
| HIGH | Fix required | YES | |
| MEDIUM | Suggest fix | NO | |
| LOW | Note | NO |
Security Checks
Quality Metrics
- Cyclomatic complexity < 10
- Lines per function < 50
- Lines per file < 800
- Nesting depth < 4
- Test coverage > 70%
Output Format
Security
- Security scanPassed, 95 of 100Pattern checks on the skill's files.
- Model reviewPassed
Quality evaluation
- Task evaluationNot runNo evaluation yet. Run one in Skill Studio.
Source
- SKILL.md in the repositoryCheckingconfig/.config/opencode/skills/code-review-plus/SKILL.md
Popularity
- 7-day trend score
- 5
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
[](https://verified-skill.com/skills/davidcoachdev/dcfiles/code-review-plus)