Provides quantitative rubrics and criteria for scoring code quality on a 1-10 scale. Use when reviewing code, performing code audits, establishing quality baselines, comparing implementations, or providing objective code feedback.
Uses a weighted 10-category rubric to score code quality 1-10. Triggers when reviewing code, auditing, comparing implementations, or requesting objective quality feedback.
/plugin marketplace add mgd34msu/goodvibes-plugin/plugin install goodvibes@goodvibes-marketThis skill inherits all available tools. When active, it can use any tool Claude has access to.
references/deduction-catalog.mdreferences/score-descriptors.mdreferences/scoring-rubrics.mdreferences/severity-weights.mdSystematic, quantitative code quality assessment using weighted categories and standardized deductions.
Full code review with score:
Score this code on a 1-10 scale using the code-scoring rubric
Category-specific assessment:
Evaluate the error handling in this module using the scoring rubric
Compare implementations:
Score both implementations and recommend which is better
Final Score = 10 - Total Deductions
Where:
Total Deductions = SUM(Category Deductions * Category Weight)
Category Deduction = SUM(Issue Points * Severity Multiplier)
| Category | Weight | Focus Areas |
|---|---|---|
| Organization | 12% | File structure, module boundaries, separation of concerns |
| Naming | 10% | Variables, functions, classes, constants, files |
| Error Handling | 12% | Try/catch, validation, error propagation, recovery |
| Testing | 12% | Coverage, quality, edge cases, maintainability |
| Performance | 10% | Efficiency, resource usage, scalability |
| Security | 12% | Input validation, auth, data protection, secrets |
| Documentation | 8% | Comments, API docs, README, inline explanations |
| SOLID Principles | 10% | SRP, OCP, LSP, ISP, DIP adherence |
| Dependencies | 6% | Version management, minimal deps, no circular refs |
| Maintainability | 8% | Readability, complexity, changeability |
Total: 100%
| Severity | Multiplier | Description |
|---|---|---|
| Critical | 2.0x | Security vulnerabilities, data loss risks, crashes |
| Major | 1.5x | Significant bugs, poor patterns, missing core functionality |
| Minor | 1.0x | Code smells, style issues, minor inefficiencies |
| Nitpick | 0.5x | Preferences, optional improvements |
| Score | Label | Meaning | Typical Characteristics |
|---|---|---|---|
| 10 | Exemplary | Production excellence | Minimal issues, well-tested, secure, documented |
| 9 | Excellent | Minor polish needed | 1-2 nitpicks, strong overall quality |
| 8 | Very Good | Ready with small fixes | Few minor issues, solid fundamentals |
| 7 | Good | Acceptable quality | Some improvements needed, no major issues |
| 6 | Satisfactory | Functional but rough | Multiple minor issues, needs cleanup |
| 5 | Adequate | Meets minimum bar | Works but has clear problems |
| 4 | Below Average | Needs significant work | Major issues present, risky to deploy |
| 3 | Poor | Substantial rework | Multiple major issues, architectural problems |
| 2 | Very Poor | Fundamental problems | Barely functional, serious concerns |
| 1 | Critical | Do not deploy | Security vulnerabilities, crashes, data risks |
Quick reference for frequent issues. See references/deduction-catalog.md for complete list.
| Issue | Base Points | Category |
|---|---|---|
| SQL injection vulnerability | 2.0 | Security |
| Hardcoded secrets/credentials | 2.0 | Security |
| No error handling in critical path | 1.5 | Error Handling |
| Missing input validation | 1.5 | Security |
| No tests for core functionality | 1.5 | Testing |
| N+1 query pattern | 1.5 | Performance |
| God class (500+ lines) | 1.5 | Organization |
| Issue | Base Points | Category |
|---|---|---|
| Inconsistent naming convention | 1.0 | Naming |
| Missing JSDoc/docstrings on public API | 1.0 | Documentation |
| Circular dependency | 1.0 | Dependencies |
| Deeply nested code (4+ levels) | 1.0 | Maintainability |
| Magic numbers without constants | 1.0 | Naming |
| Empty catch blocks | 1.0 | Error Handling |
| Duplicated code blocks | 1.0 | Organization |
| Issue | Base Points | Category |
|---|---|---|
| Inconsistent formatting | 0.5 | Maintainability |
| Missing edge case tests | 0.5 | Testing |
| Verbose variable names | 0.5 | Naming |
| Outdated dependencies (no CVEs) | 0.5 | Dependencies |
| Missing inline comments in complex logic | 0.5 | Documentation |
1. Count lines of code
2. Identify file/module structure
3. Note language and framework
4. Check for tests presence
5. Scan for obvious red flags
For each of the 10 categories:
1. Review relevant code sections
2. Identify issues
3. Classify severity (critical/major/minor/nitpick)
4. Calculate: Issues * Severity Multiplier
5. Apply category weight
Final Score = 10 - (Sum of weighted deductions)
If score < 1: score = 1
If score > 10: score = 10
## Code Score: X.X/10
### Score Breakdown
| Category | Weight | Deductions | Weighted |
|----------|--------|------------|----------|
| Organization | 12% | ... | ... |
| ... | ... | ... | ... |
### Critical Issues (Fix Immediately)
- [Issue 1]
### Major Issues (Fix Before Merge)
- [Issue 1]
### Minor Issues (Fix When Convenient)
- [Issue 1]
### Recommendations
- [Improvement 1]
Excellent (0 deductions):
Red flags:
Excellent (0 deductions):
Red flags:
Excellent (0 deductions):
Red flags:
Excellent (0 deductions):
Red flags:
Excellent (0 deductions):
Red flags:
Excellent (0 deductions):
Red flags:
Excellent (0 deductions):
Red flags:
Excellent (0 deductions):
Red flags:
Excellent (0 deductions):
Red flags:
Excellent (0 deductions):
Red flags:
| Score Range | Deployment Decision |
|---|---|
| 8-10 | Ready for production |
| 7-7.9 | Ready with minor fixes |
| 5-6.9 | Needs review and fixes |
| 3-4.9 | Significant rework required |
| 1-2.9 | Do not deploy |
| Score Range | Required Actions |
|---|---|
| 9-10 | Approve immediately |
| 7-8.9 | Approve with suggestions |
| 5-6.9 | Request changes |
| 3-4.9 | Major revision needed |
| 1-2.9 | Reject with detailed feedback |
This skill should be used when the user asks to "create a slash command", "add a command", "write a custom command", "define command arguments", "use command frontmatter", "organize commands", "create command with file references", "interactive command", "use AskUserQuestion in command", or needs guidance on slash command structure, YAML frontmatter fields, dynamic arguments, bash execution in commands, user interaction patterns, or command development best practices for Claude Code.
This skill should be used when the user asks to "create an agent", "add an agent", "write a subagent", "agent frontmatter", "when to use description", "agent examples", "agent tools", "agent colors", "autonomous agent", or needs guidance on agent structure, system prompts, triggering conditions, or agent development best practices for Claude Code plugins.
This skill should be used when the user asks to "create a hook", "add a PreToolUse/PostToolUse/Stop hook", "validate tool use", "implement prompt-based hooks", "use ${CLAUDE_PLUGIN_ROOT}", "set up event-driven automation", "block dangerous commands", or mentions hook events (PreToolUse, PostToolUse, Stop, SubagentStop, SessionStart, SessionEnd, UserPromptSubmit, PreCompact, Notification). Provides comprehensive guidance for creating and implementing Claude Code plugin hooks with focus on advanced prompt-based hooks API.