Code Quality Analysis
Scores code quality and technical debt across 14 languages before commits.
Install
npx skills add Done-0/fuck-u-code --skill fuck-u-code-analysis -g -a claude-code -y- Repository
- Done-0/fuck-u-code7.3k
- Category
- Engineering
- Updated
- 2mo ago
- License
- MIT
- Context cost
- Mediumabout 3,000 tokens
- Runs scripts
- No, instructions only
What it does
Use when code changes are complete and ready for quality review, before committing or creating PRs. Triggers after implementing features, fixing bugs, or refactoring code. Also use when user asks to check code quality, analyze technical debt, review code smell, or mentions "fuck-u-code", "code quality", "shit mountain", "code review", "static analysis". Covers all 14 supported languages (Go, JS, TS, Python, Java, C, C++, Rust, C#, Lua, PHP, Ruby, Swift, Shell).
fuck-u-code Code Quality Analysis & Review
Prerequisites
Install fuck-u-code globally before using this skill:
npm install -g eff-u-code
Verify installation:
fuck-u-code --version
Requires Node.js >= 18.0.0.
Overview
Run fuck-u-code analyze to obtain quantitative code quality metrics across 7 dimensions (11 metrics), then interpret results and provide actionable refactoring recommendations based on the standards defined in this skill.
The tool produces a 0-100 overall score and per-file scores. Higher = better quality. The skill teaches you how to interpret every metric, judge severity, and prescribe specific fixes.
Workflow
digraph workflow {
rankdir=LR;
node [shape=box];
"Run fuck-u-code analyze" -> "Read JSON output";
"Read JSON output" -> "Identify critical files (score < 60)";
"Identify critical files" -> "Drill into per-metric details";
"Drill into per-metric details" -> "Apply review standards (Section 4)";
"Apply review standards" -> "Write actionable remediation report";
}
Step 1: Run Analysis
# Basic analysis
fuck-u-code analyze . -f json -o /tmp/fuc-report.json
# Verbose with top 20 worst files
fuck-u-code analyze . -v -t 20 -f json -o /tmp/fuc-report.json
# Exclude generated/test files
fuck-u-code analyze . -e "**/*.test.ts" -e "**/generated/**" -f json -o /tmp/fuc-report.json
Read the JSON output file to get structured data.
Step 2: Identify Problem Areas
From the JSON report, extract:
- overallScore: Project-wide score (0-100). Weighted average by code line count.
- aggregatedMetrics: Per-metric averages, medians, min/max across all files.
- files[]: Per-file results, sorted by score ascending (worst first).
Focus on files with score < 60 (the "shit mountain" zone).
Step 3: Drill into Metrics
For each problem file, examine the metrics[] array. Each metric has:
