Code Quality Analyzer

A 29-line review-prompt template living in skill-up's e2e test fixtures

Test report

Verdict
In test queue
Score
6.4/10
Tested
Jul 17, 2026
Environment
Claude Code 2.x (agent harness)

This is not a distributable skill — it is a 29-line test fixture inside the skill-up eval framework's e2e testdata, and the repo's 58 stars belong to the framework, not to it. Ran it against a deliberately buggy Python file: the skill-guided review and a plain no-skill review found the identical six issues (SQL injection, hardcoded password, empty-list crash, O(n^2) duplicate finder, two resource leaks); the skill contributed only a report template with a 1-10 score. The claimed 'automatically performs static analysis' does not exist — there is no tool, no script, just a prompt, and it showed zero measurable edge over baseline Claude.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 4/5
  • Output vs. baseline 5/10
  • Docs & honesty 2/5

What Code Quality Analyzer does

A minimal prompt template that formats code reviews into a scored report with correctness, maintainability, performance and security sections. It ships as an e2e test fixture inside Alibaba's skill-up evaluation framework rather than as a standalone skill, and adds no analysis tooling of its own. Triggers on requests like 'analyze code quality' or 'code score'.

How to install Code Quality Analyzer

git clone https://github.com/alibaba/skill-up
mkdir -p ~/.claude/skills
cd skill-up && cp -r e2e/testdata/full-report-pipeline ~/.claude/skills/code-quality-analyzer

Skills live in ~/.claude/skills/ (global) or .claude/skills/ (per-project). Restart Claude Code after installing.

Commands — how to trigger Code Quality Analyzer

  • /code-quality-analyzer A 29-line review-prompt template living in skill-up's e2e test fixtures

It also activates on plain-language prompts like these:

  • Score this Python file's code quality out of 10
  • Review this code for correctness, maintainability, and security
  • Give me a scored report on this file's SQL injection risk

Frequently asked questions

Is the Code Quality Analyzer skill free?
Yes. The skill itself is free from alibaba/skill-up. SkillProof publishes the install command and an independent test verdict at no cost.
Does Code Quality Analyzer work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 17, 2026. Verdict: In test queue. This is not a distributable skill — it is a 29-line test fixture inside the skill-up eval framework's e2e testdata, and the repo's 58 stars belong to the framework, not to it. Ran it against a deliberately buggy Python file: the skill-guided review and a plain no-skill review found the identical six issues (SQL injection, hardcoded password, empty-list crash, O(n^2) duplicate finder, two resource leaks); the skill contributed only a report template with a 1-10 score. The claimed 'automatically performs static analysis' does not exist — there is no tool, no script, just a prompt, and it showed zero measurable edge over baseline Claude.
What is the Code Quality Analyzer SkillProof Score?
6.4/10 — installs cleanly 5/5, triggers reliably 4/5, output vs. baseline 5/10, docs & honesty 2/5.
How do I install Code Quality Analyzer?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Code Quality Analyzer with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.