AI Skill MartBrowse skillsPromptsProgramsLearnWhat is a Skill?
 
← Back to list

Code Quality Gate

A four-mode code quality skill covering technical-debt cleanup, Ruff/Biome linting, a Python quality gate, and a multi-language universal gate.

Dev & CodingIntermediate★ 445⑂ 51AI score 9/10Last updated: Nov 3, 2026

What it does

The skill picks one of four modes based on your request wording:

  • Cleanup: scans 9 technical-debt categories (stale TODOs, unused imports, dead code, missing type hints, deprecated functions, naming inconsistencies, high complexity, duplicate code, missing docstrings) through a SCOPE → SCAN → REPORT workflow, ranking findings as Quick Wins → Important → Polish.
  • Linting: Ruff for Python and Biome for JS/TS, reading pyproject.toml and biome.json first so existing rules are preserved.
  • Python Quality Gate: runs ruff check, ruff format --check, mypy, pytest (with coverage when configured) and bandit in order, continuing even after a failure and reporting file:line diagnostics.
  • Universal Quality Gate: auto-detects Python, Go, JavaScript, TypeScript, Rust and Shell from repo markers and runs the matching tools, with --staged, --fix and --lang options.

It explicitly refuses to loosen rules or skip tests just to pass, and applies auto-fixes only with your permission.

Who it's for

  • Developers maintaining polyglot monorepos who need a consistent lint baseline
  • Python engineers who want ruff/mypy/bandit/pytest in one pass before opening a PR
  • Tech leads who need an evidence-backed technical-debt report for a legacy codebase

Examples

  1. "Find unused imports and dead code in this module" → cleanup mode returns a prioritized report starting with auto-fixable Quick Wins.
  2. "Run the Python quality gate before I commit" → all five checks run in order with a per-tool pass/fail summary.
  3. "Lint only the staged files" → the universal gate script runs with --staged as a pre-commit check.

· · · Install guide · · ·

Try it now, no install

Paste this into Claude to use the skill without installing anything.

Read the instructions in this file and follow them to help me:
https://raw.githubusercontent.com/notque/vexjoy-agent/HEAD/skills/code-quality/code-quality/SKILL.md

What I want: (describe your task here)

If Claude can't open the link, open it yourself and paste the contents instead.

↓ If it works for you, download the ZIP below and install it. Then it runs on its own — no pasting each time.

Install in the Claude app (no terminal)
  1. Download the ZIP with the button below.
  2. In Claude, open Settings → Capabilities and turn on 'Code execution and file creation'. (one time)
  3. Go to Customize → Skills → + → 'Upload a skill' and upload the ZIP.
↓ Download ZIP
Install in Claude Code

Let Claude do it — paste this into Claude Code

Install the skill I found on AI Skill Mart.
Copy the skills/code-quality/code-quality folder from the GitHub repo notque/vexjoy-agent into my ~/.claude/skills/code-quality/.
When it's done, tell me in one line what this skill can do.

Install with a command instead

git clone https://github.com/notque/vexjoy-agent.git /tmp/vexjoy-agent && mkdir -p ~/.claude/skills && cp -r /tmp/vexjoy-agent/skills/code-quality/code-quality ~/.claude/skills/code-quality

⚠ This is a third-party skill. Check the source repository before installing.

  1. Open a terminal.
  2. Clone the repository: git clone https://github.com/notque/vexjoy-agent.git /tmp/vexjoy-agent
  3. Create the skills directory: mkdir -p ~/.claude/skills
  4. Copy the skill: cp -r /tmp/vexjoy-agent/skills/code-quality/code-quality ~/.claude/skills/code-quality
  5. Verify with ls ~/.claude/skills/code-quality that SKILL.md and the references folder are present.
  6. Install the underlying tools: pip install ruff mypy bandit pytest for Python; check Biome with npx @biomejs/biome --version for JS/TS.
  7. Restart Claude Code, then try a prompt like "code quality check" or "run ruff" to trigger the skill.
View source on GitHub ↗License: MIT