Code Quality logo

Code Quality

Community
notque
code-quality

Code quality: cleanup, linting, formatting, quality gates.

Overview

Publishernotque
Repositoryvexjoy-agent
Skill namecode-quality
Stars
443
Forks
50
Bundled files
9
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 9 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by notque on GitHub. Read the source before you install it.

Installation

Install the Code Quality AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/notque/vexjoy-agent/tree/main/skills/code-quality/code-quality
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 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
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Code Quality in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Code Quality on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Code Quality is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Code Quality

Four modes. Select by request signal:

SignalMode
Dead code, stale TODOs, unused imports, technical debtCleanup
Lint Python/JS/TS, run ruff, run biome, format codeLinting
Python quality checks, ruff+pytest+mypy+banditPython Quality Gate
Multi-language quality gate, general "quality check"Universal Quality Gate

Default: Python-specific requests run Python Quality Gate. General requests run Universal Quality Gate.


Mode A: Cleanup

Scan for 9 categories of technical debt: stale TODOs, unused imports, dead code, missing type hints, deprecated functions, naming inconsistencies, high complexity, duplicate code, missing docstrings. Follow references/code-cleanup.md for the full 3-phase workflow (SCOPE, SCAN, REPORT).

Key principles:

  • Read CLAUDE.md first for project conventions
  • Scan only what was requested; ask for a target rather than scanning everything
  • Exclude vendor/, node_modules/, .venv/, build/, dist/, generated/, .git/
  • Prioritize findings by impact/effort: Quick Wins (auto-fixable, <5 min) > Important (bugs, security) > Polish (style)
  • Apply auto-fixes only with explicit user permission; check first, fix, review diff, rerun checks

Mode B: Linting

Check or fix Python with Ruff and JavaScript/TypeScript with Biome. Read project instructions, pyproject.toml, and biome.json first; preserve configured rules.

TaskPythonJavaScript/TypeScript
Checkruff check .npx @biomejs/biome check src/
Format checkruff format --check .Included in Biome check
Fix lintruff check --fix .npx @biomejs/biome check --write src/
Formatruff format .npx @biomejs/biome format --write src/

Use project environment (./venv/bin/ruff). If configured, use make lint or make lint-fix. Check first; apply fixes only within requested scope. Review git diff, undo incorrect fixes, rerun checks. Do not change rules or install new tooling to get a pass.

Common fixes: F401 = remove/use import. I001 = sort imports. E501 = shorten lines. Biome noVar = use let/const. useConst = mark unchanged bindings.


Mode C: Python Quality Gate

Run checks in order. Read repository configuration first; project commands and thresholds override defaults.

Detect: Find pyproject.toml, setup.py, .python-version. Check tool availability: ruff and pytest required; mypy and bandit optional unless project requires them.

Execute:

OrderCommandCondition
1ruff check . --output-format=groupedRequired
2ruff format --check .Required
3mypy . --ignore-missing-imports --show-error-codesIf available
4pytest -v --tb=short --cov=src --cov-report=term-missingCoverage only when configured
5bandit -r src/ -ll --format=screenIf available

Run all checks even after one fails. Do not skip tests to get a pass.

Assess: Prioritize syntax/undefined errors, failing tests, security findings before style. Report per-tool status with actionable file:line diagnostics.

Fix: When authorized, run ruff check . --fix and ruff format ., review diff, rerun checks.


Mode D: Universal Quality Gate

Auto-detect languages and run configured checks. Read repository instructions first.

bash
python3 ~/.claude/skills/code-quality/universal-quality-gate/scripts/run_quality_gate.py

Options: --staged (pre-commit), --lang python (single language), --fix (apply fixes), -v (verbose).

Language detection uses hooks/lib/language_registry.json:

LanguageMarkersTools
Pythonpyproject.toml, requirements.txtruff, mypy, bandit
Gogo.modgofmt, golangci-lint, go vet
JavaScriptpackage.jsoneslint, biome
TypeScripttsconfig.jsontsc, eslint, biome
RustCargo.tomlclippy, cargo fmt
Shell*.shshellcheck

A gate pass means required tools passed; it does not prove tests, builds, or business behavior passed.


Deep References

Load on demand when the signal matches.

SignalReferenceContent
Full cleanup workflow (9 categories)references/code-cleanup.md3-phase cleanup: SCOPE, SCAN, REPORT
Language-specific scan commandsreferences/cleanup-scan-commands.mdPer-language commands and expected output
Cleanup report formattingreferences/cleanup-report-template.mdStructured report template
Ruff rules, F401/E711/B006references/ruff-rules-reference.mdRuff rule reference by category
Biome rules, ESLint migrationreferences/biome-rules-reference.mdBiome rule reference by category
Python quality tool commandsreferences/python-tool-commands.mdDetailed tool command options
Python quality reportreferences/python-report-template.mdStructured report template
pyproject.toml templatereferences/pyproject-template.tomlTool configuration template

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Code Quality AI skill do?

Code quality: cleanup, linting, formatting, quality gates.

Why use Code Quality on TypingMind?

Because you install it once and use it with any model. Code Quality is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Code Quality in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/notque/vexjoy-agent/tree/main/skills/code-quality/code-quality. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Code Quality?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Code Quality?

As many as you like. As long as a model supports skills, you can use Code Quality with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Code Quality AI skill free?

Yes. It is published on GitHub by notque under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇