qlty-check — Claude Code skill: lint, format, metrics
Runs qlty CLI over your code: linters, auto-fix, formatting and complexity metrics. Handy before a commit or a handoff.
npx skills add parcadei/Continuous-Claude-v3 --skill qlty-check -a claude-codeWhat qlty-check does
The skill drives qlty CLI through scripts/qlty_check.py and the runtime harness. Per the author, qlty covers 70+ linters across 40+ languages, so one tool handles linting, formatting and metrics together. It only asks for Bash and Read.
Flags pick the mode: --check for linters, --fix to auto-fix, --fmt to format, --metrics for metrics, --smells to hunt down problem spots. --all processes every file instead of just changed ones, --paths narrows to specific files or directories, and --level filters by note/low/medium/high. There is --init to set qlty up in a repo and --plugins to list what is available.
You need the qlty CLI and a .qlty/qlty.toml config in the repo before the first run — qlty init writes it. No config, no checks, so that is the first thing to do in a fresh project. If qlty is already installed, call it directly: qlty check, qlty check --fix, qlty fmt.
What it helps with
- lint changed files before a commit
- auto-fix formatting and style issues
- measure complexity and duplication
- spot code smells in fresh code
- set up qlty in a new repo in one command
Example prompts for the agent
- Run qlty-check with auto-fix on the changed files
- Show complexity metrics for the current branch
- Find code smells under
src/
How to install qlty-check
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill qlty-check -a claude-code2Manually: put the files in place
~/.claude/skills/qlty-check/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/qlty-check/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill qlty-check -a codex2Manually: put the files in place
.agents/skills/qlty-check/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill qlty-check -a cursor2Manually: put the files in place
.cursor/skills/qlty-check/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install parcadei/Continuous-Claude-v3 qlty-check2Manually: put the files in place
.github/skills/qlty-check/SKILL.md1Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill qlty-check -a gemini-cli2Platform CLI
gemini skills install https://github.com/parcadei/Continuous-Claude-v3 --path .claude/skills/qlty-checkManually: put the files in place
.devin/skills/qlty-check/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add parcadei/Continuous-Claude-v3 --skill qlty-check -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about qlty-check
How do I install qlty-check in Claude?
Run npx skills add parcadei/Continuous-Claude-v3 --skill qlty-check -a claude-code. The skill lands in ~/.claude/skills/qlty-check/SKILL.md.
What does qlty-check do?
It runs qlty CLI via scripts/qlty_check.py: linters, auto-fix, formatting, metrics and code smell detection. Works on changed files or the whole project.
What does qlty-check need to run?
The qlty CLI and a .qlty/qlty.toml config in the repo. qlty init creates the config, and the --init flag calls it for you.
Source text
SKILL.md · MIT
--- name: qlty-check description: Code quality checks, formatting, and metrics via qlty CLI allowed-tools: [Bash, Read] --- # Qlty Code Quality Universal code quality tool supporting 70+ linters for 40+ languages via qlty CLI. ## When to Use - Check code for linting issues before commit/handoff - Auto-fix formatting and style issues - Calculate code metrics (complexity, duplication) - Find code smells ## Quick Reference ```bash # Check changed files with auto-fix uv run python -m runtime.harness scripts/qlty_check.py --fix # Check all files uv run python -m runtime.harness scripts/qlty_check.py --all # Format files uv run python -m runtime.harness scripts/qlty_check.py --fmt # Get metrics uv run python -m runtime.harness scripts/qlty_check.py --metrics # Find code smells uv run python -m runtime.harness scripts/qlty_check.py --smells ``` ## Parameters | Parameter | Description | |-----------|-------------| | `--check` | Run linters (default) | | `--fix` | Auto-fix issues | | `--all` | Process all files, not just changed | | `--fmt` | Format files instead | | `--metrics` | Calculate code metrics | | `--smells` | Find code smells | | `--paths` | Specific files/directories | | `--level` | Min issue level: note/low/medium/high | | `--cwd` | Working directory | | `--init` | Initialize qlty in a repo | | `--plugins` | List available plugins | ## Common Workflows ### After Implementation ```bash # Auto-fix what's possible, see what remains uv run python -m runtime.harness scripts/qlty_check.py --fix ``` ### Quality Report ```bash # Get metrics for changed code uv run python -m runtime.harness scripts/qlty_check.py --metrics # Find complexity hotspots uv run python -m runtime.harness scripts/qlty_check.py --smells ``` ### Initialize in New Repo ```bash uv run python -m runtime.harness scripts/qlty_check.py --init --cwd /path/to/repo ``` ## Direct CLI (if qlty installed) ```bash # Check changed files qlty check # Auto-fix qlty check --fix # JSON output qlty check --json # Format qlty fmt ``` ## Requirements - **qlty CLI**: https://github.com/qltysh/qlty - **MCP server**: `servers/qlty/server.py` wraps CLI - **Config**: `.qlty/qlty.toml` in repo (run `qlty init` first) ## vs Other Tools | Tool | Use Case | |------|----------| | **qlty** | Unified linting, formatting, metrics for any language | | **ast-grep** | Structural code patterns and refactoring | | **morph** | Fast text search |
© parcadei · MIT · parcadei/Continuous-Claude-v3
