Qt Qml Review

This is a comprehensive QML code review system that runs 47+ deterministic lint rules in Python, then spins up six parallel analysis agents to catch the subtle stuff: binding loops, layout feedback cycles, memory leaks from dynamic object creation, and delegate reuse bugs. It's read-only and reports only high-confidence issues above 80/100. You'd run this before committing QML or when auditing a codebase. The interesting part is the two-phase design: fast mechanical checks first, then deep semantic analysis that actually traces symbol references and checks visual tree relationships. It also wraps system qmllint if available. Honestly a serious piece of work for teams shipping non-trivial Qt6 UIs who are tired of runtime surprises.

skills.sh installs: 1K
GitHub stars: 534
last updated: Jun 10, 2026

View on GitHub

Install

$ npx -y skills add theqtcompanyrnd/agent-skills --skill qt-qml-review --agent claude-code

Installs into .claude/skills of the current project.

Files

Qt QML Code Review

Read-only review of Qt6 QML code: a deterministic Python linter (with qmllint folded in when available) first, then agent-driven deep analysis across seven rule domains, then one consolidated report. Suggest it before the user commits QML code.

Scope detection

Diff scope -- "this commit", "these changes", "the diff", "what I changed", "staged changes", "before I commit". The range is HEAD (working tree plus index), --cached for staged changes only, or HEAD~1..HEAD for "this commit". Do not load the diff itself: the linter's --diff mode (Phase 1) lists the changed files with their changed-line counts and reports only findings on changed lines.

Codebase scope -- "review the codebase", "audit src/", or an explicit path with no commit language. Glob *.qml under the path.