qt-qml-review

Invoke when the user asks to review, check, audit, or look over Qt6 QML code -- or suggest before committing. Runs deterministic linting (47+ rules) then six parallel deep- analysis agents covering bindings, layout, loaders, delegates, states, and performance. Optionally invokes system qmllint for type-level checks. Reports only high-confidence issues (>80/100) with structured mitigations. Read-only -- never modifies code.

Quality

86%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, actionable review skill with a clear phased workflow, explicit validation checkpoints, and properly signaled one-level references. Minor tightening possible in the conciseness of preamble text and the agent-mission detail that could be partly delegated to the checklist.

Suggestions

Move the detailed per-agent 'Check for' bullet lists into references/qt-qml-review-checklist.md, keeping only each agent's scope and a one-line summary in SKILL.md to reduce inline length.

Trim explanatory asides like 'This single-pass scanner encodes all mechanically-checkable rules...' and 'The linter is authoritative -- do not second-guess its output' to tighten token efficiency.

Provide literal copy-pasteable subagent prompt templates for each of the six agents rather than prose mission descriptions, to lift actionability toward fully executable guidance.

Dimension	Reasoning	Score
Conciseness	Dense, actionable content that assumes Claude's competence (no basic QML/concept explanations), with only minor instances of over-explanation such as 'The linter is authoritative -- do not second-guess its output' and the rule-category preamble that could be trimmed slightly.	4 / 5
Actionability	Provides concrete executable commands ('python3 references/lint-scripts/qt_qml_lint.py <files...>', 'qmllint --json - -I <import-paths> <files...>', 'git diff HEAD~1..HEAD') and a fully specified output template, though the agent-launch instructions remain somewhat abstract mission descriptions rather than copy-paste prompts.	4 / 5
Workflow Clarity	Three phases are explicitly sequenced with 'Never skip a phase', plus validation checkpoints (collect output before proceeding, dedup by file+line+issue, confidence-threshold suppression <60, max 10 investigation targets) and checklists for the complex multi-agent process.	5 / 5
Progressive Disclosure	Clear overview pointing to two real one-level-deep references (references/qt-qml-review-checklist.md and references/lint-scripts/qt_qml_lint.py, both verified present), but the body is fairly long with detailed per-agent checklists that sit at the boundary of belonging in the checklist file rather than inline.	4 / 5
	Total	17 / 20 Passed

Description

92%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A highly specific, well-triggered description that clearly states both capability and invocation conditions in third person. Only minor gap is the absence of the .qml file extension among trigger terms.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions -- 'Runs deterministic linting (47+ rules)', 'six parallel deep-analysis agents', 'Optionally invokes system qmllint', 'Reports only high-confidence issues (>80/100) with structured mitigations' -- giving comprehensive coverage of what the skill does.	5 / 5
Completeness	Explicitly answers both what (linting + six agents + qmllint + high-confidence reporting, read-only) and when ('Invoke when the user asks to review, check, audit, or look over Qt6 QML code -- or suggest before committing') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Strong natural trigger verbs ('review, check, audit, or look over', 'before committing') cover the review domain well, but the description omits the .qml file extension users would naturally say, leaving a few natural terms missing (anchor 4 rather than 5).	4 / 5
Distinctiveness Conflict Risk	Narrowly scoped to 'Qt6 QML code' review with distinctive triggers; minimal overlap risk with other skills.	5 / 5
	Total	19 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
referenced_paths_exist	Referenced path issues: 3 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: x-tools-author/x-tools
Path: .github/skills/qt-qml-review/SKILL.md
Commit: 6214c41

Reviewed: 4 hours ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.