qt-cpp-review

Invoke when the user asks to review, check, audit, or look over Qt6 C++ code — or suggest before committing. Runs deterministic linting (60+ rules) then six parallel deep- analysis agents covering model contracts, ownership, threading, API correctness, error handling, and performance. Reports only high-confidence issues (>80/100) with structured mitigations. Read-only — never modifies code.

Quality

89%

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

78%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.

The body is a strong, well-structured review workflow with executable lint commands, a precise report template, and properly progressive references to real bundle files. Its main weakness is conciseness: the six inlined agent checklists duplicate content from the reference checklist and inflate the token budget, and subagent launch mechanics stay abstract rather than runnable.

Suggestions

Trim the six inlined agent-mission checklists to a short scope statement plus a pointer to the corresponding section in references/qt-review-checklist.md, to reduce duplication and token cost (conciseness).

Add concrete, copy-paste ready commands or a minimal example for launching the six parallel subagents (e.g. a Task/Agent invocation snippet), so the deep-analysis phase is as actionable as the lint phase (actionability).

Add an explicit validate/retry checkpoint after Phase 2 (e.g. re-run lint or re-check findings flagged as investigation targets) to round out the workflow's feedback loops (workflow_clarity).

Dimension	Reasoning	Score
Conciseness	The body is largely efficient and assumes Claude's competence (terse bullet checklists, no 'what is Qt' padding), but the six inlined agent-mission checklists total several hundred lines that overlap heavily with references/qt-review-checklist.md, which could be trimmed to keep the overview lean.	4 / 5
Actionability	Provides concrete executable commands (python3 references/lint-scripts/qt_review_lint.py, git diff variants) and a precise output template, but the agent missions describe what to check rather than giving copy-paste ready invocation commands for launching each agent, leaving a minor gap.	4 / 5
Workflow Clarity	Three phases are explicitly sequenced ('Never skip a phase') with confidence thresholds and a consolidation/dedup step, plus a fallback if Python is absent; however the only validation checkpoint is Phase 1 lint output feeding Phase 2, and there is no explicit validate-then-retry loop for the deep-analysis agents, leaving a minor checkpoint gap.	4 / 5
Progressive Disclosure	The SKILL.md is a well-signaled overview with one-level-deep references (qt-review-checklist.md, qt-framework-checklist.md, qt-deprecated-classes.md, lint-scripts/qt_review_lint.py), all of which exist as real bundle files, and a clear References section mapping each path to its purpose, matching the score-5 anchor.	5 / 5
	Total	17 / 20 Passed

Description

100%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.

The description is exemplary: it concisely states concrete capabilities, natural trigger terms, explicit use-when guidance, and a distinct Qt6 C++ niche with a read-only safety note. It avoids fluff, over-claims, and first/second-person voice.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — 'deterministic linting (60+ rules)', 'six parallel deep-analysis agents covering model contracts, ownership, threading, API correctness, error handling, and performance' — with comprehensive coverage, matching the score-5 anchor.	5 / 5
Completeness	Explicitly answers both 'what' (linting plus six parallel analysis agents reporting high-confidence issues with mitigations, read-only) and 'when' ('Invoke when the user asks to review, check, audit, or look over Qt6 C++ code — or suggest before committing'), matching the score-5 anchor.	5 / 5
Trigger Term Quality	Comprehensive natural trigger terms including 'review', 'check', 'audit', 'look over', and the suggest-before-commit trigger, covering the synonyms a user would actually say, matching the score-5 anchor.	5 / 5
Distinctiveness Conflict Risk	Clear niche (Qt6 C++ code review) with distinct triggers and read-only constraint, giving minimal conflict risk with other skills, matching the score-5 anchor.	5 / 5
	Total	20 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning
referenced_paths_exist	Referenced path issues: 3 deeper-than-1-level	Warning

	Total	14 / 16 Passed

Repository: x-tools-author/x-tools
Path: .github/skills/qt-cpp-review/SKILL.md
Commit: ca34d5c

Reviewed: ~19 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.