Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote.
Qt AI skills and MCP plugin for coding tools
This repo packages Qt-specific skills for reviewing, testing, documenting, and designing QML and C++ work in agent tools. The skills live in `skills/` as `SKILL.md` directories, and the documentation MCP server in `mcp/qt-documentation-mcp/` gives agents Qt API lookup while they work.
Builders who want reusable Qt workflows in Claude Code, Codex, Copilot, or Gemini CLI.
You can give your agent Qt-specific rules, review flows, tests, docs generation, and API lookup instead of starting from scratch.
What it does
Qt code review skills
`qt-cpp-review` and `qt-qml-review` combine deterministic checks with parallel analysis for correctness, ownership, bindings, layout, and performance.
QML and C++ documentation generation
`qt-qml-docs` and `qt-cpp-docs` turn source files into Markdown reference docs for components, classes, modules, and entry points.
QML test creation and execution
`qt-qml-test` generates Qt Quick Test cases, and `qt-qml-test-run` builds, runs, and reports on them for CMake projects.
Figma to QML workflows
`qt-figma-token-extraction` and `qt-figma-component-generation` extract design tokens and generate QML controls from a Figma system.
Qt documentation MCP server
`mcp/qt-documentation-mcp/` provides hosted Qt API documentation lookup across release and LTS branches.
Tool-specific packaging
`.claude-plugin/`, `.mcp.json`, and `gemini-extension.json` package the skills for Claude Code, Copilot, and Gemini CLI.
How to get it
- 1Install as a plugin using the Claude Code CLI plugin system
/plugin marketplace add TheQtCompanyRnD/agent-skills /plugin install qt-development-skills
- 2Or install individual skills manually
# Symlink a skill into your personal skills directory ln -s "$(pwd)/skills/qt-qml-review" ~/.claude/skills/qt-qml-review # Or copy into a project for team use cp -r skills/qt-qml-review .claude/skills/qt-qml-review
- 3Use Vercel's cross-platform skill installer
npx skills add TheQtCompanyRnD/agent-skills
- 4Or copy skills manually
cp -r skills/qt-qml-review ~/.codex/skills/qt-qml-review
- 5Copilot natively reads the same SKILL.md directory format as Claude Code. Install…
gh skill install TheQtCompanyRnD/agent-skills qt-qml-review
- 6Or copy/symlink the skill into one of Copilot's discovery paths
# User-wide (available in any project) cp -r skills/qt-qml-review ~/.copilot/skills/qt-qml-review # Or scoped to a specific project cp -r skills/qt-qml-review .github/skills/qt-qml-review
README
Qt AI Skills
Official agentic skills for Qt software development and quality assurance, designed for use with AI coding tools such as Claude Code, Codex CLI, Gemini CLI, and GitHub Copilot.
Skills have been tested with frontier LLMs from the Claude, Gemini, and GPT model families.
There is no settled industry standard for AI skill packaging.
Each platform has its own conventions. Our canonical format
uses SKILL.md with YAML frontmatter in a directory-based
structure — this works natively on Claude Code, Codex CLI,
and GitHub Copilot, and can be adapted to other platforms
through condensed variants. See CONTRIBUTING.md
for the full cross-platform story.
These agentic development skills use AI and can make mistakes. Always double-check the output carefully.
Before using the skills under Qt commercial licensing, make sure you have understood and agree to the Qt AI Services Terms & Conditions. By using the skills or MCP tools, you accept these terms & conditions and that you have the right to do so on behalf of your employer.
Skills
| Skill | Type | Description |
|---|---|---|
qt-cpp-review | Review | Deterministic linting + 6 parallel deep-analysis agents for Qt C++ code. Covers model rule compliance, memory ownership, thread safety, correctness, error handling, and performance. |
qt-qml-review | Review | Deterministic QML linting (47+ rules) + parallel deep-analysis agents for bindings, layout, loaders, delegates, states, and performance. |
qt-qml | Conceptual | QML best practices for writing, reviewing, fixing, and refactoring. Corrects systematic LLM pre-training biases around bindings, scoping, modules, JS interop, and types. |
qt-ui-design | Conceptual | UI design and audit for Qt/QML, web, and embedded (MPU/MCU) targets. Covers screen layout, navigation, and UX review with platform-aware defaults for geometry, viewing distance, input, and locale. |
qt-qml-docs | Process | Generates Markdown reference documentation for QML components and applications from .qml source files. |
qt-cpp-docs | Process | Generates Markdown reference documentation for Qt/C++ source files — classes, modules, utilities, headers, and entry points. |
qt-qml-profiler | Tool | Runs qmlprofiler on a 2D QML / Qt Quick application, parses the .qtd trace, and analyzes hotspots against the source code with frame-time, memory, and pixmap-cache summaries. Does not cover Qt Quick 3D. |
qt-qml-test | Process | Generates Qt Quick Test cases (tst_*.qml) for QML components using TestCase, SignalSpy, and tryCompare. Handles single files and batches. Does not cover CMake or runner setup. |
qt-qml-test-run | Tool | Builds and runs Qt Quick Test (qmltestrunner) tests for a CMake project, parses the JUnit XML, and writes a Markdown report. Opt-in CMake test-infrastructure wiring with --wire-up. Companion to qt-qml-test. |
qt-figma-token-extraction | Process | Extracts design tokens, text styles, and variables from a Figma design system and produces a design-tokens.json plus ready-to-use QML singletons. |
qt-figma-component-generation | Process | Extracts component metadata from a Figma design system and generates production-ready QML controls mapped to Qt Quick Controls 2 patterns. Requires tokens from qt-figma-token-extraction. |
qt-cmake-project | Conceptual | Sets up and manages Qt 6 projects built with CMake — fresh projects, executables, libraries, QML modules, plugins, folder layout, and static resources. Corrects systematic LLM biases around qmake-isms and the legacy qt5_* macros. |
Skill types
- Review — structured code review workflows combining deterministic linters with deep AI analysis
- Process — workflows and decision frameworks (architecture, build, test, documentation)
- Conceptual — mental model corrections for areas where LLMs consistently fail (declarative QML, C++/QML boundary, Widgets patterns, UI design)
- Tool — guidance on Qt CLI tools and testing solutions
MCP Tools
| Tool | Description |
|---|---|
qt-documentation-mcp | Hosted MCP server for Qt API documentation lookup across the latest release and active LTS branches. Bundled with the qt-development-skills plugin; also available standalone via the official MCP registry as io.qt/qt-documentation-mcp. |
Qt Documentation MCP Tool
See mcp/qt-documentation-mcp/README.md
for endpoint and manual setup instructions for AI clients other than
Claude Code.
Repository Structure
skills/ # All skills live here
qt-cpp-review/ # Each skill is a directory
SKILL.md # with a SKILL.md entry point
references/ # and optional reference docs
lint-scripts/
qt-review-checklist.md
platforms/ # Platform-specific variants
qt-qml-review/
qt-qml/
qt-ui-design/
qt-qml-docs/
qt-cpp-docs/
qt-qml-profiler/
qt-qml-test/
qt-qml-test-run/
qt-cmake-project/
mcp/ # MCP servers bundled with the plugin
qt-documentation-mcp/ # Each server is a directory
README.md # with its own README
.mcp.json # MCP registration for Claude Code
.claude-plugin/ # Claude Code CLI & Copilot CLI plugin config
gemini-extension.json # Gemini CLI extension manifest
docs/ # Source for the docs site (MkDocs)
CONTRIBUTING.md
LICENSE
README.md
Skill Format
Every skill is a directory containing a SKILL.md file with
YAML frontmatter. This format aligns with what Claude Code and
Codex CLI support natively:
---
name: qt-qml-review
description: >-
Reviews QML source files for correctness, performance, and
maintainability. Deterministic linting (47+ rules) plus
parallel deep-analysis agents for bindings, layout, loaders,
delegates, states, and performance.
license: LicenseRef-Qt-Commercial OR BSD-3-Clause
compatibility: >-
Designed for Claude Code, GitHub Copilot, and similar agents.
metadata:
author: qt-ai-skills
version: "1.0"
qt-version: "6.x"
---
Key conventions
namemust be lowercase alphanumeric + hyphens, max 64 chars, and must match the directory namedescriptionmust describe what the skill does AND when to use it — front-load the key information in the first 250 characters, as some platforms truncate beyond that point- SKILL.md body should stay under 500 lines — move detailed
content to
references/files - Progressive disclosure: agents load only
name/descriptionat startup, readSKILL.mdbody on activation, and pullreferences/files only when needed
Multi-Tool Support
Skills are authored to be tool-agnostic wherever possible. However, different AI coding tools consume skills in different ways:
| Tool | Skill Location | Format | Notes |
|---|---|---|---|
| Claude Code CLI | ~/.claude/skills/ | SKILL.md + references (native) | Full directory model with progressive loading |
| Codex CLI | ~/.codex/skills/ | SKILL.md + references (native) | Full directory model; registered in ~/.codex/config.toml |
| Gemini CLI | Extension skills/ | SKILL.md + references (native) | Installed via gemini extensions install; @file.md imports |
| GitHub Copilot | .github/skills/ or .claude/skills/ (project), ~/.copilot/skills/ (personal) | SKILL.md + references (native) | Auto-discovered across Copilot CLI, coding agent, and VS Code; existing .claude/skills/ setups Just Work |
When platform-specific variants are needed
Most skills work across tools without changes. When a skill
needs to reach platforms that cannot read multi-file directories
(e.g. Windsurf, Amazon Q), create variants in a platforms/
directory:
skills/qt-qml-review/
├── SKILL.md # Core skill (tool-agnostic)
├── references/
│ ├── qml-lint-rules.md
│ └── qml-review-checklist.md
└── platforms/ # Platform-specific variants
└── windsurf.md # Self-contained compact variant
The platforms/ directory is a convention for this repository.
See CONTRIBUTING.md for full details on
creating platform variants.
Installation
Most AI coding tools can install skills directly from this GitHub repository. Choose the method for your platform below.
Claude Code CLI
Install as a plugin using the Claude Code CLI plugin system:
/plugin marketplace add TheQtCompanyRnD/agent-skills
/plugin install qt-development-skills
Or install individual skills manually:
# Symlink a skill into your personal skills directory
ln -s "$(pwd)/skills/qt-qml-review" ~/.claude/skills/qt-qml-review
# Or copy into a project for team use
cp -r skills/qt-qml-review .claude/skills/qt-qml-review
Claude Code auto-discovers skills — no restart needed.
Codex CLI
Use Vercel's cross-platform skill installer:
npx skills add TheQtCompanyRnD/agent-skills
Or copy skills manually:
cp -r skills/qt-qml-review ~/.codex/skills/qt-qml-review
Restart Codex after adding skills.
Note: Codex is evolving rapidly. If
~/.codex/skills/does not work, try~/.agents/skills/or.agents/skills/in your project root.
GitHub Copilot CLI
Copilot natively reads the same SKILL.md directory format as
Claude Code. Install individual skills using GitHub CLI (preview):
gh skill install TheQtCompanyRnD/agent-skills qt-qml-review
Or copy/symlink the skill into one of Copilot's discovery paths:
# User-wide (available in any project)
cp -r skills/qt-qml-review ~/.copilot/skills/qt-qml-review
# Or scoped to a specific project
cp -r skills/qt-qml-review .github/skills/qt-qml-review
Copilot also auto-discovers skills installed for Claude Code
under .claude/skills/, so a single install can serve both
tools. Use /skills list inside Copilot CLI to confirm what
loaded.
VSCode Agents (Copilot and others)
Run Chat: Install Plugin From Source from the Command Palette.
Enter https://github.com/TheQtCompanyRnD/agent-skills (this repo) to clone and install
Gemini CLI
Install as an extension:
gemini extensions install https://github.com/TheQtCompanyRnD/agent-skills
Or import skills into your project's context file:
# Add to GEMINI.md (loaded automatically)
echo '@skills/qt-qml-review/SKILL.md' >> GEMINI.md
Documentation site
A browsable documentation site is built from the docs/ directory
using MkDocs Material
and published at:
The canonical repo is on Gerrit
(codereview.qt-project.org/qtai/qtaiskills); doc.qt.io builds are
driven by the qtaiskills Rundeck job in tqtc-doctools on each
push to the publishing branch.
Local preview
Requires Python 3.12+:
pip install -r requirements-docs.txt
mkdocs serve
Then open http://127.0.0.1:8000/agent-skills/ — the dev server live-reloads on every save.
Production build
mkdocs build --strict
Output goes to site/. --strict fails on broken links and
malformed nav, matching the GitHub Actions check.
Adding a new skill page
- Create
docs/skills/<skill-name>.md(use an existing skill page as a template). - Add it to
nav:inmkdocs.yml. - Add a row to the table in
docs/skills/index.md. - Run
mkdocs serveto verify.
Contributing
See CONTRIBUTING.md for guidelines on authoring new skills, including:
- Naming conventions and frontmatter requirements
- How to structure progressive disclosure
- Testing skills across AI coding tools
- When and how to create platform-specific variants
License
BSD-3-Clause — see LICENSE for details.
Files in the repo
- .claude-plugin
- docs
- mcp
- overrides
- skills
- tests
- tools
- .gitignore
- .mcp.json
- CONTRIBUTING.md
- gemini-extension.json
- gen_skills.py
- LICENSE
- mkdocs.yml
- README.md
- requirements-docs.txt
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More plugins

Graphs that teach > graphs that impress. Turn any code into an interactive knowledge graph you can explore, search, and ask questions about. Works with Claude Code, Codex, Cursor, Copilot, Gemini CLI, and more.
OmO: Just type "mass ulw" keyword with your prompt. Now you are the master of graph engineering.
Persistent Context Across Sessions for Every Agent – Captures everything your agent does during sessions, compresses it with AI, and injects relevant context back into future sessions. Works with Claude Code, OpenClaw, Codex, Gemini, Hermes, Copilot, OpenCode + More
Opinionated Oxlint rules for rejecting low-evidence TypeScript and JavaScript patterns
Teams-first Multi-agent orchestration for Claude Code