Agent skill

Maui AI Debugging

by Redth in Redth/Maui.Gtk

End-to-end workflow for building, deploying, inspecting, and debugging .NET MAUI and MAUI Blazor Hybrid apps as an AI agent.

MITAuto-check passedMobile

Install Maui AI Debugging

skills CLI
$ npx skills add Redth/Maui.Gtk --skill maui-ai-debugging -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install Redth/Maui.Gtk maui-ai-debugging --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/Redth/Maui.Gtk.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/maui-ai-debugging .claude/skills/maui-ai-debugging && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
maui-ai-debugging
GitHub stars
101
Token cost
~4.1k tokens
SKILL.md length
1,527 words
Files
8 (incl. references)
Skills in repo
1
Repo updated
First seen
Licence
MIT

At a glance

End-to-end workflow for building, deploying, inspecting, and debugging .NET MAUI and MAUI Blazor Hybrid apps as an AI agent.

  • Works in 6 steps: Ensure a Device/Simulator/Emulator is… → Detect the TFM → Build, Deploy, and Connect → …
  • Running a MAUI app on iOS simulator
  • SKILL.md covers Prerequisites, Integrating MauiDevFlow into a…, Core Workflow and Command Reference, plus 3 more sections
  • Calls dotnet, xcrun and adb

What it does

Maui AI Debugging is an agent skill from Redth/Maui.Gtk. End-to-end workflow for building, deploying, inspecting, and debugging .NET MAUI and MAUI Blazor Hybrid apps as an AI agent. Use when: (1) Building or running a MAUI app on iOS simulator, Android emulator, Mac Catalyst, macOS (AppKit), or Linux/GTK, (2) Inspecting or interacting with a running app's UI (visual tree, tapping, filling text, screenshots, property queries), (3) Debugging Blazor WebView content via CDP, (4) Managing simulators or emulators, (5) Setting up MauiDevFlow in a MAUI project, (6) Completing…

Its SKILL.md is about 4.1k tokens, which your agent loads only when the skill is triggered. The skill folder holds 8 other files, including reference files (for example `references/android.md`, `references/batch.md` and `references/ios-and-mac.md`).

It sits in Mobile, covering Cross-platform mobile apps, Mobile testing and debugging and Debugging. It works with macOS, Blazor, Linux and Android. The repository describes itself as: GTK based backend for .NET MAUI. The licence is MIT.

When your agent uses it

  • Running a MAUI app on iOS simulator
  • Android emulator
  • Interacting with a running apps UI (visual tree
  • Property queries)

Example prompts

  • “/maui-ai-debugging”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Ensure a Device/Simulator/Emulator is Running
  2. Detect the TFM
  3. Build, Deploy, and Connect
  4. Inspect and Interact
  5. Reading Application Logs
  6. Screen Recording

What it can do on your machine

Read from SKILL.md and the folder at commit c732514. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • dotnet
    • xcrun
    • adb

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Maui AI Debugging loads about 4.1k tokens when it runs, and up to ~16k if it reads all its reference files. Until then it costs about 217 tokens; SKILL.md has 1,527 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~217
When it runs · the whole SKILL.md, loaded when a task matches
~4.1k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~16k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from Redth/Maui.Gtk at commit c732514, republished under its MIT licence (© Redth). 1,527 words, ~4,076 tokens.

Download SKILL.mdSave it as .claude/skills/maui-ai-debugging/SKILL.md (or your agent's skills folder). This skill also uses 7 other files; get the full folder from GitHub.
name
maui-ai-debugging
description
End-to-end workflow for building, deploying, inspecting, and debugging .NET MAUI and MAUI Blazor Hybrid apps as an AI agent. Use when: (1) Building or running a MAUI app on iOS simulator, Android emulator, Mac Catalyst, macOS (AppKit), or Linux/GTK, (2) Inspecting or interacting with a running app's UI (visual tree, tapping, filling text, screenshots, property queries), (3) Debugging Blazor WebView content via CDP, (4) Managing simulators or emulators, (5) Setting up MauiDevFlow in a MAUI project, (6) Completing a build-deploy-inspect-fix feedback loop, (7) Handling permission dialogs and system alerts, (8) Managing multiple simultaneous apps via the broker daemon. Covers: maui-devflow CLI, androidsdk.tool, appledev.tools, adb, xcrun simctl, xdotool, and dotnet build/run for all MAUI target platforms including macOS (AppKit) and Linux/GTK.

MAUI AI Debugging

Build, deploy, inspect, and debug .NET MAUI apps from the terminal. This skill enables a complete feedback loop: build → deploy → inspect → fix → rebuild.

Prerequisites

bash
dotnet tool install --global Redth.MauiDevFlow.CLI || dotnet tool update --global Redth.MauiDevFlow.CLI
dotnet tool install --global androidsdk.tool    # Android only
dotnet tool install --global appledev.tools     # iOS/Mac only

Keep the skill up to date: maui-devflow update-skill. Check installed version vs remote with maui-devflow skill-version. For full update procedures, see references/setup.md.

Integrating MauiDevFlow into a MAUI App

For complete setup instructions, see references/setup.md.

Quick summary:

  1. Add NuGet packages (Redth.MauiDevFlow.Agent, and Redth.MauiDevFlow.Blazor for Blazor Hybrid)
    • For Linux/GTK apps (detected via grep -i 'GirCore\|Maui\.Gtk' *.csproj), use Agent.Gtk and Blazor.Gtk instead
    • For macOS (AppKit) apps (detected via grep -i 'Platform\.Maui\.MacOS' *.csproj), the standard Agent and Blazor packages include macOS support
  2. Register in MauiProgram.cs inside #if DEBUG
  3. For Blazor Hybrid: chobitsu.js is auto-injected (no manual script tag needed)
  4. For Mac Catalyst: ensure network.server entitlement
  5. For Android: run adb reverse for broker + agent ports
  6. For Linux: no special network setup needed (direct localhost)
  7. For macOS (AppKit): separate app head project, uses open App.app to launch. See references/macos.md

Core Workflow

1. Ensure a Device/Simulator/Emulator is Running

⚠️ Multi-project conflict avoidance: When multiple projects may run simultaneously (common with AI agents), each project should use its own dedicated simulator/emulator to prevent apps from replacing each other. Check what's already in use first:

bash
maui-devflow list                                             # see all registered agents

If another iOS or Android agent is already registered, create a new simulator/emulator for your project instead of reusing the one that's already booted.

iOS Simulator:

bash
xcrun simctl list devices booted                              # check booted sims

# Create a project-dedicated simulator to avoid conflicts
xcrun simctl create "MyApp-iPhone17Pro" "iPhone 17 Pro" "iOS 26.2"
xcrun simctl boot <UDID>                                      # boot the new sim

Android Emulator:

bash
android avd list                                              # list AVDs

# Create a project-dedicated emulator to avoid conflicts
android avd create --name "MyApp-Pixel8" \
  --sdk "system-images;android-35;google_apis;arm64-v8a" --device pixel_8
android avd start --name "MyApp-Pixel8"

Mac Catalyst / macOS (AppKit) / Linux/GTK: No device setup needed — runs as desktop app. Multiple desktop apps can run simultaneously without conflicts.

2. Detect the TFM

IMPORTANT: Before building, detect the correct Target Framework Moniker from the project. Do NOT assume net10.0 — many projects use net9.0, net8.0, etc.

bash
grep -i 'TargetFrameworks' *.csproj Directory.Build.props 2>/dev/null

Use the detected version (e.g. net9.0) in all build commands. The examples use $TFM.

3. Build, Deploy, and Connect

Follow these steps for every launch and rebuild.

Step 1: Kill any previous instance (skip on first launch). A stale app's agent stays registered with the broker, causing maui-devflow wait to return the old port instantly instead of waiting for the new build.

bash
# Stop the async shell from the previous launch, then confirm:
maui-devflow list                 # should show no agents (or only unrelated ones)

Step 2: Launch in an async shell.

bash
# iOS Simulator
dotnet build -f $TFM-ios -t:Run -p:_DeviceName=:v2:udid=<UDID>

# Android Emulator
dotnet build -f $TFM-android -t:Run

# Mac Catalyst
dotnet build -f $TFM-maccatalyst -t:Run

# macOS AppKit — build exits after compiling; launch separately
dotnet build -f $TFM-macos <path-to-macos-project>
open path/to/bin/Debug/$TFM-macos/osx-arm64/AppName.app

# Linux/GTK
dotnet run --project <path-to-gtk-project>

⚠️ Process lifecycle rules:

  • dotnet build -t:Run (iOS, Android, Mac Catalyst) and dotnet run (Linux/GTK) block for the lifetime of the app. Killing or stopping the shell kills the app. Use mode: "async" with initial_wait: 120 and do NOT stop the shell until you are done.
  • macOS (AppKit) is the exception: dotnet build exits after compiling, and open launches the app independently — the app survives shell termination.

Step 3: Wait for the agent — never use sleep.

bash
maui-devflow wait                                # blocks until agent registers (default 120s)
maui-devflow wait --project path/to/App.csproj   # filter to specific project

maui-devflow wait prints the assigned port as soon as the agent connects. Exit code 1 means timeout — check async shell output for build errors.

Android only — set up port forwarding after the agent connects:

bash
adb reverse tcp:19223 tcp:19223   # Broker (lets agent in emulator reach host broker)
adb forward tcp:<port> tcp:<port> # Agent (lets CLI reach agent in emulator)

To rebuild: repeat from Step 1. See references/troubleshooting.md if the build fails.

4. Inspect and Interact

Typical inspection flow:

  1. maui-devflow MAUI tree — see the full visual tree with element IDs, types, text, bounds
  2. maui-devflow MAUI query --automationId "MyButton" — find specific elements
  3. maui-devflow MAUI element <id> — get full details (type, bounds, visibility, children)
  4. maui-devflow MAUI property <id> Text — read any property by name
  5. maui-devflow MAUI screenshot --output screen.png — visual verification

Property inspection is more reliable than screenshots for verifying exact runtime values:

bash
maui-devflow MAUI property <id> BackgroundColor    # verify dark mode colors
maui-devflow MAUI property <id> IsVisible          # check element visibility

Live editing (no rebuild needed):

bash
maui-devflow MAUI set-property <id> TextColor "Tomato"
maui-devflow MAUI set-property <id> FontSize "24"

Supports: string, bool, int, double, Color (named/hex), Thickness, enums. Changes persist until the app restarts — safe for experimentation.

Typical interaction flow:

  1. maui-devflow MAUI fill <entryId> "text" — type into Entry/Editor fields
  2. maui-devflow MAUI tap <buttonId> — tap buttons, checkboxes, list items
  3. maui-devflow MAUI clear <entryId> — clear text fields
  4. Take screenshot to verify result

Blazor WebView (if applicable):

  1. maui-devflow cdp snapshot — DOM tree as accessible text (best for AI)
  2. maui-devflow cdp Input fill "css-selector" "text" — fill inputs
  3. maui-devflow cdp Input dispatchClickEvent "css-selector" — click elements
  4. maui-devflow cdp Runtime evaluate "js-expression" — run JS

Live CSS/DOM editing in Blazor (no rebuild needed):

bash
maui-devflow cdp Runtime evaluate "document.querySelector('h1').style.color = 'tomato'"
maui-devflow cdp Runtime evaluate "document.documentElement.style.setProperty('--bg-color', '#1a1a2e')"
5. Reading Application Logs

MauiDevFlow automatically captures all ILogger output and WebView console.* calls to rotating log files, retrievable remotely:

bash
maui-devflow MAUI logs                   # fetch 100 most recent log entries
maui-devflow MAUI logs --limit 50        # fetch 50 entries
maui-devflow MAUI logs --source webview  # only WebView/Blazor console logs
maui-devflow MAUI logs --source native   # only native ILogger logs

Debugging workflow: Reproduce the issue → maui-devflow MAUI logs --limit 20 → check for errors. Add temporary ILogger calls for more detail, rebuild, reproduce, and fetch logs again.

6. Screen Recording

Capture video of the app while performing interactions. Recording is host-side (not in-app) using platform-native tools.

bash
# Start recording (default 30s timeout)
maui-devflow MAUI recording start --output demo.mp4

# Interact with the app
maui-devflow MAUI tap <buttonId>
maui-devflow MAUI navigate "//blazor"
maui-devflow MAUI fill <entryId> "Hello World"

# Stop and save
maui-devflow MAUI recording stop

Platform tools used automatically:

  • Android: adb screenrecord (max 180s, capped with warning)
  • iOS Simulator: xcrun simctl io recordVideo
  • Mac Catalyst / macOS (AppKit): screencapture -v (targets app window when possible)
  • Windows/Linux: ffmpeg (must be on PATH)

Options: --timeout <seconds> (default 30), --output <path> (default recording_<timestamp>.mp4). Only one recording at a time — stop before starting a new one.

Command Reference

maui-devflow MAUI (Native Agent)

Global options: --agent-host (default localhost), --agent-port (auto-discovered via broker), --platform.

These options work on any subcommand position: maui-devflow MAUI status --agent-port 10224 or maui-devflow --agent-port 10224 MAUI status — both are valid.

CommandDescription
MAUI statusAgent connection status, platform, app name
MAUI tree [--depth N]Visual tree (IDs, types, text, bounds). Depth 0=unlimited
MAUI query --type T --automationId A --text TFind elements (any/all filters)
MAUI tap <elementId>Tap an element
MAUI fill <elementId> <text>Fill text into Entry/Editor
MAUI clear <elementId>Clear text from element
MAUI screenshot [--output path.png]PNG screenshot
MAUI property <elementId> <prop>Read property (Text, IsVisible, FontSize, etc.)
MAUI set-property <elementId> <prop> <value>Set property (live editing — colors, text, sizes, etc.)
MAUI element <elementId>Full element JSON (type, bounds, children, etc.)
MAUI navigate <route>Shell navigation (e.g. //native, //blazor)
MAUI logs [--limit N] [--skip N] [--source S]Fetch application logs (newest first). Source: native, webview, or omit for all
MAUI recording start [--output path] [--timeout 30]Start screen recording. Default timeout 30s. Uses platform-native tools (adb screenrecord, xcrun simctl, screencapture, ffmpeg)
MAUI recording stopStop active recording and save the video file
MAUI recording statusCheck if a recording is currently in progress

Element IDs come from MAUI tree or MAUI query. AutomationId-based elements use their AutomationId directly. Others use generated hex IDs. When multiple elements share the same AutomationId, suffixes are appended: TodoCheckBox, TodoCheckBox_1, TodoCheckBox_2, etc.

Show full SKILL.md (512 more words)Show less
maui-devflow cdp (Blazor WebView CDP)

Global options: --agent-host (default localhost), --agent-port (auto-discovered via broker). CDP commands use the same agent port — all communication goes through a single port.

CommandDescription
cdp statusCDP connection status
cdp snapshotAccessible DOM text (best for AI agents)
cdp Browser getVersionBrowser/WebView version info
cdp Runtime evaluate <expr>Evaluate JavaScript
cdp DOM getDocumentFull DOM document
cdp DOM querySelector <sel>Find first matching element
cdp DOM querySelectorAll <sel>Find all matching elements
cdp DOM getOuterHTML <sel>Get outer HTML of element
cdp Page navigate <url>Navigate to URL
cdp Page reloadReload page
cdp Page captureScreenshotScreenshot as base64
cdp Input dispatchClickEvent <sel>Click element by CSS selector
cdp Input insertText <text>Insert text at focused element
cdp Input fill <selector> <text>Focus + fill text into element
maui-devflow Broker & Discovery

The broker is a background daemon that manages port assignments for all running agents. The CLI auto-starts the broker on first use — no manual setup needed.

CommandDescription
listShow all registered agents (ID, app, platform, TFM, port, uptime)
wait [--timeout 120] [--project path] [--wait-platform P] [--json]Wait for an agent to connect. Outputs the port (or JSON with --json). Useful after dotnet build -t:Run to block until the app is ready
broker statusBroker daemon status and connected agent count
broker startStart broker daemon (auto-started by CLI — rarely needed manually)
broker stopStop broker daemon
broker logShow broker log file
maui-devflow batch (Multi-Command Execution)

Execute multiple commands in one invocation via stdin. Returns JSONL responses. Use for multi-step interactions to avoid repeated port resolution.

bash
echo "MAUI fill textUsername user; MAUI fill textPassword pwd123; MAUI tap buttonLogin" | maui-devflow batch

For full options, JSONL format, and streaming details, see references/batch.md.

Platform Details

For detailed platform-specific setup, simulator/emulator management, and troubleshooting:

⚠️ Non-Disruptive Operation

CRITICAL: Never run commands that steal focus, move windows, simulate mouse/keyboard input, or otherwise disrupt the user's desktop. The user is likely working on the same computer.

Never use:

  • osascript to focus/activate windows, click UI elements, or send keystrokes
  • screencapture interactively (the MauiDevFlow screenshot command captures in-process instead)
  • xdotool focus/activate/key commands that affect the active window
  • Any command that moves the mouse cursor or simulates input at the OS level
  • open -a to bring apps to the foreground (use open only to launch, not to focus)

Instead: All inspection and interaction goes through maui-devflow CLI commands, which communicate with the in-app agent over HTTP — no foreground focus required. If you need something that would require OS-level control (e.g., dismissing a system dialog outside the app), ask the user to do it manually rather than attempting automation that would hijack their input.

Tips

  • Use maui-devflow batch for multi-step interactions — resolves port once, adds delays, returns structured JSONL. See references/batch.md.
  • Always use maui-devflow MAUI screenshot — captures in-process, app does NOT need foreground focus.
  • Use AutomationId on important MAUI controls for stable element references.
  • For Blazor Hybrid, cdp snapshot is the most AI-friendly way to read page state.
  • Port discovery, multi-project setup, and custom ports: see references/setup.md.

© Redth, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 7 other files (references) in .claude/skills/maui-ai-debugging of Redth/Maui.Gtk.

  • SKILL.md
  • references/android.md
  • references/batch.md
  • references/ios-and-mac.md
  • references/linux.md
  • references/macos.md
  • references/setup.md
  • references/troubleshooting.md

Open the folder on GitHubat commit c732514

Compare with similar skills

Maui AI Debugging next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Maui AI Debugging compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Maui AI Debugging this skillRedth/Maui.Gtk101—~4.1kAutomated safety check: PassMIT
Engine Whats Newflutter/flutter179k—~978Automated safety check: PassBSD-3-Clause
Apple Crash Log .NET Symbolicationdotnet/skills5.6k1 repos~2.4kAutomated safety check: PassMIT
flutter_soloud Setupalnitak/flutter_soloud424—~3.6kAutomated safety check: NotesMIT
Fkit SetupJoker-x-dev/FlutterKit127—~720Automated safety check: PassMIT
Maui Safe Areadotnet/skills5.6k1 repos~3.2kAutomated safety check: PassMIT

Similar skills

  • Engine Whats New

    flutter/flutter

    Generates the "what's new" release summary and diff file for changes in the Flutter engine (//engine/src/flutter) between two releases (e.g., 3.47 vs 3.44).

    179k GitHub stars~978 tokensUpdated today
    MobileAuto-check passed
  • Official

    Resolves .NET runtime frames in Apple .ips crash logs to function names, source files and line numbers using dSYM symbols, atos and the Microsoft symbol server.

    5.6k GitHub starsUsed in 1 repo~2.4k tokens
    MobileAuto-check passed
  • flutter_soloud Setup

    alnitak/flutter_soloud

    Walks through adding the flutter_soloud audio engine to a Flutter app, with per-platform setup, initialization, binary-size and logging options, and output device switching.

    424 GitHub stars~3.6k tokensUpdated yesterday
    MobileAuto-check: notes
  • Fkit Setup

    Joker-x-dev/FlutterKit

    将 FlutterKit 脚手架初始化为新的应用项目,统一修改应用显示名称、Dart 包名、Android Application ID、Apple Bundle ID、Linux/Windows 标识、Web 名称、运行时品牌文案、Logo、桌面图标和启动页。用户拉取模板后要求改名、改包名、替换品牌资源或完成首次项目配置时使用。

    127 GitHub stars~720 tokensUpdated 2 mo ago
    MobileAuto-check passed
  • Maui Safe Area

    dotnet/skills

    Official

    .NET MAUI safe area and edge-to-edge layout guidance for .NET 10+.

    5.6k GitHub starsUsed in 1 repo~3.2k tokens
    MobileAuto-check passed
  • Android Screenshots

    boardsesh/boardsesh

    Capture screenshots of the Boardsesh React Native app (packages/mobile/) running on an Android emulator, driven against Metro with a cached dev-client APK.

    163 GitHub stars~1.1k tokensUpdated today
    MobileAuto-check passed

Categories

Questions about Maui AI Debugging

What does Maui AI Debugging do?

End-to-end workflow for building, deploying, inspecting, and debugging .NET MAUI and MAUI Blazor Hybrid apps as an AI agent. Gtk.NET MAUI and MAUI Blazor Hybrid apps as an AI agent.

When should I use Maui AI Debugging?

Maui AI Debugging fits situations like: running a MAUI app on iOS simulator; android emulator; interacting with a running apps UI (visual tree; property queries).

How do I install Maui AI Debugging in Claude Code?

Run `npx skills add Redth/Maui.Gtk --skill maui-ai-debugging -a claude-code`. Or copy the skill folder (.claude/skills/maui-ai-debugging in Redth/Maui.Gtk) into .claude/skills/maui-ai-debugging in your project. Claude Code loads it when a task matches its description.

How do I install Maui AI Debugging in Codex?

Run `npx skills add Redth/Maui.Gtk --skill maui-ai-debugging -a codex`. Or copy the skill folder (.claude/skills/maui-ai-debugging in Redth/Maui.Gtk) into .agents/skills/maui-ai-debugging in your project. Codex loads it when a task matches its description.

Can I use Maui AI Debugging in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Redth/Maui.Gtk --skill maui-ai-debugging -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/maui-ai-debugging, .gemini/skills/maui-ai-debugging, .github/skills/maui-ai-debugging and .opencode/skills/maui-ai-debugging in your project.

What does Maui AI Debugging need to run?

Going by SKILL.md and its folder, Maui AI Debugging needs the command-line tools its instructions call (dotnet, xcrun and adb).

Does Maui AI Debugging access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Maui AI Debugging safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Maui AI Debugging use?

Maui AI Debugging is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Maui AI Debugging use?

About 4.1k tokens (SKILL.md is roughly 16k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 12k tokens, read only when the agent opens those files.

What are the alternatives to Maui AI Debugging?

Skills that share tags, products or a category with Maui AI Debugging: Engine Whats New (flutter/flutter, 179k stars), Apple Crash Log .NET Symbolication (dotnet/skills, 5.6k stars), flutter_soloud Setup (alnitak/flutter_soloud, 424 stars) and Fkit Setup (Joker-x-dev/FlutterKit, 127 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Maui AI Debugging?

Redth (a GitHub user) maintains it in Redth/Maui.Gtk, which has 101 GitHub stars. The repository was last updated on April 16, 2026.

Source: Redth/Maui.Gtk on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.