Debug Kit — Testing skill for Claude Code
🧩 Agent Skill: drive, inspect & test apps across 9 platforms (macOS/iOS/Android/Web/Electron/Flutter/RN/Tauri/Chrome-ext) — background, no cursor hijack, with a virtual pointer.
How to install Debug Kit
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open dxiongya/debug-kit and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Debug Kit does
🧩 Agent Skill: drive, inspect & test apps across 9 platforms (macOS/iOS/Android/Web/Electron/Flutter/RN/Tauri/Chrome-ext) — background, no cursor hijack, with a virtual pointer. Install: npx skills add dxiongya/debug-kit
Alternatives in Testing
- Debug — You are tasked with helping debug issues during manual testing or implementation 10k ★
- Skill Debug — Debug issues methodically — use when stuck on errors, test failures, or unexpected behavior 2.8k ★
- Ext Apps — Official repo for spec & SDK of MCP Apps protocol - standard for UIs embedded AI chatbots, served by MCP serve 1.9k ★
README
🧩 debug-kit
An Agent Skill for Claude Code (and Cursor · Codex · Cline · Gemini CLI …)
Install it once and your AI gains hands & eyes to drive, inspect, and test real apps across 9 platforms —
in the background, without ever touching your real cursor, with a virtual pointer you can watch.
npx skills add dxiongya/debug-kit # ← one-line install (it's a skill, not a library)
[!NOTE] **This is an _Agent Skill_, not an app or a library.** You don't run or `import` it — you **install** it into your AI coding agent. After that, the agent automatically uses it whenever you say things like *"run the app", "tap the button", "take a screenshot", "test this"*. Under the hood it's a `SKILL.md` manifest plus the scripts the agent calls. Manage it with [skills.sh](https://skills.sh).
English
**debug-kit** gives an AI agent — like [Claude Code](https://cla
Related Skills
AppReveal
Debug-only in-app MCP server for iOS/macOS/Android/Flutter/ReactNative. Gives LLM agents Playwright-like contr
Apple Testing
XCTest and UI testing for Apple platforms
Desktop E2e
Run DOM-driven E2E scenario(s) against the bundled Maude desktop app (Tauri + WebdriverIO). Builds the test ap
Claude Codex Handoff
A Claude Code skill that orchestrates a three-phase planner→implementer→reviewer workflow between Claude Code
Walkthrough Video
Record a narrated product walkthrough video of a website, web app, or Electron desktop app — a Claude Code ski
Publish Speckit Ext
Release the spec-kit extension (companion) to a GitHub release for catalog/--from install
Related Agents
Desktop Agent
Worker agent for desktop application security testing — Electron / Tauri / WebView2 binary inspection + IPC fu
Ehs Local App
Local application security specialist for the Ethical Hacker Squad. Reviews command-line tools, desktop applic
UI Explorer
Drive and explore a native macOS app's GUI (screenshot → click/type → observe) and correlate each action with