mcpbeat

Quality Engineering Appium MCP

hoangnguyen0403/agent-skills-standard-quality-engineering-appium-mcp

Drives iOS/Android mobile devices via Appium MCP. Use for verifying mobile bugs, E2E tests, and navigating real device clouds (LambdaTest/BrowserStack).

This is a copy. The original lives at hoangnguyen0403/quality-engineering-appium-mcp.

3k tokens
context cost
the whole folder, loaded on every use
4
files
instructions only
0
copies elsewhere
how many repositories repackaged it
536
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/HoangNguyen0403/agent-skills-standard --skill quality-engineering-appium-mcp

What comes with it

8 078 bytes besides the instruction
references/lambdatest-cloud-setup.md
references/project-context.md
references/tool-cheatsheet.md

The instruction itself

8 sections, as written by the author

📱 Appium MCP (Mobile Automation)

Priority: P1 (HIGH)

> [!IMPORTANT]

> Tier 0 (Infrastructure): Session creation, device farm connectivity, basic OS interactions.

> Tier 1 (Core Gestures): Taps, swipes, text input for native mobile elements.

> Tier 2 (Flutter/Single-Canvas): Visual-first automation via screenshot + coordinate taps.

🔌 Activation

Triggers: appium, mobile verify, android verify, ios verify, lambdatest, real device cloud, flutter widget tap.

🛠 Core Workflow (Goal-Oriented)

| Step | Tool | Purpose |

| :--- | :--- | :--- |

| 1 | appium_session_management (create) | Open session. Resiliency: Retry with noReset: true on failure. |

| 2 | appium_get_window_size | Scale coordinates for high-density displays. |

| 3 | appium_screenshot | Capture visual state for Semantic Reasoning. |

| 4 | appium_gesture / appium_set_value | Interact. Self-Healing: Re-scan hierarchy if UUID stale. |

| 5 | appium_session_management (delete) | MANDATORY Cleanup. |

💡 AI-Driven Methodologies

  • Semantic Intent: Find element in hierarchy (e.g., "Login button") instead of raw coordinates. Resilient to layout shifts.
  • Dynamic Handling: Unexpected pop-up appears? Pause, reason about alert, dismiss, resume.
  • Visual Anchors: Find stable "Anchor" (e.g., Header) and derive coordinates relative to it.

🚫 Anti-Patterns (Zero-Tolerance)

  • Hardcoded XPaths: Use accessibility id or uiautomator. XPath flaky.
  • Implicit Wait-Only: Never assume page loaded. Poll for "Source of Truth" element.
  • Ignoring QoS: Audit CPU/Memory via appium_mobile_performance_data. Prevent lag/crashes.
  • Orphaned Sessions: Teardown mandatory. Call delete in cleanup block.

✅ Evaluation Criteria

  • Cleanup Rate: 100% session closure.
  • Visual Accuracy: Coordinate-based taps land within 5% of target center.
  • Security: No secrets in tool arguments or logs.

🔗 References

  • Visual Testing: common-mobile-visual-testing — Methodology for what to verify.
  • LambdaTest Setup: lambdatest-cloud-setup — RDC configuration.
  • Tool Cheatsheet: tool-cheatsheet — Fast copy-paste args.
  • Project Context: project-context — Project-specific overlays/macros.

How to use it

Copy the folder

Take hoangnguyen0403/agent-skills-standard-quality-engineering-appium-mcp from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.