Borrowing it
Nothing to install: this file belongs to srmorete/mobile-device-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/srmorete/mobile-device-mcp/main/.claude/skills/use-mobile-device/SKILL.mdgit clone --depth 1 https://github.com/srmorete/mobile-device-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/srmorete/mobile-device-mcp/use-mobile-device)<a href="https://agentmods.dev/skills/srmorete/mobile-device-mcp/use-mobile-device"><img src="https://agentmods.dev/badge/skills/srmorete/mobile-device-mcp/use-mobile-device.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.01054 |
| Opus 5 | $0.00028 | $0.00527 |
| Sonnet 5 | $0.00011 | $0.00211 |
| Haiku 4.5 | $0.00006 | $0.00105 |
Grade A, and why
use-mobile-device scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Using mobile devices
You have MCP tools for controlling iOS and Android devices. This skill covers how to use them effectively.
Interaction loop
- Call
list_devicesto get a validdevice_id. - Call
screenshotto see the current screen. - Call
uitreeto get elements with coordinates. Use thesearchparam to filter by text. - Act:
tap,type_text,scroll,press_button,long_press,double_tap, etc. Use the element'scenterfield as tap coordinates. - Call
screenshotto confirm the result.
Repeat 2-5 as needed.
Finding elements
uitree returns elements as JSONL. Each line is a JSON object with these fields (all always present):
| Field | Type | Description |
|---|---|---|
id |
number | Sequential integer starting from 1 |
text |
string | Element text (may be empty) |
type |
string | Semantic type: button, input, text, switch, image, etc. |
bounds |
object | {left, top, right, bottom} in screen coordinates |
center |
object | {x, y} — center of bounds, ready to use as tap coordinates |
visible |
boolean | Whether the element is within the screen bounds |
clickable |
boolean | Whether the element accepts taps |
- Use
searchto filter by text (case-insensitive substring match). - Use
limitto cap results when the tree is large. - If the target element is off-screen,
scrollto reveal it, then calluitreeagain. - Use
centercoordinates for tapping, not visual estimation from screenshots.
Coordinates
- Android: pixels.
- iOS: logical points (1x scale). Do not multiply by screen scale.
Text input
Tap the target text field first to focus it, then call type_text.
Scrolling
Scroll direction follows finger movement:
- Down (reveal content below):
startY > endY(finger moves up). - Up (reveal content above):
startY < endY(finger moves down). - Use mid-screen X and a Y delta of 300-500.
Buttons
press_button accepts these values: home, back, volumeUp, volumeDown, enter, dpadUp, dpadDown, dpadLeft, dpadRight, dpadCenter. iOS only supports home.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 8d ago First seen · 120 lines · 55 tokens per session scan A 8762d6634844
use-mobile-device is a skill published in the GitHub repository srmorete/mobile-device-mcp (45 stars, last pushed 1mo ago), licensed MIT. It adds 55 tokens to every session and 1,054 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Appium Mobile Testing
Mobile application testing skill using Appium for iOS and Android, covering device capabilities, selectors, gestures, and cross-platform testing strategies.
noqa-testing
Use this skill when the user wants to boot and interact with iOS or Android devices/simulators — inspect the screen, execute actions, generate or edit test cases, or run UI tests via the noqa platform.
ios-e2e-readiness
Use when iOS mobile E2E flows are flaky, SwiftUI and UIKit surfaces disagree with automation, mixed screens are ambiguous, retries hide the real issue, or the team keeps collapsing the problem to timing-only or SwiftUI-only without checking iOS-specific readiness contracts.
android-e2e-readiness
Use when Android mobile E2E flows are flaky, Compose and View screens disagree with automation, hybrid screens are ambiguous, retries hide the real issue, or the team keeps collapsing the problem to selector-vs-timing without checking Android-specific readiness contracts.
mobile-e2e-readiness-baseline
Use when mobile E2E flows are flaky across Android and iOS, visible screens are not reliably actionable, retries hide the real problem, or a team needs a platform-neutral readiness review before platform-specific guidance.
android-ui-journey-testing
XML-specified Android UI journey testing, interactive step execution, assertion verification, and JSON outcome reporting.