SKILLEMALL.ai
RU Sign in

AB mobilerun

Control real Android phones through the Mobilerun API. Supports tapping, swiping, typing, taking screenshots, reading the UI accessibility tree, and managing apps. Use when the user wants to automate or remotely control an Android device, interact with mobile apps, or run AI agent tasks on a phone. Requires a Mobilerun API key (prefixed dr_sk_) and a connected device (personal phone via Portal APK or cloud device).

ClawHub Agent Skills author: johnmalek312 v1.0.1 MIT-0 6 files body ≈ 1 663 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

As a process B 69/100 · Nearly there — weak spots: result and completion, consistency, running it twice

IntegrationInfrastructureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
A
94/100
safety, quality, tests
Safety 60%
100
Quality 40%
84
Run on models
none yet
Process rating
B
69/100
Nearly there
Result and completion w 14
0
Running it twice w 4
30
Consistency w 8
40
the three weakest of ten parameters · all ten

The same skill appears in 1 more place: ClawHub

How to improve

    For the model run — optional
    • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
    • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

    Guard findings · 0

    ✓ No critical or high findings

    Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.

    Against the Agent Skills spec

    ✓ No remarks against the Agent Skills spec

    Process rating: all ten parameters 69/100

    • 0Result and completion. Does not say what the result is
    • 30Running it twice. 1 mutating operations with no state check
    • 40Consistency. Frontmatter name (mobilerun) differs from the folder (mobile-run)
    • 70When it triggers. States when to use, but not when not to
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 25 steps, 1 vague phrases
    • 100Tools and files. No external tools needed
    • 100Failures and branches. 4 branches, has a failure section
    • 100Execution cost. Instruction body is 1663 tokens
    • 100Progress reporting. Reports progress

    Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

    Quality signals

    • +5Description has no quoted example phrases that should trigger the skill
    • +4Description does not say when NOT to use the skill (false activations)
    • +3Output format is not stated: the model decides each time
    • +1No license
    • +2Single-language instructions
    • +3Description length 418: enough signal without eating the budget
    • +4Structure: 7 headings
    • +3Step-by-step instructions: 25 items
    • +4Has examples (2 code blocks)

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 84.

    External checks

    ClawHub: suspicious
    Mobilerun clearly does what it says, but it gives an agent broad control over a real Android phone with some sensitive actions not guarded strongly enough.
    LLM: suspicious (high) · VirusTotal: · 29 May 2026