SKILLEMALL.ai
GitHub ↗ RU Sign in

AB android-device-automation

Vision-driven Android device automation using Midscene. Operates entirely from screenshots — no DOM or accessibility labels required. Can interact with all visible elements on screen regardless of technology stack. Control Android devices with natural language commands via ADB. Perform taps, swipes, text input, app launches, screenshots, and more. Trigger keywords: android, phone, mobile app, tap, swipe, install app, open app on phone, android device, mobile automation, adb, launch app, mobile screen, test android app, verify mobile app, QA on phone, check the app on android, test on device, see if the app works on phone, end-to-end test on android, visual verification on mobile Powered by Midscene.js (https://midscenejs.com)

ClawHub Agent Skills author: Leyang v1.0.3 MIT-0 2 files body ≈ 3 131 tokens Open the sourceclawhub.ai↗ analyzed 3 d ago

As a process B 66/100 · Nearly there — weak spots: result and completion, when it triggers, consistency

IntegrationInfrastructuretype 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
91/100
safety, quality, tests
Safety 60%
95
Quality 40%
84
Run on models
none yet
Process rating
B
66/100
Nearly there
Result and completion w 14
0
When it triggers w 12
20
Consistency w 8
40
the three weakest of ten parameters · all ten

What is at stake

Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

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 · 1

    ✓ No critical or high findings

    Medium and low: 1
    • medium Broad scope meta-broad-allowed-tools SKILL.md:1
      Broad tool permissions pre-approved: Bash
      allowed-tools: Bash

    Files scanned: 2. 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 66/100

    • 0Result and completion. Does not say what the result is
    • 20When it triggers. No condition that starts the skill
    • 40Consistency. Frontmatter name (android-device-automation) differs from the folder (midscene-android-automation)
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 13 steps, 1 vague phrases
    • 100Tools and files. Tools declared in frontmatter
    • 100Failures and branches. 4 branches, has a failure section
    • 100Execution cost. Instruction body is 3131 tokens
    • 100Running it twice. No mutating operations
    • 100Progress reporting. Reports progress
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low The response is described with custom markup (3 tags): a typed call is more reliable

    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 735: enough signal without eating the budget
    • +4Structure: 16 headings
    • +3Step-by-step instructions: 13 items
    • +4Has examples (15 code blocks)

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

    External checks

    ClawHub: suspicious
    This skill is purpose-aligned Android automation, but it gives an agent broad control over a connected device without enough scoping or confirmation guidance.
    LLM: suspicious (high) · VirusTotal: suspicious · 28 May 2026