SKILLEMALL.ai
GitHub ↗ RU Sign in

AB maestro-mobile-test

Write and run E2E tests for React Native / Expo apps using Maestro CLI — the open-source tool that drives the **real native app** on an Android emulator or iOS simulator, not a web build. Covers what browser-based e2e (Playwright, Expect, e2e-verify) cannot reach: native components, biometrics, secure storage, push notifications, platform-specific modules. Write YAML flows, run headed for authoring or headless for CI. Scripts currently automate the Android workflow end-to-end (Java + SDK detection, emulator boot, adb reverse); iOS simulator setup requires Xcode + `xcrun simctl` and is documented but not automated by the setup script. Use this skill whenever the user says "test my react native app", "e2e test the mobile app", "write maestro tests", "test the expo app", "automate emulator testing", or "/maestro-mobile-test" — even if they don't name the skill. Not for web apps (e2e-verify), unit/component tests (write-tests with RNTL + Jest), or API contract tests.

ClawHub Agent Skills author: Dennis Rongo v1.0.1 MIT-0 5 files · 2 scripts body ≈ 3 413 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Write and run E2E tests for React Native / Expo apps using Maestro CLI — the open-source tool that drives the real native app on an Android emulator or iOS…

As a process B 68/100 · Nearly there — weak spots: result and completion, running it twice, progress reporting

GeneratorPlaywrightGitHubSoftware developmenttype 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
92/100
safety, quality, tests
Safety 60%
93
Quality 40%
91
Run on models
none yet
Process rating
B
68/100
Nearly there
Result and completion w 14
0
Progress reporting w 2
0
Running it twice w 4
30
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.

Dangerous commands 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 contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

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 · 3

    ✓ No critical or high findings

    Medium and low: 3
    • medium Dangerous commands cmd-pipe-to-shell scripts/setup.sh:154
      Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)
      curl -Ls "https://get.maestro.mobile.dev" | bash
      vendor-host
    • low Dangerous commands cmd-pipe-to-shell SKILL.md:28
      Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row; documentation of a security skill; the skill's own vendor host)
      | Maestro CLI | `maestro --version` | `curl -Ls https://get.maestro.mobile.dev \| bash` — or run `scripts/setup.sh` |
      tablesecurity skillvendor-host
    • low Dangerous commands cmd-pipe-to-shell SKILL.md:272
      Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill; the skill's own vendor host)
      curl -Ls "https://get.maestro.mobile.dev" | bash
      security skillvendor-host

    Files scanned: 5. 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 68/100

    • 0Result and completion. Does not say what the result is
    • 0Progress reporting. Says nothing while it works
    • 30Running it twice. 9 mutating operations with no state check
    • 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
    • 70Inputs and preconditions. Inputs and preconditions are listed
    • 85Steps. 30 steps, 1 vague phrases
    • 100When it triggers. States when to use and when not to
    • 100Failures and branches. 1 branches, has a failure section
    • 100Consistency. Name and required fields are in place
    • 100Execution cost. Instruction body is 3413 tokens
    • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
    • low 12 top-level sections: this looks like several domains in one skill

    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

    • +3Description length 977: 120–800 characters recommended
    • +3Output format is not stated: the model decides each time
    • -214 emoji in the instructions: noise for the model
    • +1No license
    • +2Single-language instructions
    • +5Description quotes 6 example trigger phrases
    • +4Description says when NOT to use the skill
    • +4Structure: 24 headings
    • +3Step-by-step instructions: 30 items
    • +4Has examples (13 code blocks)
    • +3All 2 scripts are documented

    Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.

    External checks

    ClawHub: suspicious
    This is a coherent mobile testing skill, but its setup path can run unverified internet-downloaded shell code and install system packages on a developer machine.
    LLM: suspicious (high) · 28 Aug 2026