Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add vasilyu1983/AI-Agents-public --skill qa-testing-androidgit clone --depth 1 https://github.com/vasilyu1983/AI-Agents-publicWrote 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/vasilyu1983/ai-agents-public/qa-testing-android)<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/qa-testing-android"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/qa-testing-android/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/vasilyu1983/ai-agents-public/qa-testing-android"><img src="https://agentmods.dev/badge/skills/vasilyu1983/ai-agents-public/qa-testing-android.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 157 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 | $0.00037 | $0.05705 |
| Opus 5 | $0.00018 | $0.02853 |
| Sonnet 5 | $0.00007 | $0.01141 |
| Haiku 4.5 | $0.00004 | $0.00571 |
Grade A, and why
qa-testing-android 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 6d 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 — 349 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QA Testing (Android)
Android testing automation with Espresso, UI Automator, Compose Testing, screenshot tests, and adaptive UI validation.
Core References: Android Testing Docs, Build-Managed Devices, Compose Testing, UI Automator, Screenshot Testing, Accessibility Checking
Quick Reference
| Task | Command |
|---|---|
| List emulators | emulator -list-avds |
| Start emulator | emulator @<avd_name> |
| List devices | adb devices |
| Install APK | adb install -r <path-to-apk> |
| Run unit tests | ./gradlew test |
| Run instrumented tests (connected) | ./gradlew connectedAndroidTest |
| Run instrumented tests (GMD) | ./gradlew <device><variant>AndroidTest |
| Run screenshot tests | ./gradlew validateDebugScreenshotTest |
| List GMD tasks | `./gradlew tasks --all |
| Clear app data | adb shell pm clear <applicationId> |
Platform Versions (July 2026)
| Component | Current stable | Notes |
|---|---|---|
| Android | 17 (API 37), shipped 2026-06-16; Android 16 (API 36) is the prior release | See "Google Play Target API Policy" below for what to actually target — the newest OS version is not automatically the target-API requirement |
| AGP | 9.2.x | Requires Gradle 8.11+; breaking DSL changes from 8.x |
| Robolectric | 4.16.x | Supports up to SDK 36 (Baklava); SDK 36 requires JDK 21. API 37 support is not yet released as of 2026-07-11 — an open upstream issue (robolectric/robolectric#11239, filed 2026-06-14) tracks it. Do not assume Robolectric can simulate Android 17 behavior yet; verify before relying on it for API-37-specific logic |
| UI Automator | 2.4.0-rc01 | Modern uiAutomator {} DSL; release-candidate, not yet fully stable — verify current status before pinning in a template |
| Compose Preview Screenshot Testing | 0.0.1-alpha15 | Still alpha; requires AGP 8.5+, Kotlin 2.2.10+ (raised from 1.9.20 — verify against the current release notes before relying on an older Kotlin floor), JDK 17+ |
| ATD images | API 30 only | Use standard google/aosp images for API 35/36/37 |
| Maestro | API 35/36 added 2026 Q2 | API 37 support unverified as of 2026-07-11 — check release notes before targeting Android 17 devices in Maestro Cloud |
What ships with it
15 files 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.
- agents/openai.yaml 338 B
- assets/template-android-test-checklist.md 3.4 KB
- data/sources.json 9.7 KB
- learnings.consolidated.md 594 B
- learnings.md 370 B
- references/accessibility-checks.md 2.0 KB
- references/adaptive-screen-testing.md 2.8 KB
- references/android-ci-optimization.md 8.3 KB
- references/compose-testing.md 16 KB
- references/espresso-patterns.md 17 KB
- references/gradle-managed-devices.md 7.2 KB
- references/modern-test-tooling.md 10 KB
- references/screenshot-testing.md 8.4 KB
- references/test-orchestrator-patterns.md 16 KB
- references/uiautomator.md 5.9 KB
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.
- 6d ago First seen · 349 lines · 37 tokens per session scan A 81f81d150f96
qa-testing-android is a skill published in the GitHub repository vasilyu1983/AI-Agents-public (87 stars, last pushed 7d ago), licensed MIT. It adds 37 tokens to every session and 5,705 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
e2e-testing-patterns
Master end-to-end testing with Playwright and Cypress to build reliable test suites that catch bugs, improve confidence, and enable fast deployment. Use when implementing E2E tests, debugging flaky tests, or establishing testing standards.
android-emulator
Verify and debug native, React Native, Expo, or Flutter apps on an Android Emulator with agent-device. Use when an agent needs to launch an app, inspect its live UI, tap, type, scroll, validate a code change, collect failure evidence, or reproduce a workflow on an Android virtual device.
dogfood
Systematically explore and test a mobile app on iOS/Android with agent-device to find bugs, UX issues, and other problems. Use when asked to dogfood, QA, exploratory test, find issues, bug hunt, or test this app on mobile.
voyager
Authoring web and native E2E tests, including Playwright, Appium, XCUITest, device farms, visual regression, and App Store screenshot pipelines. Not for unit/load tests.
mobile-testing-detox
Detox E2E gray-box testing for React Native - matchers, actions, expectations, waitFor, device API, synchronization, mocking, artifacts, CI integration.