mobile-qa
Skill0 starsChanged 4 months agoMITView on GitHub
Routes selected-device mobile QA to a compatible original native testing skill with owner device and evidence policy.
We split this skill into the rules it gives an agent
8 rules. About 0 are common, 7 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
Distinctive · estimate
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 8
Use for native Android/iOS behavior.
- Distinctive: line 29
Do not select a physical device implicitly, reset user data, change accounts, install profiles, or operate unrelated apps.
- Distinctive: line 35
Before activating a third-party server, verify its pinned source, advisory fixes, telemetry controls and actual action surface.
- Distinctive: line 39
Check each batch subcommand against the same allowed operations and target.
- Distinctive: line 48
Stop only emulator/server processes created for this task.
- Distinctive: line 51
Use synthetic photos, input text and provider errors.
- Distinctive: line 53
Keep screenshots, logs, device identifiers and MCP configuration outside public repositories.
- Distinctive: line 57
Verify keyboard/input, gallery/permission, and provider-error recovery flows on their actual app builds before claiming project acceptance.
≈ “Common” is an estimate: at least 1 in 5 of the 308,232 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Native Mobile QA
Use for native Android/iOS behavior. Mobile web layouts belong to
responsive-breakpoint-check; browser flows belong to playwright-visual-qa.
Load and follow the complete original native testing skill that covers the
selected platform and target. For Android emulator feature flows, the exposed
provider is test-android-apps:android-emulator-qa; performance investigations
use test-android-apps:android-performance. Keep the native plugin's original
instructions, scripts and update path intact. This adapter does not reproduce
the author's test loop.
An Android emulator provider does not establish physical-device or iOS support. Those routes require an explicitly compatible original provider exposed by the host. If a matching provider or device capability is missing, the route is unavailable: report SKIP or BLOCKED with the missing platform or capability, use the host's official plugin setup to install or enable the matching provider, then refresh session exposure. Do not counterfeit a missing workflow with a local summary or claim that a package proves a live connection.
Owner Device And Runtime Policy
- Identify the app/build, exact device or emulator, synthetic fixture, and expected state before actions. Prefer a disposable emulator for setup tests. Do not select a physical device implicitly, reset user data, change accounts, install profiles, or operate unrelated apps.
- Discover only the capability needed by the selected original workflow. Mobile MCP is optional; the native provider may use established adb or simulator tooling when compatible. Missing devices/platform support are SKIP or BLOCKED with a reason, not a passing app test.
- Before activating a third-party server, verify its pinned source, advisory fixes, telemetry controls and actual action surface. Keep unsafe URL schemes disabled. Do not expose arbitrary shell, package installation, file transfer, account changes or unrelated device operations by default.
- Check each batch subcommand against the same allowed operations and target. A batch entry point can bypass a filter of top-level tool names; exclude it unless its nested operations are equally constrained.
Owner Evidence And Cleanup Policy
- Require expected state versus observed state, including accessibility or screenshot evidence where needed. Successful clicks alone do not prove that an app passes; preserve the original safe logs and command results.
- Stop only emulator/server processes created for this task. Preserve existing devices, apps, SDKs, accounts and host settings.
Use synthetic photos, input text and provider errors. Never type real secrets into fixtures or collect personal notifications, photos or account screens. Keep screenshots, logs, device identifiers and MCP configuration outside public repositories. Report source build, target, actions, expected versus observed state, raw artifact paths, actual command exit codes, and remaining gaps.
Verify keyboard/input, gallery/permission, and provider-error recovery flows on their actual app builds before claiming project acceptance. A generic emulator smoke test proves only that tested device/tool path.
In this repository62 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessibility-ui-reviewSkill
- agent-retrospectiveSkill
- agents-md-retrospectiveSkill
- agent-squadSkill
- architecture-mapSkill
- architecture-normalizerSkill
- architecture-principlesSkill
- authz-boundary-reviewSkill
- c-cppSkill
- code-qualitySkill
- code-reviewSkill
- code-to-figmaSkill
- code-wiki-ruSkill
- context-packSkill
- core-engineeringSkill
- debuggingSkill
- dependency-advisory-auditSkill
- deserialization-parser-reviewSkill
- design-system-extractorSkill
- documentationSkill
- engineering-standardsSkill
- esp32Skill
- esphomeSkill
- external-agent-pack-auditSkill
- fastSkill
- figma-to-codeSkill
- fix-security-findingSkill
- goSkill
- homeassistantSkill
- mcp-tool-routerSkill
- migration-plannerSkill
- multi-agent-pr-reviewSkill
- performanceSkill
- playwright-visual-qaSkill
- pythonSkill
- quality-gatesSkill
- refactoringSkill
- responsive-breakpoint-checkSkill
- review-routerSkill
- rustSkill
- secrets-and-config-reviewSkill
- security-diff-reviewSkill
- security-routerSkill
- securitySkill
- session-memorySkill
- specialist-dispatchSkill
- subagent-result-mergeSkill
- supply-chain-reviewSkill
- tdd-guardSkill
- testing-tddSkill
- threat-modelSkill
- typescriptSkill
- ui-buildSkill
- ui-business-appsSkill
- ui-concept-firstSkill
- ui-figmaSkill
- ui-qaSkill
- ui-researchSkill
- ui-routerSkill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

