跳到正文
cccskills
免费在 GitHub 公开

qa-specialist-mobile

Design platform-specific Android and iOS checks with explicit SDK, driver, device, lifecycle, and evidence prerequisites.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md7.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

QA mobile specialist

Use this specialist when a QA workflow needs native, hybrid, or mobile Web coverage for Android or iOS. This specialist does not execute a workflow or tests and cannot grant authorization. Read workflow, safety, and tooling before advising the calling workflow.

Inputs

  • Target application/build, identified contract, preserved criterion IDs and text, and in-scope platform: Android, iOS, or both.
  • Supported OS versions, device classes, screen/orientation matrix, app lifecycle, permissions, connectivity, localization, and accessibility behavior.
  • Probe inventory for host OS, SDK/toolchain, automation tool, platform driver, device or emulator/simulator, build, app installation, and connectivity.
  • Synthetic or reviewed test data, accounts, backend environment, evidence needs, and explicit authorization boundaries.

Procedure

  1. Preserve the target, contract, criteria, platforms, device matrix, and authorization supplied by the caller. Never silently substitute Android coverage for iOS or a simulator for a required physical device.
  2. For Android, evaluate the Android SDK, ADB, build, device or emulator, and configured driver. Appium use requires its UiAutomator2 driver; a tool-only positive probe is insufficient.
  3. For iOS, evaluate a macOS host, Xcode/iOS SDK, build/signing prerequisites, device or simulator, and configured driver. Appium use requires its XCUITest driver; record physical device trust/signing limitations separately.
  4. Ask qa-tooling to derive available, missing, or unverified from all supplied probes. Keep tool, SDK, driver, and device evidence separate. Never install an SDK or driver and never fabricate a device from an absent probe. Declare READY only when separate probes for the tool, compatible host, SDK/toolchain, platform connectivity (including ADB for Android), driver, build, signing, device, and required service are all positive. A prerequisite may be not applicable only when it genuinely does not apply to that platform. An absent or not_run probe makes readiness unverified; an explicit negative required-prerequisite probe makes the path BLOCKED.
  5. Propose observable checks for installation/launch, foreground/background/termination, state restoration, navigation, gestures, keyboard/input, orientation, permissions, interruption, connectivity, localization, accessibility, and platform-specific behavior where applicable.
  6. Assign every check to an exact platform, OS/device class, build, precondition, expected observable result, and evidence need. Keep expected and observed results distinct.
  7. Return coverage and limitations to the calling workflow. A missing required device, SDK, driver, build, account, or service blocks that execution path; recommend a compatible native runner or authorized manual device run without claiming it occurred.

Output

Return:

  • target/build, contract, criteria, Android/iOS scope, device/OS matrix, environment, and authorization;
  • checks with platform, lifecycle state, preconditions, actions, expected observable result, data, and evidence need;
  • separate tool, host, SDK, driver, build, device, and service availability with exact probe evidence and platform-compatible alternatives;
  • coverage gaps, device-only limitations, defects, blockers, and the next valid action.

READY below means all listed prerequisites for the proposed path are available. It is not an executed case result or global verdict.

Reference scenarios

scenarioplatformtool_probehost_probesdk_probeadb_probedriver_probebuild_probesigning_probedevice_probeservice_probeoutcome
platform-readyAndroidpositive: Appiumpositive: compatible hostpositive: Android SDKpositive: connectedpositive: UiAutomator2positive: test buildpositive: installablepositive: emulatorpositive: test backendREADY
platform-readyiOSpositive: Appiumpositive: macOSpositive: Xcode iOS SDKnot applicable: iOSpositive: XCUITestpositive: test buildpositive: simulator-validpositive: simulatorpositive: test backendREADY
missing-deviceAndroidpositive: Appiumpositive: compatible hostpositive: Android SDKpositive: connectedpositive: UiAutomator2positive: test buildpositive: installablenegative: missingpositive: test backendBLOCKED
missing-hostiOSpositive: Appiumnot_run: hostpositive: Xcode iOS SDKnot applicable: iOSpositive: XCUITestpositive: test buildpositive: simulator-validpositive: simulatorpositive: test backendunverified
missing-buildiOSpositive: Appiumpositive: macOSpositive: Xcode iOS SDKnot applicable: iOSpositive: XCUITestnegative: missingpositive: simulator-validpositive: simulatorpositive: test backendBLOCKED
missing-signingiOSpositive: Appiumpositive: macOSpositive: Xcode iOS SDKnot applicable: iOSpositive: XCUITestpositive: test buildnot_run: signingpositive: simulatorpositive: test backendunverified
missing-adbAndroidpositive: Appiumpositive: compatible hostpositive: Android SDKnot_run: ADBpositive: UiAutomator2positive: test buildpositive: installablepositive: emulatorpositive: test backendunverified

The ready rows remain separate because Android host/SDK/ADB/UiAutomator2/build/signing/emulator evidence cannot prove iOS macOS/Xcode/XCUITest/build/signing/simulator readiness, or vice versa. Both also require a positive tool and service probe. In missing-device and missing-build, an explicit negative required probe keeps execution BLOCKED. In missing-host, missing-signing, and missing-adb, the applicable probe was not run, so readiness remains unverified. None of these limitation scenarios may become READY from the remaining positive probes.

Failure modes

  • Platform, app build, contract, expected behavior, or device matrix absent: return affected coverage as BLOCKED and name the missing input.
  • Tool positive but SDK, driver, device, build, or host probe absent/not run/negative: preserve each probe and report the complete capability as unverified or blocked as appropriate.
  • Required physical behavior with only a simulator/emulator: record the limitation; do not claim hardware, camera, sensor, biometric, push, or performance coverage.
  • Device missing or offline: do not execute or fabricate observations; propose a compatible device, native test runner, or authorized manual run.
  • Unsupported host/platform pairing: exclude the incompatible tool and return a compatible alternative or none verified.

Safety

  • This specialist cannot grant device access, signing, production, external-effect, load, or penetration-test authorization.
  • Never install SDKs, drivers, apps, profiles, or certificates; never alter personal device or user configuration, publish, push, merge, or correct product code.
  • Do not read personal device data, secrets, credentials, notifications, photos, contacts, or unrelated logs. Use synthetic accounts and isolated test data.
  • Review screenshots visually before attachment, bind evidence to the exact build/device/target, and apply confinement and sanitization requirements.

Related skills

  • qa-tooling owns platform filtering, prerequisite probes, and safe alternatives.
  • qa-test may execute approved mobile checks and bind reviewed evidence.
  • qa-specialist-functional supplies behavior partitions and state transitions.
  • qa-specialist-accessibility evaluates platform accessibility behavior when applicable.

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Accessibility auditing and remediation skill for Vue 3 + Reka UI. Use when reviewing components, verifying WCAG 2.1 AA, fixing ARIA issues, or validating keyboard navigation in Reka UI components.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

ai-infra

免费

Infraestrutura para IA — GPU, servidores MCP, gateway de LLM, pipeline de inferência, custo de token, cache semântico e observabilidade de modelo. Use quando o usuário disser "GPU", "MCP server", "LLM", "inferência", "modelo", "gateway de IA", "custo de token", "rate limit da API de IA", "self-host de modelo".

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

alt-text

免费

Escreve texto alternativo e descrição de imagem para peças de rede social. Use quando o usuário disser "alt text", "texto alternativo", "descrição da imagem", "acessibilidade da peça", "descrever para leitor de tela", ou automaticamente antes de qualquer publicação. Obrigatório em todas as peças — em carrossel, um por slide.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

Organiza, compara e seleciona entre as variações geradas, e publica a grade de comparação como Artifact para aprovação do time. Use quando o usuário disser "qual dessas", "comparar as variações", "escolher a melhor", "mostrar as opções", "montar grade de aprovação", ou após qualquer lote de geração. Selecionar é trabalho, não detalhe.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

Aumenta resolução e qualidade de imagem via Freepik/Magnific, ou orienta o processo manual quando não há chave. Use quando o usuário disser "upscale", "melhorar a resolução", "a imagem está pixelada", "Magnific", "Freepik", "aumentar a imagem", "imagem pequena demais". Gasta crédito — exige confirmação.

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

CI/CD e automação — GitHub Actions, Terraform, OpenTofu, Ansible, n8n. Use quando o usuário disser "pipeline", "CI/CD", "GitHub Actions", "workflow", "terraform", "ansible", "n8n", "automatizar", "deploy automático", "IaC".

中文简介正在准备中。当前显示原文说明。

pwdev-solucoes/pwdev-claude-marketplace32026年10月15日 更新

查看 pwdev-solucoes 的全部技能

报告此技能的问题