/install cloudphone
What this skill does
cloudphone guides the agent to run Android automation tasks in a cloud phone environment by calling cpc-mcp-server tools through mcporter.
It is designed for:
- AutoJS-based cloud phone automation
- App regression / smoke test execution
- Remote batch operation workflows
- Scripted interaction on cloud Android devices
When to use this skill
Use this skill when the user asks for actions such as:
- “Run a script on a cloud phone”
- “Use AutoJS to automate this app flow”
- “Execute Android UI steps remotely and return screenshots/logs”
- “Use cpc-mcp-server for cloud-device automation”
When NOT to use this skill
Do not use this skill for:
- Local ADB/emulator automation (non-cloud devices)
- iOS automation (e.g., XCUITest)
- Static script/code review without real device execution
- Pure consulting requests without executable task goals
Required prerequisites (must pass before execution)
Before any call, ensure authentication is configured correctly.
cpc-mcp-server requires:
Authorization: Bearer \x3CAPI_KEY>
This skill standardizes the API key through:
CLOUDPHONE_API_KEY(required)
Requirements
- Set environment variable
CLOUDPHONE_API_KEY. - Ensure MCP server header injection is active before execution:
Authorization: Bearer $CLOUDPHONE_API_KEY
- Never hardcode or commit real keys in repo files,
SKILL.md, or config JSON.
This skill defines naming and preconditions only.
Secret injection implementation is handled by runtime/environment config.
Invocation model (via mcporter)
This skill does not call MCP tools directly. It uses mcporter CLI to invoke tools on cpc-mcp-server.
Common command patterns:
- List configured MCP servers:
mcporter list
- Inspect server schema:
mcporter list cpc-mcp-server --schema
- Call tool with JSON args (recommended):
mcporter call cpc-mcp-server.\x3Ctool> --args '\x3Cjson>'
Prefer
--argsJSON for long instructions, multilingual text, and special characters.
Minimal input checklist (before creating tasks)
Collect these fields first (ask follow-up only if missing):
- Target app (name/package)
- Intended action (what to do)
- Success criteria (what counts as done)
- Expected output type (screenshot/log/text result)
Tool 1: Create task (createAutoJsAgentTask)
Goal
Create and dispatch an AutoJS Agent task, then obtain taskId (and possibly sessionId).
Recommended call
mcporter call cpc-mcp-server.createAutoJsAgentTask --args '{
"instruction": "Open \x3CAPP_NAME> on cloud phone, log in with test account, navigate to Orders page, capture a screenshot, and return order count.",
"lang": "en"
}'
- 确保已安装 OpenClaw(本地或 Docker 部署)
- 在对话框中输入安装命令:
/install cloudphone - 安装完成后,直接呼叫该 Skill 的名称或使用
/cloudphone触发 - 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
Cloud Phone Agent 是什么?
Use mcporter to call cpc-mcp-server AutoJS Agent tools for cloud Android task execution and result retrieval. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1090 次。
如何安装 Cloud Phone Agent?
在 OpenClaw 或 Claude Code 对话框中运行命令「/install cloudphone」即可一键安装,无需额外配置。
Cloud Phone Agent 是免费的吗?
是的,Cloud Phone Agent 完全免费(开源免费),可自由下载、安装和使用。
Cloud Phone Agent 支持哪些平台?
Cloud Phone Agent 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。
谁开发了 Cloud Phone Agent?
由 sav7ng(@sav7ng)开发并维护,当前版本 v0.0.2。