agentleFS
weininghuiweininghui/skills/cloudphone/SKILL.md

cloudphone

Skill1 starsChanged 12 days agoMITView on GitHub

Use mcporter to call cpc-mcp-server AutoJS Agent tools for cloud Android task execution and result retrieval.

  • Reads credentials

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill when the user asks for actions such as:

    line 24
  2. Distinctive:

    Do not use this skill for:

    line 34
  3. Distinctive:

    Before any call, ensure authentication is configured correctly.

    line 44
  4. Distinctive:

    Ensure MCP server header injection is active before execution:

    line 57
  5. Very specific:

    Never hardcode or commit real keys in repo files, SKILL.md, or config JSON.

    line 59
  6. Distinctive:

    Call tool with JSON args (recommended):

    line 75
  7. Very specific:

    Create and dispatch an AutoJS Agent task, then obtain taskId (and possibly sessionId).

    line 95

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

运行依赖:需要本机已安装命令 mcporter;需要环境变量 CLOUDPHONE_API_KEY(未配置则该技能不可用);缺失时先安装 / 配置,再执行正文步骤。

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 <API_KEY>

This skill standardizes the API key through:

  • CLOUDPHONE_API_KEY (required)

Requirements

  1. Set environment variable CLOUDPHONE_API_KEY.
  2. Ensure MCP server header injection is active before execution:
    • Authorization: Bearer $CLOUDPHONE_API_KEY
  3. 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.<tool> --args '<json>'

Prefer --args JSON for long instructions, multilingual text, and special characters.


Minimal input checklist (before creating tasks)

Collect these fields first (ask follow-up only if missing):

  1. Target app (name/package)
  2. Intended action (what to do)
  3. Success criteria (what counts as done)
  4. 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 <APP_NAME> on cloud phone, log in with test account, navigate to Orders page, capture a screenshot, and return order count.",
  "lang": "en"
}'

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.