← 返回 Skills 市场
tallman2014

Manus Monitor

作者 tallman2014 · GitHub ↗ · v1.0.3
cross-platform ⚠ suspicious
1468
总下载
2
收藏
1
当前安装
4
版本数
在 OpenClaw 中安装
/install manus-monitor
功能描述
Create and manage AI agent tasks via Manus API. Manus is an autonomous AI agent that can browse the web, use tools, and deliver complete work products.
使用说明 (SKILL.md)

Manus AI Agent

Use the Manus API to create autonomous AI tasks. Manus can browse the web, use tools, and deliver complete results (reports, code, presentations, etc.).

API Base

https://api.manus.ai/v1

Authentication

Header: API_KEY: \x3Cyour-key>

Set via:

  • MANUS_API_KEY env var
  • Or skills.manus.apiKey in clawdbot config

Recommended Workflow

When using Manus for tasks that produce files (slides, reports, etc.):

  1. Create the task with createShareableLink: true
  2. Poll for completion using the task_id
  3. Extract output files from the response and download them locally
  4. Deliver to user via direct file attachment (don't rely on manus.im share links)

Create a Task

curl -X POST "https://api.manus.ai/v1/tasks" \
  -H "API_KEY: $MANUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Your task description here",
    "agentProfile": "manus-1.6",
    "taskMode": "agent",
    "createShareableLink": true
  }'

Response:

{
  "task_id": "abc123",
  "task_title": "Task Title",
  "task_url": "https://manus.im/app/abc123"
}

Agent Profiles

Profile Description Use for
manus-1.6 Standard (default) Most tasks
manus-1.6-lite Faster, lighter Quick/simple stuff
manus-1.6-max Complex, thorough Deep research/analysis

Default: Always use manus-1.6 unless user specifies otherwise.

Task Modes

Mode Description
chat Conversational mode
adaptive Auto-selects best approach
agent Full autonomous agent mode (recommended for file creation)

Get Task Status & Output

curl "https://api.manus.ai/v1/tasks/{task_id}" \
  -H "API_KEY: $MANUS_API_KEY"

Status values: pending, running, completed, failed

Important: When status is completed, check the output array for files:

  • Look for type: "output_file" entries
  • Download files from fileUrl directly
  • Save locally and send to user as attachments

Extracting Output Files

The task response includes output like:

{
  "output": [
    {
      "content": [
        {
          "type": "output_file",
          "fileUrl": "https://private-us-east-1.manuscdn.com/...",
          "fileName": "presentation.pdf"
        }
      ]
    }
  ]
}

Download these files with curl and deliver directly to the user rather than relying on share URLs.

List Tasks

curl "https://api.manus.ai/v1/tasks" \
  -H "API_KEY: $MANUS_API_KEY"

Best Practices

  1. Always poll for completion before telling user the task is done
  2. Download output files locally instead of giving manus.im links (they can be unreliable)
  3. Use agent mode for tasks that create files/documents
  4. Set reasonable expectations — Manus tasks can take 2-10+ minutes for complex work

Docs

安全使用建议
This skill largely does what its description promises (managing Manus tasks), but review the following before installing: 1) The package will create a recurring platform cron job that polls your Manus tasks every minute — confirm you want that persistent behavior. 2) The scripts will send notifications via Telegram if TELEGRAM_BOT_TOKEN and TELEGRAM_CHAT_ID are present; those env vars are not declared in the skill metadata, so only set them if you trust the skill and want notifications. 3) The scripts assume external tools (curl, jq, openclaw CLI, etc.) but these are not declared — ensure those binaries are present and you are comfortable with the agent using them. 4) The skill downloads output files from URLs returned by the Manus API and saves them locally; verify you trust the Manus service and the API key you provide. 5) There is a mismatch in the included _meta.json ownerId versus the registry owner; consider verifying the skill author/website (https://manus.im) and the publisher identity before granting credentials. If you proceed, only provide MANUS_API_KEY (and Telegram tokens only if you want notifications), and consider inspecting and running the scripts manually once to understand their behavior.
功能分析
Type: OpenClaw Skill Name: manus-monitor Version: 1.0.3 The skill is classified as suspicious due to the use of high-risk capabilities, specifically the creation of a persistent cron job via `openclaw cron add` in `scripts/manus-monitor-start.sh` and the external network communication to `api.telegram.org` for notifications in `scripts/manus-monitor.sh`. While these actions are aligned with the stated purpose of monitoring Manus tasks and sending alerts, they represent significant attack surfaces. The cron job allows for scheduled execution of commands, and the Telegram integration could be leveraged for data exfiltration if `TELEGRAM_BOT_TOKEN` and `TELEGRAM_CHAT_ID` were controlled by an attacker. There is no clear evidence of intentional malicious behavior, but these capabilities carry inherent risks.
能力评估
Purpose & Capability
The scripts and SKILL.md align with the stated purpose: they call the Manus API (MANUS_API_KEY), create tasks, poll status, download output files, and surface results. That capability legitimately needs the Manus API key and the ability to make HTTP requests and write local files.
Instruction Scope
Runtime scripts do more than the SKILL.md documents: they create scheduled cron jobs via the openclaw CLI, write and read local task/state files, and send Telegram messages. The SKILL.md does not mention Telegram notification environment variables (TELEGRAM_BOT_TOKEN, TELEGRAM_CHAT_ID) even though the scripts will use them if present. The scripts also log to /tmp and automatically start/stop monitoring when tasks are saved — behavior not fully described in SKILL.md.
Install Mechanism
There is no install spec (instruction-only), which reduces installer risk. However, the package includes multiple helper scripts that will be executed by the agent/cron; those scripts assume the presence of external tools (curl, jq, openclaw, date, mktemp) that are not declared in the registry metadata.
Credentials
Declared primary credential MANUS_API_KEY is appropriate. But the code expects additional environment variables (TELEGRAM_BOT_TOKEN, TELEGRAM_CHAT_ID) that are not declared in requires.env. Scripts also rely on openclaw CLI and jq/curl — these binaries are not declared. Unexpected or undeclared env usage is a red flag because it may cause accidental credential exposure or unexpected behavior if users set those envs.
Persistence & Privilege
The skill will create a recurring 'manus-task-monitor' cron job via the platform 'openclaw cron add' when a task is saved. always:false in the metadata is preserved, but the skill installs a persistent scheduled job that runs every minute until removed. This is a meaningful persistence capability and should be disclosed to the user (what the job does, what notifications it can send).
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install manus-monitor
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /manus-monitor 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.0.3
排除data目录,确保用户数据安全
v1.0.2
排除用户数据目录
v1.0.1
修复data目录问题,不包含用户数据
v1.0.0
新增任务自动监控功能,支持保存任务ID、状态轮询、完成后通知用户
元数据
Slug manus-monitor
版本 1.0.3
许可证
累计安装 1
当前安装数 1
历史版本数 4
常见问题

Manus Monitor 是什么?

Create and manage AI agent tasks via Manus API. Manus is an autonomous AI agent that can browse the web, use tools, and deliver complete work products. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 1468 次。

如何安装 Manus Monitor?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install manus-monitor」即可一键安装,无需额外配置。

Manus Monitor 是免费的吗?

是的,Manus Monitor 完全免费(开源免费),可自由下载、安装和使用。

Manus Monitor 支持哪些平台?

Manus Monitor 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 Manus Monitor?

由 tallman2014(@tallman2014)开发并维护,当前版本 v1.0.3。

💬 留言讨论