home / skills / openclaw / skills / manus-ai

manus-ai skill

/skills/joelchance/manus-ai

This skill creates and manages Manus AI agent tasks via the Manus API, enabling task tracking, status checks, and output retrieval.

npx playbooks add skill openclaw/skills --skill manus-ai

Review the files below or copy the command above to add this skill to your agents.

Files (3)
SKILL.md
3.0 KB
---
name: manus
description: 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.
homepage: https://manus.im
user-invocable: true
disable-model-invocation: true
metadata:
  clawdbot:
    emoji: "🤖"
    primaryEnv: MANUS_API_KEY
    requires:
      bins: [curl, jq]
      env: [MANUS_API_KEY]
---

# Manus AI Agent

Create tasks for Manus, an autonomous AI agent, and retrieve completed work products.

## Authentication

Set `MANUS_API_KEY` env var with your key from [manus.im](https://manus.im).

---

## Commands

All commands use `scripts/manus.sh`.

### Create a Task

```bash
{baseDir}/scripts/manus.sh create "Your task description here"
{baseDir}/scripts/manus.sh create "Deep research on topic" manus-1.6-max
```

Profiles: `manus-1.6` (default), `manus-1.6-lite` (fast), `manus-1.6-max` (thorough).

### Check Status

```bash
{baseDir}/scripts/manus.sh status <task_id>
```

Returns: `pending`, `running`, `completed`, or `failed`.

### Wait for Completion

```bash
{baseDir}/scripts/manus.sh wait <task_id>
{baseDir}/scripts/manus.sh wait <task_id> 300  # custom timeout in seconds
```

Polls until task completes or times out (default: 600s).

### Get Task Details

```bash
{baseDir}/scripts/manus.sh get <task_id>
```

Returns full task JSON including status and output.

### List Output Files

```bash
{baseDir}/scripts/manus.sh files <task_id>
```

Shows filename and download URL for each output file.

### Download Output Files

```bash
{baseDir}/scripts/manus.sh download <task_id>
{baseDir}/scripts/manus.sh download <task_id> ./output-folder
```

Downloads all output files to the specified directory (default: current directory).

### List Tasks

```bash
{baseDir}/scripts/manus.sh list
```

---

## Typical Workflow

1. **Create task**: `manus.sh create "your prompt"`
2. **Wait for completion**: `manus.sh wait <task_id>`
3. **Download results**: `manus.sh download <task_id>`

---

## Advanced API Features

For file attachments, webhooks, connectors, projects, multi-turn conversations, and interactive mode, see the full Manus API documentation:

- API Reference: https://open.manus.ai/docs
- Main Docs: https://manus.im/docs

---

## Security & Permissions

**What this skill does:**
- Sends task prompts to the Manus API at `api.manus.ai`
- Polls for task completion and downloads output files from Manus CDN
- API key is sent only in the `API_KEY` header to `api.manus.ai`

**What this skill does NOT do:**
- Does not upload local files (file upload is an advanced API feature not implemented in the bundled script)
- Does not register webhooks or connect external accounts
- Does not send your API key to any endpoint other than `api.manus.ai`
- Does not modify local system configuration
- Cannot be invoked autonomously by the agent (`disable-model-invocation: true`)
- You must explicitly trigger every Manus task

**Bundled scripts:** `scripts/manus.sh` (Bash — uses `curl` and `jq`)

Review `scripts/manus.sh` before first use to verify behavior.

Overview

This skill creates and manages tasks for the Manus autonomous AI agent via the Manus API. It provides lightweight command scripts to submit prompts, poll task status, retrieve task JSON, list and download output files, and wait for completion. The workflow is optimized for repeatable research, content production, and automated delivery of work products.

How this skill works

The skill uses a bundled Bash script that calls the Manus REST API (api.manus.ai) with your MANUS_API_KEY set in the environment. It can create tasks with a chosen Manus profile, poll status, fetch full task JSON, list output files, and download files to a local directory. All API requests include the key in the API_KEY header and files are downloaded from Manus CDN URLs returned by the API.

When to use it

  • Automate research or content generation that requires web browsing and tool use
  • Run long-running or multi-step agent tasks and retrieve complete work products
  • Batch submit similar prompts with different parameters or profiles
  • Backup or archive outputs produced by Manus tasks
  • Integrate Manus task execution into CI scripts or developer tooling

Best practices

  • Set MANUS_API_KEY in your environment and verify the script behavior before use
  • Pick an appropriate Manus profile: lite for speed, default for balance, max for thorough results
  • Use the wait command with a timeout to avoid indefinite polling in automation
  • Inspect returned task JSON with the get command before downloading files
  • Review scripts/manus.sh for safety and adapt download paths to a controlled directory

Example use cases

  • Deep web research assignment: create a Manus task to gather sources and export a report PDF
  • Marketing content pack: request blog posts, social captions, and image assets then download all outputs
  • Data enrichment: ask Manus to scrape, consolidate, and return structured CSVs
  • Proof-of-concept automation: integrate task creation and polling into a CI job to validate deliverables

FAQ

How do I authenticate?

Export your Manus API key as the MANUS_API_KEY environment variable before running the scripts.

Which profiles are available and when to use them?

Profiles include manus-1.6 (default), manus-1.6-lite (faster, less thorough), and manus-1.6-max (more thorough). Choose based on speed vs. depth trade-offs.

Can the script upload local files or register webhooks?

Not in the bundled script. File uploads and webhooks are supported by the Manus API but require extending the scripts or using the API directly.