manus-ai_skill

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