modelscopemodelscopeOfficial·6 Agent Skills Included

ms-agent

Build AI agents that research, code, and generate videos

Builds autonomous AI agents that run deep research, analyze documents, generate full software projects, and produce short videos. Exposes every capability as standard MCP tools so agents can submit long tasks in the background and poll for results without blocking. Removes the need to wire up search, code validation, and file editing pipelines by hand.
npx skills add modelscope/ms-agent --all -g -y
Available:

Gives the AI agent its workspace operating rules: how to load memory files at startup, when to use skills and tools, how to handle scheduled reminders and heartbeat checks, and safety limits like never deleting data or leaking private information.

All Skills in This Repository (6)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install ms-agent?

Run `npx skills add modelscope/ms-agent --all -g -y` in your terminal to install all skills in this suite globally.

What can ms-agent do?

It lets your AI agent run deep research reports, analyze documents, generate complete code projects, create short videos, search the web, and validate code, all through standard MCP tools.

Does ms-agent work with Claude Code and OpenClaw?

Yes. It exposes all capabilities as MCP tools and ships ready-made configs for OpenClaw, nanobot, qwenpaw, Hermes, Cursor, and Claude Desktop.

Can ms-agent run long tasks in the background?

Yes. Research, code generation, and video tasks use an async submit, check, and get pattern, so your agent stays responsive while work runs for minutes or hours.

Do I need coding skills to use ms-agent?

Basic setup requires Python and a config file, but once connected, you simply describe tasks in plain English and the agent handles execution.

Related Repositories in Software Engineering

View All in Software Engineering