← Back to Skills Marketplace
MiniCPM-o 4.5 Deploy
by
Dennis Huang
· GitHub ↗
· v1.0.0
· MIT-0
174
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install minicpmo-45-deploy
Description
Deploy MiniCPM-o 4.5 multimodal model via Web Demo, vLLM Serve, or llamacpp-omni. Use when the user asks to deploy, start, configure, or troubleshoot MiniCPM...
Usage Guidance
This skill appears internally consistent for deploying MiniCPM-o 4.5, but it performs network downloads and installs packages and runs project install scripts. Before using it: (1) verify the upstream repository (the instructions clone https://github.com/OpenBMB/MiniCPM-o-Demo); (2) avoid using untrusted mirrors (the SKILL.md suggests hf-mirror.com, which is not an official HuggingFace host); (3) run install steps in an isolated environment (container or VM) or a dedicated virtualenv/conda env; (4) do not provide private tokens unless you understand why they’re needed (private model downloads may prompt for credentials); and (5) inspect install.sh and any downloaded scripts yourself if you need stronger assurance.
Capability Analysis
Type: OpenClaw Skill
Name: minicpmo-45-deploy
Version: 1.0.0
The skill bundle provides a legitimate workflow for deploying the MiniCPM-o 4.5 multimodal model. It includes automated environment setup (Miniconda, FFmpeg), model verification, and service management. While the skill involves high-privilege actions such as installing Python packages via pip in `scripts/download_model.py` and executing shell scripts for environment setup in `SKILL.md`, these actions are standard for machine learning deployment and aligned with the stated purpose. No evidence of data exfiltration, unauthorized persistence, or malicious prompt injection was found.
Capability Assessment
Purpose & Capability
The name/description (deploy MiniCPM-o 4.5 via Web Demo / vLLM / llamacpp-omni) matches the included files and runtime instructions. The provided download/verification script, references, and step-by-step install/launch commands align with model download and deployment tasks. No unrelated credentials, binaries, or config paths are requested.
Instruction Scope
SKILL.md gives explicit installation and deployment steps (conda or venv, pip installs, git clone, running install.sh, starting gateway/workers). It instructs network downloads from GitHub, HuggingFace, and ModelScope and running a local Python script to verify/download models. This scope is appropriate for a deployment guide, but the agent will run networked downloads and install packages at runtime — actions that have real consequences and should be done in a trusted/isolated environment.
Install Mechanism
There is no packaged install spec (instruction-only) but the included scripts call pip to install dependencies on demand and recommend running the project's install.sh. That is expected for this type of skill but is higher-risk than pure documentation because it causes code to be written/executed locally. A non-official mirror (https://hf-mirror.com) is suggested in troubleshooting; using unofficial mirrors carries extra risk and should be avoided unless you trust the mirror.
Credentials
The skill declares no required environment variables or credentials. The runtime instructions mention optional environment variables (e.g., HF_ENDPOINT) and may prompt for HuggingFace/ModelScope credentials if private models are used, which is proportional. There are no requests for unrelated secrets or broad system credentials.
Persistence & Privilege
always is false and the skill does not request persistent platform-level privileges or modify other skills. It runs as-needed commands and scripts in the user's environment; autonomous invocation by the agent is allowed by default but not excessive here.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install minicpmo-45-deploy - After installation, invoke the skill by name or use
/minicpmo-45-deploy - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release: deployment skill for MiniCPM-o 4.5 multimodal model.
- Provides complete step-by-step deployment guide for MiniCPM-o 4.5 via Web Demo.
- Includes detailed hardware and device compatibility guidelines, highlighting supported and unsupported platforms.
- Documents model download, verification, and configuration procedures.
- Covers SSL certificate generation and service startup for secure browser access.
- Offers troubleshooting and verification steps, with clear references and resource links.
Metadata
Frequently Asked Questions
What is MiniCPM-o 4.5 Deploy?
Deploy MiniCPM-o 4.5 multimodal model via Web Demo, vLLM Serve, or llamacpp-omni. Use when the user asks to deploy, start, configure, or troubleshoot MiniCPM... It is an AI Agent Skill for Claude Code / OpenClaw, with 174 downloads so far.
How do I install MiniCPM-o 4.5 Deploy?
Run "/install minicpmo-45-deploy" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is MiniCPM-o 4.5 Deploy free?
Yes, MiniCPM-o 4.5 Deploy is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does MiniCPM-o 4.5 Deploy support?
MiniCPM-o 4.5 Deploy is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created MiniCPM-o 4.5 Deploy?
It is built and maintained by Dennis Huang (@zmxjj); the current version is v1.0.0.
More Skills