← Back to Skills Marketplace
265
Downloads
0
Stars
0
Active Installs
12
Versions
Install in OpenClaw
/install minimax-vision-search
Description
Analyze images and search the web using MiniMax MCP tools
Usage Guidance
This skill appears to do what it says: it runs local Python scripts that call the uvx MCP client using your MiniMax API key. Before installing or running: (1) confirm which binary you should install — the scripts call 'uvx' but some docs say 'uv'; install the correct package from a trusted source (prefer your package manager). (2) Do not paste your API key into third‑party install scripts; if you run any curl|sh installer linked in the docs, review the script first. (3) Only set MINIMAX_API_KEY for services you trust and avoid exporting other secrets globally. (4) If you need added assurance, inspect the included Python files (they are small and readable) and verify the GitHub/homepage link before publishing or giving the skill access to your environment.
Capability Analysis
Type: OpenClaw Skill
Name: minimax-vision-search
Version: 1.1.2
The skill provides image analysis and web search capabilities by interfacing with the MiniMax MCP server using the `uvx` tool. The implementation in `understand_image.py` and `web_search.py` follows good security practices by explicitly filtering environment variables passed to subprocesses, ensuring only necessary keys are exposed. The documentation and test scripts are consistent with the stated purpose and do not contain any malicious instructions or obfuscated code.
Capability Assessment
Purpose & Capability
The skill declares and uses the uvx binary and MINIMAX_API_KEY/HOST environment variables and its scripts call uvx to run an MCP ('minimax-coding-plan-mcp') for image understanding and web search. These requirements are appropriate for the described MiniMax MCP integration.
Instruction Scope
Runtime instructions are narrowly scoped to running the bundled Python scripts which invoke uvx via subprocess. However there are small inconsistencies in the documentation: some places say to install 'uv' (brew install uv) while the scripts check for and invoke 'uvx'; SKILL.md lists MINIMAX_API_HOST as required but the scripts supply a sensible default. The docs also mention Telegram images auto-saved to ~/.openclaw/media/inbound/ (informational) but the scripts do not automatically scan that directory — they accept a provided image path.
Install Mechanism
There is no automated install spec (instruction-only), which keeps risk low. The references/docs recommend installing uv/uvx and include a curl|sh installer URL (https://astral.sh/uv/install.sh) as a fallback — that external install command is not executed by the skill but is recommended to users and carries the usual risks of piping a remote script to sh. No archives or arbitrary downloads are embedded in the skill.
Credentials
The skill requests only MINIMAX_API_KEY and MINIMAX_API_HOST, which are proportionate to a MiniMax API integration. The scripts explicitly limit the environment passed to the subprocess to avoid leaking unrelated variables and set a local MINIMAX_MCP_BASE_PATH. Note: MINIMAX_API_HOST is treated as optional in code (defaults to https://api.minimaxi.com) despite being listed as required in metadata.
Persistence & Privilege
The skill does not request permanent/always-on presence (always:false) and does not modify other skills or global agent configuration. It runs as-invoked and requires no elevated privileges.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install minimax-vision-search - After installation, invoke the skill by name or use
/minimax-vision-search - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.1.2
minimax-vision-search 1.1.2
- Added homepage link and improved metadata in SKILL.md for better integration.
- No changes to user-facing commands or functionalities.
v1.1.1
- Simplified and clarified documentation for easier setup and usage.
- Shortened description and removed duplicate sections.
- Moved technical requirements into a dedicated section.
- Refined Quick Start instructions for image analysis and web search.
- Highlighted image source options and clarified webchat image support status.
v1.1.0
- Added _meta.json metadata file.
- Updated requirements: uvx is now the required binary (uv removed), and MINIMAX_API_HOST added as a required environment variable.
- Adjusted installation instructions to reference only uvx.
- Updated script and documentation references to match new dependency requirements.
v1.0.11
- Added a test script (scripts/test.py) for easier pre-publish testing.
- Updated documentation (SKILL.md) to include instructions for running the new test script.
v1.0.10
- Updated skill metadata to add a clawdbot emoji and improved installation section structure.
- Added unique IDs to installation methods for better management.
- No functional changes to skill logic; documentation improvements only.
v1.0.9
- Added a link to a new Chinese documentation file (references/README_zh.md) in the Tips section.
- Included references/README_zh.md in the repository.
v1.0.8
- Added explicit instructions and metadata for installing the required "uv" dependency using Homebrew or pipx.
- Updated prerequisites and quick start sections to recommend "brew install uv" for macOS.
- Updated metadata to include both "uv" and "uvx" as required binaries.
- Minor documentation clarifications for improved setup guidance.
v1.0.7
- Removed unused metadata section "config: requiredEnv" from SKILL.md.
- No changes to usage, features, or requirements.
v1.0.6
- Cleaned up and simplified environment and config instructions in SKILL.md.
- Removed unused stateDirs from metadata.
- Updated prerequisite steps and API key setup process for clarity.
- No changes to core functionality.
v1.0.5
Version 1.0.5 of minimax-vision-search
- No file changes detected in this version.
- No new features, bug fixes, or documentation changes introduced.
v1.0.4
- Added metadata section specifying required binaries, environment variables, and state directories.
- Clarified prerequisites, including installation instructions for uvx and configuration of MINIMAX_API_KEY.
- Split out prerequisites and quick start steps for improved clarity.
v1.0.0
MiniMax Vision & Search MCP skill initial release.
- Adds support for MiniMax image analysis and web search via MCP tools.
- Enables image understanding: analyze, describe, and interpret image content.
- Integrates web search for user queries.
- Supports local image files, URLs, and Telegram images.
- Simple command-line usage for both image understanding and web search.
Metadata
Frequently Asked Questions
What is Minimax Vision Search?
Analyze images and search the web using MiniMax MCP tools. It is an AI Agent Skill for Claude Code / OpenClaw, with 265 downloads so far.
How do I install Minimax Vision Search?
Run "/install minimax-vision-search" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Minimax Vision Search free?
Yes, Minimax Vision Search is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Minimax Vision Search support?
Minimax Vision Search is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created Minimax Vision Search?
It is built and maintained by wuu Dao (@daowuu); the current version is v1.1.2.
More Skills