← Back to Skills Marketplace
qwen-enhance
by
Tom Mcpherson
· GitHub ↗
· v1.0.0
· MIT-0
189
Downloads
0
Stars
1
Active Installs
1
Versions
Install in OpenClaw
/install qwen-enhance
Description
增强通义千问 (Qwen) 模型的适配能力，特别是 Qwen-VL 多模态输入格式化。在处理视觉任务时使用。
Usage Guidance
This skill is small and coherent: it simply formats text (and an optional image URL) into a Qwen‑VL prompt. Before installing, verify the script path referenced in SKILL.md matches where the skill will be placed (the example uses a .trae/ path while the file manifest shows scripts/qwen_vl.py). Inspect the included script if you want extra assurance (it contains no network calls or secret access). If you plan to run unmodified third‑party skills in sensitive environments, consider reviewing or sandboxing them first.
Capability Analysis
Type: OpenClaw Skill
Name: qwen-enhance
Version: 1.0.0
The qwen-enhance skill is a straightforward utility designed to format prompts for the Qwen-VL multimodal model. The Python script scripts/qwen_vl.py performs simple string concatenation to wrap image URLs in tags, and the SKILL.md documentation accurately describes this behavior without any malicious instructions or suspicious execution patterns.
Capability Assessment
Purpose & Capability
The name/description promise (generate Qwen‑VL image+text prompts and optimize prompts) matches the included script and SKILL.md. The only minor mismatch is the example invocation path (SKILL.md shows .trae/skills/...), while the repository provides scripts/qwen_vl.py; this looks like a documentation/pathing inconsistency rather than functional overreach.
Instruction Scope
SKILL.md instructions are narrowly scoped to generating/formating prompts. They do not instruct reading system files, accessing environment variables, calling external endpoints, or collecting unrelated data. The example usage path differs from the manifest path (documentation note).
Install Mechanism
There is no install spec; this is instruction-only plus a tiny local script. Nothing is downloaded or written to disk by an installer.
Credentials
No environment variables, credentials, or config paths are required. The script does not read secrets or invoke network I/O.
Persistence & Privilege
Skill is not always-on, is user-invocable, and does not request persistent/system-wide changes or modify other skills' configurations.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install qwen-enhance - After installation, invoke the skill by name or use
/qwen-enhance - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
- Initial release of qwen-enhance skill.
- Adds tools for enhanced compatibility with Aliyun Qwen and Qwen-VL models.
- Supports automatic formatting of multimodal (image/text) prompts for Qwen-VL.
- Includes prompt optimization features for better instruction following.
- Example script and output provided for generating visual task prompts.
Metadata
Frequently Asked Questions
What is qwen-enhance?
增强通义千问 (Qwen) 模型的适配能力，特别是 Qwen-VL 多模态输入格式化。在处理视觉任务时使用。 It is an AI Agent Skill for Claude Code / OpenClaw, with 189 downloads so far.
How do I install qwen-enhance?
Run "/install qwen-enhance" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is qwen-enhance free?
Yes, qwen-enhance is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does qwen-enhance support?
qwen-enhance is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created qwen-enhance?
It is built and maintained by Tom Mcpherson (@dnorris2926-0); the current version is v1.0.0.
More Skills