Qwen Enhance
- 8 installs
- 33 repo stars
- Updated April 26, 2026
- bighardperson/computer-science-skills-collection
qwen-enhance is a Claude skill that formats multimodal Qwen-VL prompts and tunes prompts for Alibaba's Qwen models.
About
This skill formats mixed image and text prompts for Alibaba's Qwen (Tongyi Qianwen) models, especially Qwen-VL. A developer uses it when building an agent that sends visual tasks to a Qwen-VL model and needs the correct <img>...</img> prompt format. It also offers Qwen-specific prompt-tuning tips.
- Formats multimodal input for Alibaba Qwen-VL models, wrapping image URLs as <img>url</img>
- Provides prompt-tuning helpers tailored to Qwen instruction following
- Ships a qwen_vl.py script that emits the mixed image/text prompt
Qwen Enhance by the numbers
- 8 all-time installs (skills.sh)
- Ranked #12,269 of 16,556 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Jul 30, 2026 (Skillselion catalog sync)
qwen-enhance capabilities & compatibility
Free; the skill only formats prompts (no API key stated in docs)
- Use cases
- token optimization
- Pricing
- Free
npx skills add https://github.com/bighardperson/computer-science-skills-collection --skill qwen-enhanceAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 8 |
|---|---|
| repo stars | ★ 33 |
| Last updated | April 26, 2026 |
| Repository | bighardperson/computer-science-skills-collection ↗ |
What it does
Generate correctly formatted Qwen-VL multimodal prompts (image plus text) for vision tasks.
When should I use this skill?
Building or debugging a Qwen-VL vision task and you need the correct multimodal prompt format.
By the numbers
- Wraps image URLs as <img>url</img> for Qwen-VL
Files
Qwen Enhance
此 Skill 专为阿里云通义千问（Qwen）系列模型设计，提供多模态输入（Qwen-VL）和长文本处理的辅助工具。
能力描述
- 多模态适配：自动生成 Qwen-VL 的图片/文本混合 Prompt 格式（如
<img>url</img>）。 - Prompt 优化：针对 Qwen 的指令遵循能力进行 Prompt 调优。
典型用法
1. 生成视觉任务 Prompt：
python3 .trae/skills/qwen-enhance/scripts/qwen_vl.py "描述这张图片" "https://example.com/image.jpg"输出示例
<img>https://example.com/image.jpg</img> 描述这张图片{
"ownerId": "kn750bvaw1b5vwe14rnbv1zpr983hvdw",
"slug": "qwen-enhance",
"version": "1.0.0",
"publishedAt": 1774336292299
}{
"version": 1,
"registry": "https://clawhub.ai",
"slug": "qwen-enhance",
"installedVersion": "1.0.0",
"installedAt": 1776068538652
}
#!/usr/bin/env python3
import sys
def qwen_vl_prompt(text, image_url=None):
# Simulate Qwen-VL prompt structure
if image_url:
return f"<img>{image_url}</img> {text}"
return text
if __name__ == "__main__":
if len(sys.argv) > 1:
query = sys.argv[1]
img = sys.argv[2] if len(sys.argv) > 2 else None
print(qwen_vl_prompt(query, img))
else:
print("Usage: python3 qwen_vl.py <text> [image_url]")
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10