← Back to Skills Marketplace
irron

qwenz-image-gen

by irron · GitHub ↗ · v1.0.1
cross-platform ⚠ suspicious
963
Downloads
1
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install qwenz-image-gen
Description
Generate images using Alibaba Cloud Bailian Qwen-Image and Z-Image models (通义千图文生图 + 人像照片模型)
Usage Guidance
This skill appears to do what it says (call Alibaba Bailian image APIs), but review how it obtains your API key before installing. Prefer setting DASHSCOPE_API_KEY as an environment variable rather than placing secrets in shared TOOLS.md files. If you must use TOOLS.md, inspect its contents and location — the script will search: the current working directory's TOOLS.md, a TOOLS.md located four directories above the script, and /home/admin/clawd/TOOLS.md. Those extra paths could cause the skill to read unintended files that may contain other secrets. Run the script in a restricted project workspace or container, verify the API hostname (dashscope.aliyuncs.com) matches your provider, and consider manually supplying the key to avoid accidental disclosure.
Capability Analysis
Type: OpenClaw Skill Name: qwenz-image-gen Version: 1.0.1 The skill is designed to generate images using Alibaba Cloud's Qwen-Image and Z-Image models. It retrieves the `DASHSCOPE_API_KEY` from environment variables or `TOOLS.md`, which is a standard and expected practice for OpenClaw skills. Network communication is exclusively with the legitimate Alibaba Cloud DashScope API (`dashscope.aliyuncs.com`) for image generation and retrieval. The `SKILL.md` provides clear instructions for the user and does not contain any prompt injection attempts against the OpenClaw agent. All file system and network operations are directly aligned with the stated purpose, with no evidence of malicious intent, data exfiltration, or unauthorized execution.
Capability Assessment
Purpose & Capability
Name/description match the observed behavior: the script calls dashscope.aliyuncs.com and requests image generation from Qwen-Image / Z-Image models. Model selection, sizes, and CLI options align with the stated purpose.
Instruction Scope
SKILL.md and the script instruct the agent to obtain DASHSCOPE_API_KEY from the environment or a TOOLS.md file. The code looks for TOOLS.md in the current working directory, an upward traversal path (four parents up from the script), and a hard-coded /home/admin/clawd/TOOLS.md — these extra filesystem probes are not documented in SKILL.md and may read files outside the skill's intended workspace.
Install Mechanism
There is no install spec (instruction-only plus a single script). Nothing is downloaded or written by an installer; the script is executed directly, which is low risk compared with arbitrary remote installs.
Credentials
The skill requires a single credential (DASHSCOPE_API_KEY), which is appropriate for calling the external API. The script uses the key solely as a Bearer token to call the Aliyun endpoint.
Persistence & Privilege
always is false and the skill does not request persistent platform-wide privileges. It does write generated images to disk (user-specified or timestamped filenames) which is expected behavior.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install qwenz-image-gen
  3. After installation, invoke the skill by name or use /qwenz-image-gen
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.1
- Added SKILL.md with detailed instructions for using Alibaba Cloud Bailian Qwen-Image and Z-Image models. - Describes automatic model selection based on scenario (portrait vs. general images). - Lists features, setup steps, available models, supported image sizes, usage examples, and tips. - Specifies API key configuration for model access. - Outlines advanced options, prompt examples, and keyword-based auto-detection behavior. - Documentation provided in Chinese for optimal user guidance.
Metadata
Slug qwenz-image-gen
Version 1.0.1
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is qwenz-image-gen?

Generate images using Alibaba Cloud Bailian Qwen-Image and Z-Image models (通义千图文生图 + 人像照片模型). It is an AI Agent Skill for Claude Code / OpenClaw, with 963 downloads so far.

How do I install qwenz-image-gen?

Run "/install qwenz-image-gen" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is qwenz-image-gen free?

Yes, qwenz-image-gen is completely free (open-source). You can download, install and use it at no cost.

Which platforms does qwenz-image-gen support?

qwenz-image-gen is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created qwenz-image-gen?

It is built and maintained by irron (@irron); the current version is v1.0.1.

💬 Comments