← Back to Skills Marketplace
502
Downloads
1
Stars
0
Active Installs
8
Versions
Install in OpenClaw
/install wuli
Description
Generate AI images and videos with 17+ active models via Wuli.art open platform API. Use when creating images from text prompts, editing images with one or m...
Usage Guidance
This skill appears to do what it says: it calls Wuli.art APIs, uploads any local files you give it, and may download remote URLs you provide before re-uploading them to Wuli's OSS. Before installing/using: (1) only set WULI_API_TOKEN obtained from the official wuli.art site; (2) do not upload sensitive or private media (uploads go to the third party and API calls consume credits); (3) avoid passing untrusted remote URLs (the skill will fetch them); (4) review the included skill.py if you want to confirm behavior, and run the skill in an isolated environment if you are concerned about handling unknown media or automatically opening downloaded files.
Capability Analysis
Type: OpenClaw Skill
Name: wuli
Version: 1.0.7
The 'wuli' skill bundle is a legitimate integration for the Wuli.art AI generation platform. The core logic in `skill.py` uses Python's standard library to facilitate image and video generation by uploading media to the platform's OSS storage and polling for results. The code is well-documented, lacks obfuscation, and its behaviors (network access, file uploads, and opening results via system defaults) are entirely consistent with its stated purpose.
Capability Tags
Capability Assessment
Purpose & Capability
Name/description match the declared requirements: only a WULI_API_TOKEN is required and python3 is listed as the runtime. The token is the expected credential for calling the Wuli.art platform API.
Instruction Scope
SKILL.md and skill.py instruct the agent to upload local files and to download remote media and re-upload it to Wuli OSS (using pre-signed URLs returned by the platform). This is expected for a media-generation skill, but means local files and any remote URLs you supply will be transmitted to the third-party service.
Install Mechanism
No install spec; the skill is instruction + a single Python script and uses only standard library modules. No external downloads or suspicious installers are present.
Credentials
Only the WULI_API_TOKEN is required (declared as primaryEnv). No unrelated secrets, config paths, or extra environment variables are requested.
Persistence & Privilege
always is false and the skill does not request permanent platform-level privileges. It does open downloaded result files with the OS viewer (subprocess/os.startfile/xdg-open), which is normal for a CLI utility but worth noting.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install wuli - After installation, invoke the skill by name or use
/wuli - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.7
ci: pin publish slug to 'wuli'
v1.0.6
wuli 1.0.6
- Added support for 17+ active models, including new models like Seedream 5.0 Lite and 可灵 3.0 Omni.
- Introduced new video generation modes: first-last-frame video (flf2video) and auto-video (auto-video) from images and videos.
- Enhanced input flexibility: multiple reference images and/or videos can be used for applicable actions; parameter support for start/end frames and multiple file uploads or URLs.
- Improved sound control for supported video models, with explicit --sound and --no-sound flags.
- Updated documentation, usage instructions, and API references for new actions and input rules.
- Deprecated and removed outdated reference materials in favor of updated API docs.
v1.0.5
Fix: add WULI_API_TOKEN to clawdbot requires.env and primaryEnv so registry correctly surfaces required credential
v1.0.4
Fix: add requires.env frontmatter so registry correctly shows WULI_API_TOKEN as required credential
v1.0.3
Set display name to Wuli
v1.0.2
Fix: declare WULI_API_TOKEN as required env var, add privacy note about file uploads, fix license to MIT-0
v0.1.1
wuli 0.1.1
- Updated version to 1.0.1 in SKILL.md to match manifest.
- No feature or functional changes. Documentation now accurately reflects the current version.
v0.1.0
Initial release of the Wuli skill for AI image and video generation.
- Generate AI images and videos from text prompts using 15+ models via the Wuli.art API.
- Supports text-to-image, image editing, text-to-video, image-to-video, batch generation, and prompt optimization.
- Users can choose models for specific needs (e.g., Qwen Image, Seedream, Wan Xiang, Kling, Seedance, MiniMax Hailuo).
- Output options include high-resolution (up to 4K) images and HD/1080P video, including no-watermark downloads.
- Command-line interface with clear parameters for rapid integration and control.
Metadata
Frequently Asked Questions
What is Wuli Skill?
Generate AI images and videos with 17+ active models via Wuli.art open platform API. Use when creating images from text prompts, editing images with one or m... It is an AI Agent Skill for Claude Code / OpenClaw, with 502 downloads so far.
How do I install Wuli Skill?
Run "/install wuli" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is Wuli Skill free?
Yes, Wuli Skill is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does Wuli Skill support?
Wuli Skill is cross-platform and runs anywhere OpenClaw / Claude Code is available (linux, darwin, win32).
Who created Wuli Skill?
It is built and maintained by zihao chu (@sir1st-inc); the current version is v1.0.7.
More Skills