← Back to Skills Marketplace
SeaArt Image Generator
by
seaartpublic
· GitHub ↗
· v1.0.0
· MIT-0
108
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install seaart-image
Description
Use this skill to generate AI images using the SeaArt platform (seaart.ai). Supports text-to-image generation with multiple models, custom dimensions, LoRA m...
Usage Guidance
This skill appears to do what it says: it needs your SeaArt session token (the 'T' cookie) and uses it to call seaart.ai to generate images. Before installing: (1) only provide the SEAART_TOKEN if you trust this skill and you understand it will be stored in your agent config; (2) consider creating and using a dedicated SeaArt account or token with limited usage if possible; (3) protect the agent config file (it will contain the token) and avoid pasting the token into chat; (4) confirm the small documentation mismatch about the default model with the author if model defaults matter to you. If you are uncomfortable persisting a browser cookie as an env var, do not install or grant the token.
Capability Analysis
Type: OpenClaw Skill
Name: seaart-image
Version: 1.0.0
The seaart-image skill enables AI image generation via the SeaArt.ai platform. It requires a user-provided session token (SEAART_TOKEN) which is used exclusively to authenticate requests to official SeaArt endpoints (seaart.ai and seaart.me). The Python script (scripts/generate.py) implements standard API interaction logic using the requests library, including task submission and status polling. The documentation (SKILL.md) provides clear instructions and security warnings regarding token handling, and no evidence of data exfiltration, malicious execution, or harmful prompt injection was found.
Capability Assessment
Purpose & Capability
The skill needs a SeaArt session token (the T cookie) and a Python runtime; the included script calls SeaArt APIs (text-to-img and batch-progress). These requirements match the described functionality.
Instruction Scope
SKILL.md instructs the agent to check the SEAART_TOKEN env var, guide the user to extract the T cookie from browser DevTools, and persist it via /update-config. This is expected for a web-account-based integration, but there is a minor inconsistency in the doc about the default model (the top of the doc lists SeaArt Infinity as default, another spot mentions a different default). The instructions do not ask the agent to read unrelated files or exfiltrate data to other endpoints.
Install Mechanism
No install spec; this is instruction-only with a provided Python script. It relies on standard Python and requests. No downloads from arbitrary URLs or archive extraction are present.
Credentials
The only sensitive environment value used is SEAART_TOKEN (the T cookie), which is proportionate to the skill's purpose. Registry metadata shows an unclear 'Required env vars: [object Object]' entry (parser glitch) but SKILL.md and the script clearly declare and use SEAART_TOKEN as the primary secret.
Persistence & Privilege
The skill recommends persisting SEAART_TOKEN in the agent config via /update-config so the agent can use it later. Persisting an account token is normal for convenience but increases the impact if the agent config is accessible — users should ensure the agent config is stored securely. The skill does not request 'always: true' or modify other skills.
How to Use
- Make sure OpenClaw is installed (local or Docker)
- Run the install command in chat:
/install seaart-image - After installation, invoke the skill by name or use
/seaart-image - Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
Initial release of SeaArt Image Generator skill. Features: 14 built-in models (SeaArt Infinity, Film series, Seedream series, Nano Banana series, Grok Imagine, Z Image Turbo, WAI-ANI-PONYXL), smart HD/SD resolution auto-scaling, 7 aspect ratios, LoRA support, negative prompts, and custom model support via URL.
Metadata
Frequently Asked Questions
What is SeaArt Image Generator?
Use this skill to generate AI images using the SeaArt platform (seaart.ai). Supports text-to-image generation with multiple models, custom dimensions, LoRA m... It is an AI Agent Skill for Claude Code / OpenClaw, with 108 downloads so far.
How do I install SeaArt Image Generator?
Run "/install seaart-image" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.
Is SeaArt Image Generator free?
Yes, SeaArt Image Generator is completely free, licensed under MIT-0. You can download, install and use it at no cost.
Which platforms does SeaArt Image Generator support?
SeaArt Image Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).
Who created SeaArt Image Generator?
It is built and maintained by seaartpublic (@seaartpublic); the current version is v1.0.0.
More Skills