glm-image
Generate images using GLM-Image API. Use when the user wants to generate, create, or draw an image from a text prompt. Triggers on requests like "generate an image of...", "create a picture of...", "draw...", or any image generation request.
Why use this skill?
Add image generation capabilities to your OpenClaw agent. Supports GLM and OpenRouter for creating high-quality AI art from text prompts quickly and easily.
Install via CLI (Recommended)
clawhub install openclaw/skills/skills/chunhualiao/glm-imageWhat This Skill Does
The glm-image skill is a powerful extension for the OpenClaw AI agent that enables high-quality image generation directly from your terminal or AI interface. By leveraging industry-leading APIs like GLM (Zhipu AI) or OpenRouter, the agent can translate natural language descriptions into creative visual assets. Whether you are drafting conceptual art, visualizing data points, or simply experimenting with generative AI, this skill streamlines the entire creative workflow within the OpenClaw ecosystem.
Installation
To integrate this skill into your environment, use the OpenClaw installation manager:
clawhub install openclaw/skills/skills/chunhualiao/glm-image
Once installed, ensure you have an active API key from either Zhipu AI (BigModel) or OpenRouter. You can manage these keys via your environment variables or the ~/.openclaw/config.json configuration file. Refer to the documentation for your specific provider to complete the authentication setup before triggering your first generation.
Use Cases
The glm-image skill is designed for versatility. Typical use cases include:
- Conceptual Design: Generate rapid prototypes or mood boards for web and graphic design projects.
- Content Creation: Produce unique illustrations, backgrounds, or social media imagery based on specific thematic prompts.
- Visual Aid Generation: Create descriptive images to accompany technical documentation or presentations.
- Creative Experimentation: Explore how different model parameters and prompt engineering techniques affect visual output.
Example Prompts
- "Generate an image of a futuristic city with neon lights and flying cars."
- "Create a picture of a calm forest landscape during autumn in a watercolor style."
- "Draw a minimalist logo for a tech startup focusing on artificial intelligence."
Tips & Limitations
- Mandatory Language Selection: Always specify the language code (e.g., 'en', 'zh', 'ja') when prompted. The skill requires this to correctly interpret prompt nuances and generate the best possible imagery.
- Provider Preference: If you have both keys configured, the system defaults to GLM. You can override this using the
--provider openrouterflag. - API Limits: Be mindful of your provider's rate limits and subscription tier. Large batches of generation requests may impact your API quota.
- Prompt Quality: For better results, describe the subject, style, lighting, and composition explicitly in your prompt.
Metadata
Not sure this is the right skill?
Describe what you want to build — we'll match you to the best skill from 16,000+ options.
Find the right skillPaste this into your clawhub.json to enable this plugin.
{
"plugins": {
"official-chunhualiao-glm-image": {
"enabled": true,
"auto_update": true
}
}
}Tags(AI)
Flags: external-api, code-execution
Related Skills
task-runner
Persistent task queue system. Users add tasks at any time via natural language; tasks are stored in a single persistent queue file and executed asynchronously via subagents. A heartbeat/cron dispatcher wakes periodically to check pending tasks, spawn workers, and report completions. The system never "finishes" — it always remains ready for the next task.
git-repo-to-book
Write a full-length technical book using multi-agent AI orchestration. Spawns parallel research, writing, and review agents to produce 60K-100K+ word manuscripts. Also supports revising individual chapters of existing books. Based on the real workflow that produced an 88,000-word, 14-chapter book in under 18 hours.
claude-usage
Check Claude Max plan usage limits by launching Claude Code and running /usage. Use when the user asks about Claude plan usage, remaining quota, rate limits, or sends /claude_usage.
skill-engineer
Design, test, review, and maintain agent skills for OpenClaw systems using multi-agent iterative refinement. Orchestrates Designer, Reviewer, and Tester subagents for quality-gated skill development. Use when user asks to "design skill", "review skill", "test skill", "audit skills", "refactor skill", or mentions "agent kit quality".
deepwiki
Query DeepWiki MCP to get AI-grounded answers about any public GitHub repository. Use when answering questions about a repo's source code, architecture, configuration, or internals. Triggers on "how does X work in <repo>", "deepwiki", "look up in codebase", "ask deepwiki", "check the source code".