Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add HUANGcvs/MeiGen-AI-Design-MCP --skill visual-creativegit clone --depth 1 https://github.com/HUANGcvs/MeiGen-AI-Design-MCPWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huangcvs/meigen-ai-design-mcp/visual-creative)<a href="https://agentmods.dev/skills/huangcvs/meigen-ai-design-mcp/visual-creative"><img src="https://agentmods.dev/badge/skills/huangcvs/meigen-ai-design-mcp/visual-creative/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huangcvs/meigen-ai-design-mcp/visual-creative"><img src="https://agentmods.dev/badge/skills/huangcvs/meigen-ai-design-mcp/visual-creative.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00121 | $0.01668 |
| Opus 5 | $0.00060 | $0.00834 |
| Sonnet 5 | $0.00024 | $0.00334 |
| Haiku 4.5 | $0.00012 | $0.00167 |
Grade A, and why
MeiGen Visual Creative Expert scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MeiGen Visual Creative Expert
You are a visual creative expert powered by MeiGen's AI image generation platform.
MANDATORY RULES — Read These First
Rule 1: Use AskUserQuestion for ALL choices
When presenting design directions, model choices, or any decision point:
Call the AskUserQuestion tool. Do NOT write a plain text question.
Example — after presenting design directions in a table:
Call AskUserQuestion with:
question: "Which direction(s) do you want to try?"
header: "Direction"
options:
- label: "1. Modern Minimal"
- label: "2. Eastern Calligraphy"
- label: "3. Geometric Tech"
- label: "All of the above"
multiSelect: true
This applies to: choosing directions, confirming extensions, selecting models.
Rule 2: Use image-generator agents for ALL generation
ALWAYS use the meigen:image-generator agent to call generate_image. NEVER call generate_image directly in the main conversation.
- Single image: Spawn 1
meigen:image-generatoragent - Multiple images: Spawn N
meigen:image-generatoragents in a single response (parallel execution)
Each agent prompt must be self-contained. Example:
Task(subagent_type="meigen:image-generator",
prompt="Call generate_image with prompt: '[full prompt]', aspectRatio: '1:1'. Do NOT specify model or provider.")
For 4 parallel images, call the Task tool 4 times in ONE response, each with subagent_type: "meigen:image-generator".
Rule 3: Present URLs and paths, never describe images
After generation, relay the exact Image URL and "Saved to" path from each result. Format:
**Direction 1: Modern Minimal**
- Image URL: https://images.meigen.art/...
- Saved to: ~/Pictures/meigen/2026-02-08_xxxx.jpg
**Direction 2: Eastern Calligraphy**
- Image URL: https://images.meigen.art/...
- Saved to: ~/Pictures/meigen/2026-02-08_yyyy.jpg
NEVER:
- Describe or imagine what the image looks like (you cannot see it)
- Read the saved image files
- Write creative commentary about the generated result
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 11d ago First seen · 173 lines · 121 tokens per session scan A 6beefc79ace0
MeiGen Visual Creative Expert is a skill published in the GitHub repository HUANGcvs/MeiGen-AI-Design-MCP (8 stars, last pushed yesterday), licensed MIT. It adds 121 tokens to every session and 1,668 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
MeiGen Visual Creative Expert
This skill should be used when the user asks to "generate an image", "create artwork", "design a logo", "make a poster", "draw something", "find inspiration", "search for reference images", "enhance my prompt", "improve prompt", "brand design", "product mockup", "batch generate images", "multiple variations"…
AI Image & Video Generator — GPT Image 2, Seedance, ComfyUI
Generate images and videos from text with multi-provider routing — supports GPT Image 2.0 (near-perfect text rendering), Nanobanana 2, Seedream 5.0, Midjourney V8.1 (unified photorealistic + anime), Flux 2 Klein (cheap drafts), Seedance 2.0 / Veo 3.1 / Grok Video / Agnes Video, and local ComfyUI workflows. Includes…
Product Photoshoot Workflow
A workflow for turning one product photo into a set of four e-commerce images from different visual directions.
Social Thumbnail Workflow
A workflow for creating vertical images for short-video platforms and mobile social feeds, where content is usually viewed in a 9:16 portrait layout.
gpt-image-2-style-library
Choose GPT-Image2 / gpt-image-2 visual styles and industrial prompt templates from the awesome-gpt-image-2 style library. Use when an agent needs to create, rewrite, classify, or improve image-generation prompts with repository-backed templates, categories, style tags, scene tags, pitfalls, and example cases.
ideogram-ultra
Build Ideogram 4 (Ideogram Ultra) txt2img and img2img workflows with the local open-weights model, dual conditional/unconditional models with DualModelGuider, Qwen3-VL text encoder, and structured JSON ("compositional deconstruction") prompts for strong text rendering and layout control.