x402-creative-resourcesAccess Xona's x402 creative resource APIs on api.xona-agent.com. Includes creative director (design research), image generation (nano-banana, seedream, grok-...
Install via ClawdBot CLI:
clawdbot install xona-labs/x402-creative-resourcesAll endpoints live on https://api.xona-agent.com and are paid via x402 (Solana USDC micropayments). The agent wallet pays automatically.
Use the x402-fetch.js script in the workspace scripts folder. It handles the 402 payment flow automatically using the agent's Solana wallet.
node /home/node/.openclaw/workspace/scripts/x402-fetch.js <endpoint> [payload_json]
POST example:
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /image/creative-director '{"idea":"futuristic Solana DeFi dashboard"}'
GET example:
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /token/pumpfun-trending
The script outputs JSON. Parse the response and extract relevant fields (image_url, video_url, banner_url, etc.) to present to the user.
curl -s https://api.xona-agent.com/x402-resources
Research trending design ideas on X and Google, analyze user intent, return refined creative direction.
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /image/creative-director \
'{"idea":"futuristic Solana DeFi dashboard aesthetic","reference_images":["https://example.com/ref.jpg"]}'
| Field | Required | Description |
|-------|----------|-------------|
| idea | Yes | Creative idea or design research query |
| reference_images | No | Array of reference image URLs |
Response: { success, data: { intent, research, direction } }
The direction array contains generation plans with output_metadata.prompt — feed these into an image generation endpoint.
All image endpoints accept:
| Field | Required | Description |
|-------|----------|-------------|
| prompt | Yes | Detailed image description |
| aspect_ratio | No | 1:1 (default), 16:9, 9:16, 4:3, 3:4 |
| referenceImage | No | Array of reference image URLs |
All return: { success, data: { image_url, image_description, metadata } }
Also accepts style (array of keywords to blend into prompt).
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /image/designer \
'{"prompt":"a glowing Solana logo floating in space","style":["digital art","futuristic","neon"],"aspect_ratio":"16:9"}'
Artistic, handles text-in-image well. Cheapest option.
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /image/grok-imagine \
'{"prompt":"...","aspect_ratio":"1:1"}'
Balanced quality and cost.
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /image-model/qwen-image \
'{"prompt":"...","aspect_ratio":"1:1"}'
ByteDance photorealistic model. Best for high-detail, realistic images.
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /image-model/seedream-4.5 \
'{"prompt":"...","aspect_ratio":"1:1"}'
Fast creative generation. Good default.
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /image/nano-banana \
'{"prompt":"...","aspect_ratio":"1:1"}'
Highest quality.
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /image/nano-banana-pro \
'{"prompt":"...","aspect_ratio":"1:1"}'
| Model | Endpoint | Price | Best for |
|-------|----------|-------|----------|
| Grok Imagine | /image/grok-imagine | $0.04 | Artistic, text-in-image |
| Qwen Image | /image-model/qwen-image | $0.05 | Balanced quality/cost |
| Designer | /image/designer | $0.08 | Style-blended, art-directed |
| Seedream 4.5 | /image-model/seedream-4.5 | $0.08 | Photorealistic |
| Nano Banana | /image/nano-banana | $0.10 | Fast creative, good default |
| Nano Banana Pro | /image/nano-banana-pro | $0.20 | Highest quality |
10-second AI video using Grok Imagine Video. Supports text-to-video and image-to-video.
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /video/short-generation \
'{"prompt":"camera slowly orbiting a glowing Solana logo in deep space","aspect_ratio":"16:9"}'
For image-to-video, pass a previously generated image_url as image:
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /video/short-generation \
'{"prompt":"smooth zoom into center","aspect_ratio":"16:9","image":"https://cdn.example.com/img.jpg"}'
| Field | Required | Description |
|-------|----------|-------------|
| prompt | Yes | Video description with motion cues |
| aspect_ratio | No | Aspect ratio (default: 16:9) |
| image | No | Still image URL to animate |
Response: { success, data: { video_url, duration, model, metadata } }
Takes up to 5 minutes. Let the user know it's processing.
Extract latest news from any X account, generate tweet draft and banner.
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /ai/x-news \
'{"x_username":"solana"}'
| Field | Required | Description |
|-------|----------|-------------|
| x_username | Yes | X username (with or without @) |
| x_persona | No | X username whose style to mimic for tweet draft |
Response: { success, data: { x_username, trending_news: { title, tweet_draft, banner_url } } }
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /token/pumpfun-trending
Response: { success, data: { summary, suggestions, trending_tokens, count } }
node /home/node/.openclaw/workspace/scripts/x402-fetch.js /token/pumpfun-movers
Same response format as trending.
/image/creative-director with the user's ideadirection[].output_metadata.prompt to call an image endpointimage_url to /video/short-generation to animate it/ai/x-news with a target X accounttweet_draft and banner_url/token/pumpfun-trending for current meta/token/pumpfun-movers for biggest movesGenerated Mar 1, 2026
A marketing agency uses the skill to generate visual assets and research design trends for client campaigns. They can create branded images, videos, and social media banners quickly, leveraging the creative director for trend analysis and image generation for custom graphics, enhancing campaign creativity and speed.
A Solana-based crypto project utilizes the skill to produce promotional materials like token logos, explainer videos, and news updates. They can generate trending token intelligence from PumpFun and extract X news for community engagement, streamlining content creation for social media and websites.
An e-commerce business employs the skill to generate high-quality product images and videos for listings. Using image generation models like Seedream 4.5 for photorealistic visuals and video generation for demos, they can showcase products in various styles and aspects, boosting sales conversions.
An educational platform leverages the skill to create visual aids and instructional videos for courses. They can research design trends for engaging layouts, generate images to illustrate concepts, and produce short videos, making learning materials more interactive and appealing to students.
A social media manager uses the skill to curate and create content for platforms like X. They extract news from accounts, generate tweet drafts and banners, and produce images or videos for posts, enabling efficient content scheduling and trend-based engagement with followers.
Businesses integrate the skill via API calls, paying per request for specific services like image generation or news extraction. Revenue is generated from micropayments in USDC, with tiered pricing based on usage volume, appealing to clients needing flexible, on-demand creative tools.
A platform bundles the skill's endpoints into a subscription service for agencies or creators. Users pay a monthly fee for access to all features, including design research and media generation, with revenue from recurring subscriptions and potential upsells for premium support or higher usage limits.
Enterprises license the skill as a white-label solution to embed into their own products, such as marketing tools or content management systems. Revenue comes from licensing fees and customization services, allowing businesses to offer branded creative capabilities without developing in-house AI.
💬 Integration Tip
Use the provided x402-fetch.js script to handle payments automatically, and parse JSON responses to extract URLs like image_url or video_url for user presentation.
Display and control HTML content on connected Mac, iOS, or Android nodes via a web-based canvas with live reload and remote actions.
生成和编辑各种类型的图表(drawio、mermaid、excalidraw)。支持流程图、时序图、类图、ER图、思维导图、架构图、网络拓扑图等常见图表类型。能够根据自然语言描述创建新图表,也能读取并修改已有的 drawio/mermaid/excalidraw 文件。使用独立的 MCP server (mcp-diagram-generator) 生成图表文件,减少 token 消耗并保证输出一致性。支持自动配置管理,默认输出路径为项目目录下的 diagrams/{format}/,支持自定义路径和自动创建目录。
Create, export, and manage Canva designs via the Connect API. Generate social posts, carousels, and graphics programmatically.
Create software diagrams using Mermaid syntax. Use when users need to create, visualize, or document software through diagrams including class diagrams, sequence diagrams, flowcharts, ERDs, C4 architecture diagrams, state diagrams, git graphs, and other diagram types. Triggers include requests to diagram, visualize, model, map out, or show the flow of a system.
Generate and render diagrams from Mermaid syntax into PNG, SVG, or PDF using customizable themes and various diagram types.
Generate diagrams from descriptions with Mermaid, PlantUML, or ASCII for architecture, flows, sequences, and data models.