← Back to Skills Marketplace
killingjacky

SenseCraft HMI Web Content Generator

by Jack Shao · GitHub ↗ · v1.0.0
cross-platform ✓ Security Clean
333
Downloads
0
Stars
0
Active Installs
1
Versions
Install in OpenClaw
/install sensecraft-hmi-gen
Description
Generate beautiful web content for SenseCraft HMI e-ink displays. AI-powered layout selection, e-ink optimization. Creates artistic, minimalist pages optimiz...
README (SKILL.md)

SenseCraft HMI Web Content Generator

Generate stunning, e-ink optimized web content with AI-powered design.

Philosophy

E-ink screens are digital art pieces, not web pages.

Inspired by Kindle screensavers and minimalist posters. Every page should be beautiful enough to frame.


AI Workflow

When the user requests to generate e-ink screen content, execute according to the following workflow:

Step 1: Study Reference Files and Keep Them in Mind

Read design reference files (mandatory):

Design Philosophy - {baseDir}/references/design-patterns.md

10 Classic Layout References - {baseDir}/references/layouts.md, but do not limit yourself to these layouts. Specifically, when the user provides layout ideas, follow the user's instructions.

Step 2: Guide the User to Answer Necessary Configuration Information

If the user is conversing with you via a webchat channel, call the wizard.js script. This script will serve a web page at http://localhost:39527/ and pop up this visual configuration interface in the user's browser. The script will automatically exit once the user completes the configuration. The script will create a {baseDir}/data/.wizard-config.json file to save the configuration information.

If the user is using a remote conversation channel like Discord, use dialogue to ask the user for the following information:

  • Screen size and color support
  • The user's ideas about the layout

These configuration details will be saved in the {baseDir}/data/.wizard-config.json file. Subsequent workflows should follow these configurations, such as the size of the generated web page, color support, etc.

Step 3: Prepare Content

Text Content:

  • AI generates content based on user requests (quotes, poems, weather info, etc.)
  • Or use content provided by the user

Image Content (if the user's request explicitly mentions the need for images):

Ask the user for the image source:

  • User provides image URL
  • User provides local image
  • If openclaw is configured with a text-to-image large model, call it to generate an image

Image storage path: {baseDir}/data/public/images/

Step 4: Generate HTML

Generate an HTML file based on the user's requirements and store it in the {baseDir}/data/ directory. The HTML file can contain Javascript, and the image paths referenced in the HTML should be ./public/images/.

Please embed CSS directly into the HTML file. If you need to reference a CSS framework like Bootstrap, use the CDN link for the CSS file.

Please embed Javascript scripts directly into the HTML file. If you need to reference a JS framework like jQuery, use the CDN link for the JS file.

Primary rules for the web page:

  • The pixel count of the entire web page's visible area must match the screen size exactly; there should be no scrolling controls.
  • The colors used in the web page should not exceed the color support capabilities of the screen. This includes controlling the background color, text color, image color, etc., using CSS.

Design philosophy and layout references:

  • {baseDir}/references/design-patterns.md
  • {baseDir}/references/layouts.md

Step 5: Start server.js

We use pm2 to manage the http server.

# Start service
pm2 start {baseDir}/data/server.js --name sensecraft-hmi

# Stop service
pm2 stop sensecraft-hmi

# View logs
pm2 logs sensecraft-hmi

# Access address
http://localhost:19527/?token=XXXXX

After the server starts, automatically open a browser to visit http://localhost:19527/?token=XXXXX so the user can see the generated web page. Also, prompt the user in the chat interface that they can open the http://localhost:19527/?token=XXXXX link to view the web page effect in real-time.

Step 6: Reverse Proxy

Guide the user to use a reverse proxy tool to forward http://localhost:19527 to the public network, and then use the html widget in the SenseCraft HMI platform to display the web page.

Reverse proxy tools include: frp, ngrok, cloudflare tunnel, etc. Encourage users to use HTTP forwarding rather than TCP forwarding because HTTP is more secure.

Due to openclaw skill security review reasons, this skill does not provide the binary of reverse proxy tools. Please ask the user to search, download, and use them on their own.


Tool List

Tool Description Usage
init_project.js Project initialization node {baseDir}/scripts/init_project.js
wizard.js Configuration wizard server node {baseDir}/scripts/wizard.js

10 Classic Layouts

See references/layouts.md for detailed specs.

Layout ID Use Case
Minimalist Center minimalCenter Quotes, maxims, single words
Info Card infoCard Poetry, elegant text
Dashboard Grid dashboardGrid Weather, stocks, data
Comic Fullscreen comicFullscreen Comics, artwork
Calendar Grid calendarGrid Calendars, schedules
News List newsList News, RSS, to-do lists
Split Layout splitLayout Sidebar + main content
Big Number bigNumber Clocks, countdowns
Image & Text imageText Images + captions
Newspaper Front newspaperFront News summaries

Scheduled Updates

If the user's request includes scheduled tasks, there are 3 approaches:

  1. Use OpenClaw cron to update content on a schedule, suitable when each update's content varies significantly
openclaw cron add --name "daily-summary" --schedule "0 9 * * *" \
  --task "Generate a work summary based on Notion"
  1. Embed Javascript scripts within the HTML file to dynamically update content, suitable for pulling data from APIs

  2. Write background services in a Node.js Express backend using templating technologies or frameworks like React to push data from backend to frontend, suitable for particularly complex content updates


Files Structure

sensecraft-hmi-gen/
├── SKILL.md                    # This file (current file)
├── data/                       # Source files for AI-generated web pages
│   ├── server.js               # Express server
│   ├── index.html              # Currently displayed content
│   ├── .token                  # Access token
│   ├── public/images/          # Image resources (optional)
│   ├── public/css/             # CSS resources (optional)
│   └── public/js/              # JS resources (optional)
├── scripts/
│   ├── init_project.js         # Project initialization
│   ├── wizard.js               # Configuration wizard server (Frontend + Backend)
└── references/
    ├── layouts.md              # Detailed layout specifications
    ├── design-patterns.md      # Design patterns and aesthetics
    └── screen-specs.md         # Hardware specifications


Tips

  • Let AI be creative - Don't force templates, let design flow from content
  • Read design references - design-patterns.md and layouts.md are your inspiration
  • Go bigger than you think - fonts that look huge on screen look perfect on e-ink
  • Test with actual device - e-ink looks different than LCD
  • Embrace whitespace - it's not wasted space, it's elegance

Troubleshooting

Issue Solution
Text too small Minimum 32px, headings 60px+
Blurry images Apply color dithering to images to make them better suited for e-ink displays
Crowded layout Increase padding to 40-60px
Service inaccessible Check token, run pm2 restart sensecraft-hmi
Usage Guidance
This skill is coherent with its stated purpose, but take these precautions before using it: - Review the server.js and wizard.js files locally (they are included) so you understand what will be written and served; the init script will create files under {baseDir}/data and run npm install express when invoked. - The skill's workflow recommends exposing http://localhost:19527 (with a token query) to the public internet using tunnels (ngrok, frp, Cloudflare Tunnel). Exposing a local service has real risk: anyone who obtains the tokenized URL can view the page and any files you serve. Only publish if you understand and accept that exposure and rotate/regenerate tokens if needed. - Prefer secure tunneling configuration: use authenticated tunnels, restrict origins where possible, and avoid forwarding ports that allow access to other local services. Do not use TCP tunnels that might expose other ports. - The init script uses npm to install express and uses child_process.execSync; run these scripts in a controlled environment and inspect output before executing. If you do not want files created on disk, do not run init_project.js. - The SKILL.md suggests using pm2 but does not install it — installing global process managers requires elevated privileges and should be done intentionally. - If you intend to use any text-to-image model integration mentioned in the docs, confirm that your OpenClaw instance or environment is configured securely and that any generated images are stored only in the intended data/public/images/ directory. - If you are unsure, run the skill in an isolated machine/container or review the code with someone who knows Node.js. If you want tighter security, avoid exposing the service publicly and use local previews only.
Capability Analysis
Type: OpenClaw Skill Name: sensecraft-hmi-gen Version: 1.0.0 The sensecraft-hmi-gen skill bundle is a legitimate tool designed to generate and serve e-ink optimized web content for SenseCraft HMI displays. It follows a transparent workflow involving a configuration wizard (wizard.js), project initialization (init_project.js), and a local Express server with token-based authentication. While the skill performs high-risk actions such as executing shell commands (npm, pm2) and starting a network service, these are well-documented and essential to its stated purpose. No evidence of malicious intent, data exfiltration, or prompt injection attacks was found.
Capability Assessment
Purpose & Capability
The name/description (e-ink web content generator) matches the shipped files and runtime behavior: design references, layout templates, a configuration wizard, code to create a local project, and a local HTTP server that hosts generated HTML. Dependencies (Node/npm/express, pm2 optionally for process management) are reasonable for this purpose.
Instruction Scope
Runtime instructions are focused on reading the shipped reference docs, prompting the user for screen/layout choices, generating HTML into a local data directory, and serving it via a local HTTP server. The SKILL.md additionally instructs starting the server with pm2 and recommends exposing localhost through reverse-proxy/tunneling tools (ngrok, frp, cloudflare tunnel) — functionally coherent but increases blast radius because it tells the user to publish a local service to the public internet and embed a token in a URL.
Install Mechanism
There is no platform install spec (instruction-only), but the included init_project.js will run npm init and npm install express in the skill's data directory when invoked, and it writes a server.js file to disk. Using npm to fetch express is expected, but the script performs disk writes and spawns child processes (execSync). This is coherent with the skill's runtime needs but is higher-risk than a purely instruction-only skill because it creates files and pulls packages at runtime.
Credentials
The skill declares no required environment variables, credentials, or config paths. The runtime files operate only on files under the skill's baseDir/data and the shipped references; no unrelated cloud credentials or system tokens are requested.
Persistence & Privilege
always is false and autonomous invocation is allowed (normal). The skill instructs the user to run a long‑running local HTTP service (pm2 suggested) and to expose it via tunnels; that grants the skill the ability to host content persistently while pm2 is running, but it does not request system-wide config changes or modify other skills. Running a background server is within scope but increases persistence and exposure.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install sensecraft-hmi-gen
  3. After installation, invoke the skill by name or use /sensecraft-hmi-gen
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v1.0.0
SenseCraft HMI Web Content Generator – Initial Release - Generate beautiful, minimalist webpages optimized for SenseCraft e-ink screen sizes (800x480 to 1600x1200) - AI-powered layout selection, referencing design-patterns.md and layouts.md for inspiration - Interactive configuration wizard or chat guidance for screen sizing, color, and layout preferences - Automatic image handling via user upload, URL, or AI text-to-image (if available) - Exports fully responsive HTML/CSS/JS with support for scheduled content updates - Includes instructions for local server launch, browser preview, and reverse proxy setup for remote access
Metadata
Slug sensecraft-hmi-gen
Version 1.0.0
License
All-time Installs 0
Active Installs 0
Total Versions 1
Frequently Asked Questions

What is SenseCraft HMI Web Content Generator?

Generate beautiful web content for SenseCraft HMI e-ink displays. AI-powered layout selection, e-ink optimization. Creates artistic, minimalist pages optimiz... It is an AI Agent Skill for Claude Code / OpenClaw, with 333 downloads so far.

How do I install SenseCraft HMI Web Content Generator?

Run "/install sensecraft-hmi-gen" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is SenseCraft HMI Web Content Generator free?

Yes, SenseCraft HMI Web Content Generator is completely free (open-source). You can download, install and use it at no cost.

Which platforms does SenseCraft HMI Web Content Generator support?

SenseCraft HMI Web Content Generator is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created SenseCraft HMI Web Content Generator?

It is built and maintained by Jack Shao (@killingjacky); the current version is v1.0.0.

💬 Comments