An automated utility for AI agents to package, publish, and manage web prototypes on the ProtoHub platform.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tc-protohub
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install tc-protohub using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is ProtoHub AI Agent Integration?
The ProtoHub AI Agent Integration is a specialized toolset designed to streamline the lifecycle of web prototypes. By leveraging Openclaw Skills, developers can enable AI agents to handle complex tasks such as directory packaging, entry point validation, and automated deployments to the ProtoHub Private Sandbox. This integration ensures that every upload is formatted correctly and contains the necessary entry files, significantly reducing manual overhead during the design and development iteration phases.
This skill serves as a bridge between your local development environment and the ProtoHub server, allowing for seamless updates to existing prototypes or the creation of new ones via simple CLI commands. It provides a robust framework for managing digital assets with built-in safeguards against common deployment errors, such as missing index files or incorrect authentication headers.
ProtoHub AI Agent Integration Use Cases
- Automatically packaging a build directory and uploading it as a new prototype.
- Updating a specific prototype version using its ID or searchable name.
- Quickly retrieving preview URLs to share functional prototypes with stakeholders.
- Searching and listing existing prototypes to manage a growing library of project versions.
How ProtoHub AI Agent Integration Works
- The AI Agent identifies the target directory or ZIP file that needs to be published.
- The system performs a mandatory check for the presence of index.html at the root to ensure valid previews.
- Environment variables (API Key and URL) are verified to establish a secure connection to ProtoHub.
- The agent executes the publish script to package the files and transmit them to the designated server.
- If an update is requested without an ID, the skill searches for matching prototype names to identify the correct target.
- Upon completion, the system returns the prototype ID and a direct preview link for the user.
ProtoHub AI Agent Integration Setup
To begin using this skill, you must configure your environment with your ProtoHub credentials. These Openclaw Skills require the following variables to be set in your terminal or environment configuration:
export PROTOHUB_API_KEY="your-api-key"
export PROTOHUB_URL="http://your-protohub-instance:48080"
You can then use the provided Python script to interact with the API:
python skills/tc-protohub/scripts/publish.py publish ./dist-folder --name "Project-X"
ProtoHub AI Agent Integration Data Schema & Taxonomy
The skill interacts with the ProtoHub API using a structured schema to ensure data integrity. Below is the metadata and file requirements taxonomy:
| Attribute | Description | Requirement |
|---|---|---|
PROTOHUB_API_KEY |
Secure token for API authentication | Mandatory |
index.html |
Entry point file at the root of the upload | Mandatory |
prototypeId |
Unique integer identifier for updates | Optional (auto-generated for new) |
name |
Human-readable title for the prototype | Required for new uploads |
url |
Base endpoint for the ProtoHub server | Mandatory (default provided) |
ProtoHub AI Agent Integration Advanced Features
- Intelligent Name-to-ID Mapping: Automatically finds the correct prototype ID when users refer to a project by its name.
- Pre-upload Validation: Aborts the process if the index.html file is missing, preventing broken links and wasted bandwidth.
- Automated ZIP Compression: Transparently handles the packaging of folders into ZIP format before transmission.
- Headless Discovery: Allows agents to list and filter prototypes programmatically to maintain sync between local and remote states.
SKILL.md
Loading
Related Openclaw Skills
Aqara Open API Skill
A professional-grade interface for controlling Aqara smart home hardware and managing spatial hierarchies via the Aqara Open Platform API.
Polymarket Alpha Suite
A suite of 6 institutional-grade trading tools for Polymarket prediction markets featuring arbitrage, scalping, and alpha detection algorithms.
Square Post
A specialized AI agent skill designed to automate text-based posting to the Binance Square social platform.
Movie Subtitle Viewer Skill
An AI agent skill that enables searching, downloading, and parsing movie subtitles to provide automated plot summaries and dialogue analysis.
Web Fetcher
A smart extraction engine that automatically detects platforms to download articles or high-quality videos with ease.
Agent Control
A command-driven interface for orchestrating isolated OpenClaw agents directly through chat shorthand.
Featured*
