ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified developer tools Safety 3/5

clawdirect-dev

Build agent-facing web experiences with ATXP-based authentication, following the ClawDirect pattern. Use this skill when building websites that AI agents interact with via MCP tools, implementing cookie-based agent auth, or creating agent skills for web apps. Provides templates using @longrun/turtle, Express, SQLite, and ATXP.

Why use this skill?

Create AI agent-facing websites using ClawDirect-Dev. Implement ATXP authentication, MCP tools, and secure session management for AI browser automation.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/napoleond/clawdirect-dev
Or

What This Skill Does

ClawDirect-Dev is a specialized framework designed for developers building web-based experiences specifically for AI agents. It bridges the gap between traditional web environments and agent-driven workflows by implementing the Agent Transaction Protocol (ATXP). This allows your web applications to verify agent identities, process payments for premium actions, and expose programmatic tools via MCP (Model Context Protocol). The skill provides a cohesive architecture using Express for web serving, @longrun/turtle for MCP server implementation, and SQLite for persistent storage of session cookies and authentication states.

Installation

To integrate this skill into your local OpenClaw environment, execute the following command in your terminal: clawhub install openclaw/skills/skills/napoleond/clawdirect-dev

Ensure that you have Node.js and the ClawHub CLI installed prior to running the installation. Once installed, refer to the documentation in your local node_modules or the reference repository at https://github.com/napoleond/clawdirect to initialize your database schema and start your development server.

Use Cases

  1. Automated E-commerce Interfaces: Build storefronts where agents can research products, authenticate via ATXP, and execute purchases programmatically.
  2. Subscription-based Agent Tools: Develop web apps that offer specialized data processing or generation services, charging agents for usage via ATXP.
  3. Agent-Managed Dashboards: Create administrative interfaces that agents can navigate to perform complex tasks, manage configurations, or monitor system logs using their specific browser-based auth session.
  4. Bridge Environments: Enable agents to manage SaaS platforms by creating a web-based intermediary that handles the cookie-session lifecycle for them.

Example Prompts

  1. "Build a new ClawDirect project template that connects to a local SQLite database and exposes an MCP tool to authenticate users via ATXP."
  2. "Help me debug my agent-facing web app where the browser automation tool is failing to set the session cookie during navigation."
  3. "Extend my current ClawDirect app to include a premium tool that requires an ATXP payment transaction before it returns any data to the agent."

Tips & Limitations

When designing your UI for agents, remember that agents do not 'see' the screen like humans. Focus on clear HTML structures that are easy for LLMs to parse via browser tools. Always handle cookie-based authentication by allowing the agent to pass the session value in the URL query string, as many headless browsers have restricted cookie access policies. Keep your SQLite database optimized; while great for lightweight agent states, it may require migration to PostgreSQL for high-concurrency production environments. Always test your agent workflows using simulated browser tools to ensure authentication persistence is maintained across multiple navigation steps.

Metadata

Author@napoleond
Stars1335
Views0
Updated2026-02-23
View Author Profile
AI Skill Finder

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 skill
Add to Configuration

Paste this into your clawhub.json to enable this plugin.

{
  "plugins": {
    "official-napoleond-clawdirect-dev": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#atxp#mcp#web-development#agents#authentication
Safety Score: 3/5

Flags: network-access, file-write, file-read, external-api