A technical integration packet designed to teach AI agents how to interface with Shopflow as a read-only surface using MCP servers.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install shopflow-read-only-packet
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
Copy this prompt to OpenClaw to install it automatically.
Help me install shopflow-read-only-packet using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The Shopflow Read-only Packet is a specialized resource for developers seeking to integrate Shopflow capabilities into their agentic workflows without making live store claims. It focuses on providing a truthful representation of integration and submission-readiness, specifically optimized for the Openclaw Skills ecosystem. By utilizing this packet, agents learn how to interact with the Shopflow local stdio MCP server, ensuring that data retrieval and capability mapping are handled within a secure, read-only context.
This skill is essential for operators who need a structured approach to verify commerce integrations. It consolidates installation steps, capability maps, and proof-of-concept demos into a single, cohesive folder structure. This ensures that when you build with Openclaw Skills, your AI agent maintains a high degree of technical accuracy regarding Shopflow’s current status and capabilities.
To set up the Shopflow Read-only Packet, follow these steps to configure your environment for Openclaw Skills:
# Navigate to the packet directory
cd shopflow-readonly-packet
# Review the installation requirements
cat references/INSTALL.md
# Implement the host-specific configuration
# For OpenClaw users:
cp references/OPENCLAW_MCP_CONFIG.json ~/.config/openclaw/mcp.json
# Run the verification proof loop
bash references/DEMO.md
The Shopflow packet organizes its data into a clear hierarchy of reference files to guide the agent through Openclaw Skills integration:
| File Name | Description |
|---|---|
INSTALL.md |
Core setup instructions and environmental prerequisites. |
OPENCLAW_MCP_CONFIG.json |
JSON schema for connecting the OpenClaw host to the MCP server. |
CAPABILITIES.md |
A complete map of available read-only tools and safe operations. |
DEMO.md |
A scripted proof loop for verifying integration success. |
TROUBLESHOOTING.md |
Logic for resolving packet failures or attach path errors. |
Loading
A disciplined prediction market trading skill for AI agents that utilizes value-based analysis to trade on Simmer and Polymarket venues.

A specialized skill for AI agents to transform raw, unstructured information into a disciplined taxonomy of durable knowledge.

A disciplined reasoning protocol that protects against high-stakes errors by intelligently switching between rapid execution and deep, risk-aware deliberation.

A disciplined, closed-loop protocol for AI agents to identify, localize, and correct execution drift through a structured feedback system.

A specialized skill for installing and utilizing Switchyard's read-only MCP runtime diagnostics surface for precise AI agent debugging.

A safety-oriented skill for AI agents to manage local MCP servers with a review-first approach to data mutation and batch analysis.








































