A secure, read-only integration skill for AI agents to interact with DealWatch grocery data using the Model Context Protocol.
The fastest way to install a skill directly from the registry.
npx clawhub@latest install dealwatch-readonly-builder
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 dealwatch-readonly-builder using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Get the raw skill files in a ZIP archive.
The DealWatch Read-only Builder is a specialized technical skill designed to facilitate a safe-first interaction between AI agents and the DealWatch ecosystem. By prioritizing read-only access, this skill ensures that agents can verify runtime readiness and compare product data without mutating state or triggering unauthorized write actions. It is a critical component for developers building Openclaw Skills that require reliable grocery data inspection and environment diagnostics.
This skill focuses on the shortest truthful path for integration, guiding users through the installation of the published DealWatch MCP package while maintaining local-first boundaries. It provides a structured methodology for agents to choose the correct tool based on the current objective, whether that is checking system health or inspecting complex watch groups.
To activate this skill within your Openclaw Skills environment, ensure the DealWatch MCP package is installed. Do not use repo-local launch commands if the published package is available.
# Follow the installation guide in references/INSTALL.md
# Ensure the MCP server is registered in your agent configuration
# Verify connection using the readiness tool
Always refer to the local README.md for the most up-to-date installation snippets and environment variables.
The skill manages information through a structured read-only taxonomy focused on grocery monitoring metadata:
| Data Component | Description |
|---|---|
| Runtime Status | Diagnostic state of the local MCP environment. |
| Comparison Preview | Temporary analysis of grocery product attributes from provided URLs. |
| Watch Tasks | Metadata for individual items being monitored, including price history. |
| Watch Groups | Logical collections of related tasks for organized tracking. |
| Recovery Inbox | Log of system-level notifications and diagnostic recovery states. |
Loading
A high-leverage design agent focused on surrealist, minimalist, and atmospheric aesthetics tailored for Gen-Z audiences.

A read-only triage tool that transforms complex workspace snapshots into a single, evidence-based next action for students.

A systematic framework for AI agents to log errors, capture user corrections, and continuously evolve through persistent project memory.

A specialized skill for AI agents to safely connect and navigate the CortexPilot read-only MCP for secure workflow and run inspection.

An AI agent skill designed to retrieve and analyze comprehensive corporate data, market standing, and historical context for American Airlines.

An intelligent agent skill that analyzes uploaded templates to generate context-aware, import-ready sample data.








































