Fidel for Openclaw

A powerful financial infrastructure skill that enables AI agents to securely access and manage real-time card transaction data through the Fidel API.

membranedev
v1.0.2
Apr 30, 2026
0
399
0

Install & Download

1. ClawHub CLI

The fastest way to install a skill directly from the registry.

npx clawhub@latest install fidel

2. Manual Installation

Copy the skill folder to one of these locations

Global
~/.openclaw/skills/
Workspace
<project>/skills/

Priority: Workspace > Local > Bundled

3. Prompt Installation

Copy this prompt to OpenClaw to install it automatically.

Help me install fidel 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 Fidel?

The Fidel skill provides a robust bridge between AI agents and financial card networks. By utilizing this integration within Openclaw Skills, developers can build agents that interact with credit and debit card data to drive loyalty programs, expense management tools, and personalized financial insights.

This skill leverages the Membrane framework to simplify the complexities of financial data access. It removes the burden of manual authentication plumbing, allowing the agent to focus on executing logic while Membrane handles the secure credential lifecycle and connection management server-side.

Fidel Use Cases

  • Automating expense management by pulling real-time card transaction data into accounting systems.
  • Building AI-driven loyalty programs that trigger rewards based on specific merchant transactions.
  • Creating personalized financial insight tools that analyze spending patterns across multiple accounts.
  • Streamlining audit processes for fintech applications using automated data retrieval.
  • Developing intelligent banking assistants that provide context-aware notifications for specific transaction types using Openclaw Skills.

How Fidel Works

  1. The Membrane CLI is installed and initialized to act as the primary interface for the AI agent.
  2. The user authenticates via a secure login process, establishing a tenant-based session for the agent.
  3. A connection is established to the Fidel API, where Membrane manages the OAuth flow or API keys automatically.
  4. The agent uses natural language intents to search for specific financial actions, such as retrieving transaction history or merchant details.
  5. High-level actions are executed through the CLI, or the agent performs direct proxy requests to the Fidel API for custom data requirements.

Fidel Setup

First, install the necessary CLI tool globally:

npm install -g @membranehq/cli@latest

Authenticate your environment for the agent:

membrane login --tenant --clientName=openclaw

Establish a secure connection to the Fidel infrastructure:

membrane connection ensure "https://fidel.uk/" --json

Fidel Data Schema & Taxonomy

The skill organizes financial data into several key entities to facilitate structured processing within Openclaw Skills:

Entity Description
Merchant Information regarding the business entity where transactions occur.
Transaction Detailed records of credit or debit card activity, including amounts and timestamps.
Program The overarching logic or campaign container for card-linked services.
Authorization Real-time status updates and verification records for card events.
Insight Aggregated analytics and patterns derived from cardholder behavior.

Fidel Advanced Features

  • Server-side credential management that handles token refreshes without exposing secrets to the local environment.
  • Intent-based action discovery allows agents to find the most efficient way to query financial data using natural language.
  • Direct API proxying capability for endpoints that require custom parameters or specific financial metadata.
  • Support for headless environments with long-polling connection states for resilient automated deployments.
  • Unified data output in JSON format, optimized for processing by other Openclaw Skills in a multi-agent workflow.

SKILL.md


Loading

Related Openclaw Skills

METADATA

Github Stars: 0
forks: 0

Featured*