ClawKit Logo
ClawKitReliability Toolkit
Back to Registry
Official Verified communication Safety 4/5

fieldy

Wire a Fieldy webhook transform into Moltbot hooks.

Why use this skill?

Configure the Fieldy webhook for OpenClaw to process transcripts, trigger agents with wake words, and automatically log interactions to local files.

skill-install — Terminal

Install via CLI (Recommended)

clawhub install openclaw/skills/skills/mrzilvis/fieldy-ai-webhook
Or

What This Skill Does

The Fieldy skill acts as a intelligent middleware layer for OpenClaw, specifically designed to bridge the gap between incoming Fieldy webhook events and the Moltbot execution engine. By routing incoming requests through a custom transform module, this skill allows users to process unstructured webhook transcripts before they are handed off to an agent. Its primary function is to act as a gatekeeper: it parses raw transcripts, triggers the agent only when specific 'wake words' like 'Fieldy' are detected, and silently archives non-triggering interactions into structured JSONL files for future review or training. This creates a powerful conversational interface that filters out ambient noise while maintaining a reliable audit trail of all incoming data.

Installation

Installation involves a two-part setup process. First, copy the fieldy-webhook.js logic to your dedicated transforms directory at /root/clawd/skills/fieldy/scripts. Ensure that the file path matches the configuration precisely. Second, integrate the webhook mapping into your ~/.clawdbot/moltbot.json file. You must define a valid security token under the hooks object and ensure the transformsDir points to the correct local directory. After modifying the configuration, perform a complete restart of the Moltbot Gateway to register the new endpoint. Once initialized, configure your external Fieldy application developer settings to point to your secure public-facing URL with your authentication token attached as a query parameter.

Use Cases

This skill is ideal for teams or individuals looking to integrate voice or text-to-speech inputs from the Fieldy platform into an automated agent workflow. Use it to build a hands-free command center where the agent waits in the background until addressed by name. It is also perfect for logging and analytics; since it saves all non-triggered transcripts to the local file system, you can use these logs to refine your wake word detection or identify common requests that your agent might currently be ignoring.

Example Prompts

  1. 'Hey Fieldy, summarize the meeting notes I just sent.'
  2. 'Fieldy, add a new task to my calendar for next Tuesday at 9 AM.'
  3. 'Hey, Fieldy, what is the current status of the open pull requests in the repository?'

Tips & Limitations

The primary limitation is that it relies on the custom JavaScript logic within the transform module to interpret the message. If the script is modified, users must be careful to preserve the regex patterns that detect wake words. For security, always ensure that your webhook token is kept secret and that your Gateway is behind a robust firewall or authentication proxy. Since it writes transcripts to the local file system, be sure to manage disk space if you expect a high volume of traffic, as the JSONL log files will continue to grow over time.

Metadata

Author@mrzilvis
Stars1335
Views3
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-mrzilvis-fieldy-ai-webhook": {
      "enabled": true,
      "auto_update": true
    }
  }
}

Tags(AI)

#automation#webhooks#integration#logging#voice-control
Safety Score: 4/5

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