← Back to Skills Marketplace
mrzilvis

Fieldy AI Webhook

by mrzilvis · GitHub ↗ · v0.1.2
cross-platform ✓ Security Clean
2244
Downloads
3
Stars
3
Active Installs
3
Versions
Install in OpenClaw
/install fieldy-ai-webhook
Description
Wire a Fieldy webhook transform into Moltbot hooks.
README (SKILL.md)

What this sets up

You’ll configure Moltbot Gateway webhooks so an incoming request to POST /hooks/fieldy runs through a transform module (fieldy-webhook.js) before triggering an agent run.

Behavior notes (defaults in fieldy-webhook.js):

  • Saying "Hey, Fieldy" (or just "Fieldy") will trigger the agent with the text after the wake word.
  • Transcripts without the wake word will not wake the agent; they’ll only be logged to JSONL files by fieldy-webhook.js (under \x3Cworkspace>/fieldy/transcripts/).
  • You can adjust wake words, parsing, and logging behavior by editing fieldy-webhook.js.

1) Put the transform script in the configured transforms dir

Your hooks.transformsDir is:

/root/clawd/skills/fieldy/scripts

Move the script from this repo:

  • From: src/fieldy-webhook.js
  • To: /root/clawd/skills/fieldy/scripts/fieldy-webhook.js

Notes:

  • Make sure the destination filename is exactly fieldy-webhook.js (matches the config below).

2) Add the webhook mapping to ~/.clawdbot/moltbot.json

Add this config:

"hooks": {
  "token": "insert-your-token",
  "transformsDir": "/root/clawd/skills/fieldy/scripts",
  "mappings": [
    {
      "match": {
        "path": "fieldy"
      },
      "action": "agent",
      "name": "Fieldy",
      "messageTemplate": "{{message}}",
      "deliver": true,
      "transform": {
        "module": "fieldy-webhook.js"
      }
    }
  ]
}

Important:

  • hooks.token is required when hooks are enabled (see Webhooks docs).
  • Ensure hooks.enabled: true exists somewhere in your config (and optionally hooks.path, default is /hooks).

3) Restart the Gateway

Plugins/config changes generally require a gateway restart. After restarting, the webhook endpoint should be live.

4) Configure the webhook URL in the Fieldy app

  • Log in to your Fieldy app
  • Go to SettingsDeveloper Settings
  • Set Webhook Endpoint URL to:

https://your-url.com/hooks/fieldy?token=insert-your-token

Note: Moltbot supports sending the token via header too, but many webhook providers only support query params. Moltbot still accepts ?token= (see Webhooks docs).

5) Test

Example request (adjust host/port and token):

curl -X POST "http://127.0.0.1:18789/hooks/fieldy" \
  -H "Authorization: Bearer insert-your-token" \
  -H "Content-Type: application/json" \
  -d '{"transcript":"Hey Fieldy summarize this: hello world"}'
Usage Guidance
This skill appears to do what it says: parse incoming webhook payloads, log transcripts to <workspace>/fieldy/transcripts, and trigger the agent when a wake word is detected. Before installing: 1) Do not drop the script into a privileged system directory — use a workspace owned by a non-root user. The SKILL.md suggests /root/...; adapt that to a non-root path if appropriate. 2) Protect your Moltbot hooks token: prefer sending it in an Authorization header rather than embedding it in a public URL query string, and rotate it if exposed. 3) Transcripts may contain sensitive data — ensure the transcripts directory has appropriate filesystem permissions and retention policies. 4) If you need stricter verification of webhook origin (signatures, IP allowlist), add that into the transform — the current script does not validate source authenticity. 5) Review and test the transform in a safe environment to confirm the workspace detection logic uses the intended directory and that no unexpected files are read/written.
Capability Analysis
Type: OpenClaw Skill Name: fieldy-ai-webhook Version: 0.1.2 The skill bundle is designed to set up a Moltbot webhook transform for a 'Fieldy' integration. The `SKILL.md` provides clear, human-readable instructions for configuration, and does not contain any prompt injection attempts against the AI agent. The `src/fieldy-webhook.js` script primarily parses webhook input, performs wake word detection, and logs non-wake-word transcripts to a specific, controlled directory (`<workspace>/fieldy/transcripts/`) using `fs.appendFileSync`. This file system access is explicitly documented and aligns with the stated purpose of logging. No evidence of data exfiltration, malicious execution, persistence, or other harmful behaviors was found.
Capability Assessment
Purpose & Capability
Name/description (Fieldy webhook → Moltbot transform) align with the included transform script and the SKILL.md instructions. The skill requires no unrelated credentials or binaries and the script only reads/parses incoming webhook payloads, writes transcript JSONL files to a workspace subdirectory, and returns a message to trigger an agent run.
Instruction Scope
Instructions are focused on placing the transform in the transformsDir and adding a Moltbot mapping; they explicitly instruct editing ~/.clawdbot/moltbot.json and restarting the gateway. The transform writes transcript logs under <workspace>/fieldy/transcripts and may use process.env.CLAWDBOT_WORKSPACE or walk the filesystem to locate the workspace. This behavior is expected for local logging but means transcripts (possibly PII) will be stored on disk — the user should confirm acceptable storage location and permissions.
Install Mechanism
No install spec; instruction-only with a single transform JS file. Nothing is downloaded from external URLs and no packages are installed by the skill itself.
Credentials
The skill declares no required environment variables or credentials. The code optionally reads CLAWDBOT_WORKSPACE to locate the workspace directory — appropriate and documented. The example token in SKILL.md refers to Moltbot's hooks.token (Moltbot config), not a secret required by the skill code itself.
Persistence & Privilege
always:false (default). The skill requires adding configuration to the user's Moltbot config and will create/write files under the detected workspace (fieldy/transcripts). It does not modify other skills' configs or request system-wide credentials.
How to Use
  1. Make sure OpenClaw is installed (local or Docker)
  2. Run the install command in chat: /install fieldy-ai-webhook
  3. After installation, invoke the skill by name or use /fieldy-ai-webhook
  4. Provide required inputs per the skill's parameter spec and get structured output
Version History
v0.1.2
fieldy-ai-webhook 0.1.2 - Transcripts without the wake word are now logged to JSONL files under `<workspace>/fieldy/transcripts/`. - Updated documentation to clarify transcript logging behavior.
v0.1.1
Initial release. Adds a Fieldy webhook transform for Moltbot. - Added transform script: fieldy-webhook.js for integrating Fieldy webhooks with Moltbot Gateway. - Provided setup instructions for configuring webhook mapping and agent triggers. - Supports wake-word-based transcript handling ("Hey, Fieldy" or "Fieldy") to activate Moltbot agents.
v0.1.0
Initial release of Fieldy webhook skill for Moltbot. - Adds transform module to process incoming Fieldy webhooks at /hooks/fieldy. - Supports wake-word detection ("Hey, Fieldy" or "Fieldy") to trigger agent actions. - Ignores/logs transcripts without the wake word. - Provides setup instructions for script placement, Moltbot config, and Fieldy webhook integration. - Customization available via editing fieldy-webhook.js.
Metadata
Slug fieldy-ai-webhook
Version 0.1.2
License
All-time Installs 3
Active Installs 3
Total Versions 3
Frequently Asked Questions

What is Fieldy AI Webhook?

Wire a Fieldy webhook transform into Moltbot hooks. It is an AI Agent Skill for Claude Code / OpenClaw, with 2244 downloads so far.

How do I install Fieldy AI Webhook?

Run "/install fieldy-ai-webhook" in the OpenClaw or Claude Code chat to install it in one step — no extra setup required.

Is Fieldy AI Webhook free?

Yes, Fieldy AI Webhook is completely free (open-source). You can download, install and use it at no cost.

Which platforms does Fieldy AI Webhook support?

Fieldy AI Webhook is cross-platform and runs anywhere OpenClaw / Claude Code is available (cross-platform).

Who created Fieldy AI Webhook?

It is built and maintained by mrzilvis (@mrzilvis); the current version is v0.1.2.

💬 Comments