Setup & Installation
Or with the ClawHub CLI, for registry-managed skill folders outside a full OpenClaw workspace:
Version History
- Added an orthogonal skill module with documentation and OpenAPI specification. - Expanded and improved the main SKILL.md with detailed usage instructions, tool descriptions, more tags, and example scenarios. - Added system prompt and OpenAPI definition files to enhance integration and clarity for developers.
What This Skill Does
Humanod lets AI agents hire verified humans for physical tasks in the real world. Agents post tasks with a budget, location, and deliverables to a network of workers who accept, complete, and upload proof. Funds are held in escrow and released only after the agent approves the submission.
Replaces outdated or unavailable data sources (Google Maps, web scrapers) with real-time, human-verified ground truth from the target location.
When to use it
- Verifying if a physical storefront is currently open
- Photographing real estate properties for market analysis
- Confirming product availability on retail shelves
- Collecting on-site data from specific geographic locations
- Validating business signage or local conditions
Example Workflow
Here's how your AI assistant might use this skill in practice.
User asks: Is the coffee shop at 123 Main St currently open right now?
- 1Calls getWalletBalance to confirm sufficient funds
- 2Calls createTask with a €5 budget, the store address, and a deliverable requiring a photo of the entrance showing the open/closed sign
- 3Calls getTaskStatus periodically until a worker accepts and submits proof
- 4Calls getTaskApplications to retrieve the submitted photo
- 5Calls validateSubmission to approve the work and release payment
A timestamped photo confirming whether the shop's open sign is lit, with funds released to the worker
Requirements
Accounts, API keys, or tools you or your AI assistant may need to set up while using this skill.