internet-court/internet-court-skill

The trust layer for agent-to-agent commerce — natural-language mandates, ERC-7710 delegated permissions, x402 payments, escrow, and dispute resolution as one open, catch-all Agent Skill / Claude Code plugin.

What it solves

Internet Court provides a standardized way for AI agents to enter into trustworthy contracts, transact, and resolve disputes without human intervention. It addresses the fragmentation of the agentic commerce ecosystem by unifying various protocols for identity, negotiation, payment, and execution into a single "skill" that agents can use to handle the entire lifecycle of a deal, including what happens when a deal goes wrong.

How it works

It acts as a master router (SKILL.md) that connects a wide array of existing standards and protocols across six layers:

  1. Discovery & Identity: Managing agent reputation and registration.
  2. Negotiation: Facilitating agent-to-agent (A2A) agreements.
  3. Contracts: Handling natural-language agreements and escrow.
  4. Payment: Managing funds and settlement.
  5. Execution: Providing the compute and data rails for the deal.
  6. Verification & Disputes: Integrating adjudication services (like GenLayer, Kleros, or UMA) to settle disagreements based on terms written into the contract.

Who it’s for

Developers building autonomous AI agents that need to transact, negotiate, and pay one another securely and accountably.

Highlights

  • Unified Interface: Consolidates dozens of fragmented protocols into one catch-all skill.
  • Built-in Adjudication: Enables agents to agree on a dispute resolution method upfront.
  • Consortium-Backed: Developed by a wide group of industry members including MetaMask, OKX, NEAR, and Starknet.
  • Flexible Installation: Compatible with multiple agent harnesses including Claude Code, npx skills, Codex, and OpenClaw.

Related

  • Project
    evolsb/claude-legal-skill

    An AI agent skill for legal contract review that provides risk detection, market benchmarks, and specific redline suggestions grounded in the CUAD dataset.

  • Project
    zjunlp/SkillNet

    SkillNet is an open‑source infrastructure that treats AI agent capabilities as reusable, searchable software assets. It offers a public skill library, a Python SDK/CLI, and a public REST API for discovering, downloading, creating, evaluating, analyzing, and orchestrating these skills. The platform enables agents to reuse existing functionality (e.g., PDF parsing, web‑scraping) instead of reinventing it, provides quality scores, builds skill‑relationship graphs, and can generate scene‑specific prompts for downstream LLM agents. Installation is as simple as `pip install skillnet-ai`; no API key is needed for search or public downloads, while creation/evaluation/orchestration require an LLM API key. The project includes a web explorer, MCP server, and integrations with Claude, OpenAI, OpenClaw, and JiuwenClaw, plus benchmark scripts for ALFWorld, WebShop, and ScienceWorld.

  • Project
    mgechev/skills-best-practices

    A comprehensive guide on best practices for creating structured agent skills to improve AI agent reliability, discoverability, and token efficiency.

  • Project
    wanikua/danghuangshang

    A multi-agent collaboration system based on the OpenClaw framework that organizes AI agents into a hierarchical government or corporate structure for efficient task delegation and execution.

  • Project
    agentic-commerce-protocol/agentic-commerce-protocol

    An open standard and interaction model maintained by OpenAI and Stripe that enables AI agents to seamlessly conduct commercial transactions between buyers and businesses.