本文へ移動
cccskills
無料GitHub で公開

starknet-identity

Register AI agents on-chain using the ERC-8004 Trustless Agents standard. Manage agent identity as NFTs, build reputation through feedback, and request third-party validation.

インストール方法を見る

含まれるファイル(3)

  • SKILL.md10.5 KB
  • agents/openai.yaml320 B
  • LICENSE1.1 KB

SKILL.md(原文)

インストールする前に、エージェントに与えられる指示の中身を確認できます。

Starknet Identity Skill

Register and manage AI agent identities on Starknet using the ERC-8004 standard.

When to Use

  • Registering agents on-chain, updating agent metadata, or managing reputation and validation flows.
  • Building features that depend on ERC-8004 identity, feedback, or validator attestations.

When NOT to Use

  • Simple wallet, payment, or DeFi flows that do not depend on ERC-8004 registries.
  • Cairo contract authoring, deployment-only tasks, or security auditing.

Quick Start

  1. Install starknet and connect a funded account to the target ERC-8004 registry deployment.
  2. Use skills catalog if the flow also needs wallet setup, deployment, or contract auditing.

Overview

ERC-8004 defines three interconnected on-chain registries for AI agents:

  1. Identity Registry -- Agents as ERC-721 NFTs with metadata
  2. Reputation Registry -- Feedback system with cryptographic authorization
  3. Validation Registry -- Third-party assessments (zkML, TEE, staker)

Reference implementation: erc8004-cairo

Prerequisites

npm install starknet

Agent Registration

Register a New Agent

import { Account, RpcProvider, Contract, CallData } from "starknet";

const provider = new RpcProvider({ nodeUrl: process.env.STARKNET_RPC_URL });
const account = new Account({ provider, address, signer: privateKey });

const identityRegistry = new Contract({
  abi: identityRegistryAbi,
  address: registryAddress,
  providerOrAccount: account,
});

// Register with metadata
const metadata = [
  { key: "agentName", value: "MyTradingAgent" },
  { key: "agentType", value: "defi-trader" },
  { key: "version", value: "1.0.0" },
  { key: "model", value: "claude-opus-4-5" },
  { key: "status", value: "active" },
];

const tokenUri = "ipfs://QmYourAgentSpecHash"; // IPFS link to full agent spec

const { transaction_hash } = await account.execute({
  contractAddress: registryAddress,
  entrypoint: "register_with_metadata",
  calldata: CallData.compile({
    token_uri: tokenUri,
    metadata: metadata,
  }),
});

const receipt = await account.waitForTransaction(transaction_hash);
// Parse agent_id from events

Query Agent Information

// Check if agent exists
const exists = await identityRegistry.agent_exists(agentId);

// Get total registered agents
const totalAgents = await identityRegistry.total_agents();

// Get agent metadata
const name = await identityRegistry.get_metadata(agentId, "agentName");
const agentType = await identityRegistry.get_metadata(agentId, "agentType");

// Get agent owner (ERC-721)
const owner = await identityRegistry.owner_of(agentId);

Update Agent Metadata

// Only the agent owner can update metadata
await account.execute({
  contractAddress: registryAddress,
  entrypoint: "set_metadata",
  calldata: CallData.compile({
    agent_id: agentId,
    key: "status",
    value: "upgraded",
  }),
});

Reputation System

Authorize and Submit Feedback

The reputation system uses a cryptographic authorization flow:

  1. Agent owner creates a FeedbackAuth struct and signs it
  2. Client submits feedback with the authorization
// Step 1: Agent owner creates authorization
const feedbackAuth = {
  agent_id: agentId,
  client_address: clientAddress,
  index_limit: 10, // Max feedback entries allowed
  expiry: Math.floor(Date.now() / 1000) + 3600, // 1 hour
  chain_id: chainId,
  identity_registry: registryAddress,
  signer_address: ownerAddress,
};

// Sign the authorization (using agent owner's account)
const messageHash = computePoseidonHash(feedbackAuth); // EIP-712 style
const signature = await ownerAccount.signMessage(messageHash);

// Step 2: Client submits feedback
await clientAccount.execute({
  contractAddress: reputationRegistryAddress,
  entrypoint: "give_feedback",
  calldata: CallData.compile({
    agent_id: agentId,
    score: 85, // 0-100
    tag1: encodedTag("reliability"),
    tag2: encodedTag("speed"),
    fileuri: "",
    filehash: 0,
    feedback_auth: feedbackAuth,
    signature: signature,
  }),
});

Query Reputation

const reputationRegistry = new Contract({
  abi: reputationAbi,
  address: reputationAddress,
  providerOrAccount: provider,
});

// Get summary for an agent (count + average score)
const [count, avgScore] = await reputationRegistry.get_summary(
  agentId,
  [], // all client addresses (or filter specific ones)
  0,  // tag1 filter (0 = all)
  0,  // tag2 filter (0 = all)
);

// Read specific feedback
const [score, tag1, tag2, isRevoked] = await reputationRegistry.read_feedback(
  agentId,
  clientAddress,
  feedbackIndex,
);

// Get all clients who gave feedback
const clients = await reputationRegistry.get_clients(agentId);

Validation System

Request Validation

const validationRegistry = new Contract({
  abi: validationAbi,
  address: validationAddress,
  providerOrAccount: account,
});

// Agent owner requests validation from a specific validator
await account.execute({
  contractAddress: validationAddress,
  entrypoint: "validation_request",
  calldata: CallData.compile({
    validator_address: validatorAddress,
    agent_id: agentId,
    request_uri: "ipfs://QmValidationRequestDetails",
    request_hash: 0, // Auto-generated if 0
  }),
});

Submit Validation Response

// Validator responds to the request
await validatorAccount.execute({
  contractAddress: validationAddress,
  entrypoint: "validation_response",
  calldata: CallData.compile({
    request_hash: requestHash,
    response: 92, // Score 0-100
    response_uri: "ipfs://QmValidationReport",
    response_hash: reportHash,
    tag: encodedTag("performance"),
  }),
});

Query Validation Status

// Get validation summary
const [validationCount, avgValidationScore] = await validationRegistry.get_summary(
  agentId,
  [], // all validators
  0,  // tag filter
);

// Get specific validation
const [validator, agentId_, response, tag, lastUpdate] =
  await validationRegistry.get_validation_status(requestHash);

A2A Agent Card Integration

Combine on-chain identity with A2A Agent Cards for discoverability:

{
  "name": "MyTradingAgent",
  "description": "Autonomous DeFi trading agent on Starknet",
  "url": "https://my-agent.example.com",
  "provider": {
    "organization": "MyOrg"
  },
  "version": "1.0.0",
  "capabilities": {
    "streaming": true,
    "pushNotifications": false
  },
  "skills": [
    {
      "id": "starknet-swap",
      "name": "Token Swap",
      "description": "Execute token swaps on Starknet via avnu"
    }
  ],
  "defaultInputModes": ["text/plain"],
  "defaultOutputModes": ["text/plain"],
  "authentication": {
    "schemes": ["bearer"]
  },
  "starknetIdentity": {
    "registryAddress": "0x...",
    "agentId": 42,
    "reputationScore": 85,
    "validationCount": 3
  }
}

Serve at /.well-known/agent.json for A2A discovery.

Metadata Schema (Recommended)

KeyDescriptionExample
agentNameDisplay name"MyTradingAgent"
agentTypeCategory"defi-trader", "nft-curator", "data-analyst"
versionSemantic version"1.0.0"
modelLLM model used"claude-opus-4-5", "gpt-4o"
statusCurrent status"active", "paused", "deprecated"
frameworkAgent framework"daydreams", "openclaw", "langchain"
capabilitiesComma-separated"swap,stake,lend"
a2aEndpointAgent Card URL"https://agent.example.com"
moltbookIdMoltBook agent ID"agent_abc123"

Security Considerations

  • Only the agent owner can update metadata and authorize feedback
  • Feedback requires cryptographic authorization (prevents spam)
  • Self-feedback is prevented (agent owner cannot give feedback to own agent)
  • Self-validation is prevented (agent owner cannot validate own agent)
  • Signatures include chain ID and expiry to prevent replay attacks
  • Agent identity (NFT) is transferable -- new owner inherits reputation

Error Codes

CodeMeaningLikely causesRecoveryUser-facing message
REGISTRATION_FAILEDInitial ERC-8004 registration or metadata write reverted.Missing fees, duplicate registration, invalid calldata, or stale contract state.Retry after checking wallet balance, contract state, and constructor/registration inputs."Registration failed. Check wallet state and retry."
AUTHORIZATION_DENIEDOwnership or feedback authorization proof was rejected.Wrong signer, bad nonce, missing permission, or outdated owner state.Re-fetch owner/nonce state, verify permissions, and re-sign with the current account."Authorization denied. Verify signer permissions and retry."
VALIDATION_TIMEOUTOff-chain validation or watcher flow did not complete before the deadline.Slow relayer, RPC degradation, or downstream A2A service lag.Retry with a longer timeout after checking chain health, relayer status, and RPC latency."Validation timed out. Retry after checking network health."
SIGNATURE_EXPIREDSigned payload expired before submission.Expiry window too short or user approval arrived too late.Generate a fresh signature with a new expiry and resubmit immediately."Signature expired. Re-sign and submit again."
OWNER_TRANSFERREDAgent NFT ownership changed while a write or feedback flow was in flight.NFT transfer, marketplace sale, or custodial wallet rotation.Refresh ownership state, re-authorize with the new owner, and explain that reputation follows the NFT."Ownership changed. Refresh owner state and retry with the new owner."

References

レビュー

まだレビューはありません。使ってみた感想をお寄せください。

同じリポジトリのスキル

概要と使いどころ

0G Compute Network guide for decentralized AI inference, fine-tuning, and GPU services. Covers chatbots, image generation, speech-to-text, SDK integration (0g-serving-broker), processResponse API, broker.inference methods, CLI commands (0g-compute-cli), and account management. Use this skill for any 0G compute, 0G AI, or decentralized GPU question.

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

Builds Agent-to-Agent (A2A) servers and clients following Google's open protocol for agent interoperability. Use when the user wants to create an A2A-compliant agent, build an Agent Card, implement task management, connect agents across frameworks, set up agent discovery, handle streaming responses, implement push notifications, or orchestrate multi-agent workflows. Trigger words: a2a, agent to agent, agent2agent, a2a protocol, a2a server, a2a client, agent card, agent interoperability, agent collaboration, multi-agent, agent discovery, a2a sdk, a2a task.

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

Give the AI agent its own EVM wallet with admin-controlled policies the agent CANNOT bypass even under prompt injection. Encrypted keystore (AES-256-GCM, scrypt KDF), policy file the agent has no tool to write, deterministic policy gate on every signing operation, optional local HTTP dashboard. Triggers: agent wallet, give the agent a wallet, agent address, fund the agent, agent autonomy, policy gate, kill switch, agent permissions, bounded autonomy, ERC-4337 alternative, session-key alternative.

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

Crypto wallet operations via the awal CLI — sign in, check balances, send USDC/ETH/POL/SOL, trade tokens, fund the wallet, and use the x402 payment protocol to discover paid services, pay for API calls, monetize an API, or query onchain data. Use whenever the user mentions signing in, login, authentication, wallet status, balance, address, sending money, paying someone, transferring tokens, ENS names, swapping/trading/converting tokens, funding/topping up/onramp, USDC, ETH, POL, SOL, the x402 bazaar, paid APIs, monetizing an endpoint, or querying onchain data on Base.

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

Help developers write code that interacts with Alkahest escrow contracts using the TypeScript, Rust, or Python SDK

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

Interact with Alkahest escrow contracts as a buyer, seller, or oracle using the CLI

日本語の概要は準備中です。原文の説明を表示しています。

internet-court/internet-court-skill6,7302026年8月20日 更新

internet-court のスキルをすべて見る

このスキルの問題を報告する