WalletPilot-7715
Execute on-chain transactions with user-granted permissions. Built on MetaMask ERC-7715. No private keys, full guardrails.
Best use case
WalletPilot-7715 is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Execute on-chain transactions with user-granted permissions. Built on MetaMask ERC-7715. No private keys, full guardrails.
Teams using WalletPilot-7715 should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/walletpilot-7715/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How WalletPilot-7715 Compares
| Feature / Agent | WalletPilot-7715 | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Execute on-chain transactions with user-granted permissions. Built on MetaMask ERC-7715. No private keys, full guardrails.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
Related Guides
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
AI Agents for Coding
Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.
SKILL.md Source
# WalletPilot-7715
Give your AI agent crypto superpowers with MetaMask ERC-7715 permissions.
## Overview
WalletPilot enables AI agents to execute on-chain transactions using MetaMask's ERC-7715 permission standard. Users grant scoped permissions (spend limits, chain restrictions) once, then agents can execute freely within those limits.
**Key Features:**
- No private keys shared - users keep their MetaMask
- Configurable guardrails (spend limits, chain allowlists)
- Multi-chain support (Ethereum, Polygon, Arbitrum, Optimism, Base)
- Built on MetaMask's official Smart Accounts Kit
## Setup
1. Get an API key at [walletpilot.xyz](https://walletpilot.xyz)
2. Install the SDK: `npm install @walletpilot/sdk`
## Available Actions
### connect
Request wallet permissions from user.
```typescript
import { WalletPilot, PermissionBuilder } from '@walletpilot/sdk';
const pilot = new WalletPilot({ apiKey: 'wp_...' });
const permission = new PermissionBuilder()
.spend('USDC', '100', 'day') // Max $100 USDC per day
.spend('ETH', '0.1', 'day') // Max 0.1 ETH per day
.chains([1, 137, 42161]) // Ethereum, Polygon, Arbitrum
.expiry('30d') // Valid for 30 days
.build();
const { deepLink } = await pilot.requestPermission(permission);
console.log('User should open:', deepLink);
```
### execute
Execute a transaction using granted permissions.
```typescript
const result = await pilot.execute({
to: '0x1234...', // Target contract
data: '0xabcd...', // Calldata (e.g., swap)
value: '0', // ETH value (optional)
chainId: 1, // Chain ID
});
console.log('Transaction hash:', result.hash);
```
### balance
Check token balances (uses standard RPC, no permission needed).
```typescript
import { createPublicClient, http } from 'viem';
import { mainnet } from 'viem/chains';
const client = createPublicClient({
chain: mainnet,
transport: http(),
});
const balance = await client.getBalance({ address: '0x...' });
```
### swap
Execute a token swap via DEX aggregator.
```typescript
// Get swap quote from 1inch, 0x, or similar
const quote = await fetch('https://api.1inch.io/v5.0/1/swap?...');
const { tx } = await quote.json();
// Execute via WalletPilot
await pilot.execute({
to: tx.to,
data: tx.data,
value: tx.value,
chainId: 1,
});
```
### send
Send tokens to an address.
```typescript
import { encodeFunctionData, erc20Abi } from 'viem';
// Encode ERC20 transfer
const data = encodeFunctionData({
abi: erc20Abi,
functionName: 'transfer',
args: ['0xRecipient...', 1000000n], // 1 USDC (6 decimals)
});
await pilot.execute({
to: '0xUSDC_ADDRESS...',
data,
chainId: 1,
});
```
### history
Get transaction history.
```typescript
const state = pilot.getState();
console.log('Active permissions:', state.permissions);
// Or via API
const response = await fetch('https://api.walletpilot.xyz/v1/tx/history/PERMISSION_ID', {
headers: { 'Authorization': 'Bearer wp_...' },
});
const { data } = await response.json();
console.log('Recent transactions:', data);
```
## Permission Types
| Permission | Example | Description |
|------------|---------|-------------|
| `spend` | `{ token: 'USDC', limit: '100', period: 'day' }` | Max token spend per period |
| `chains` | `[1, 137, 42161]` | Allowed chain IDs |
| `contracts` | `['0x...']` | Allowed contract addresses |
| `expiry` | `'30d'` | Permission expiration |
## Supported Chains
| Chain | ID | Name |
|-------|-----|------|
| Ethereum | 1 | mainnet |
| Polygon | 137 | polygon |
| Arbitrum | 42161 | arbitrum |
| Optimism | 10 | optimism |
| Base | 8453 | base |
## Security
- **No Private Keys**: Users keep full custody via MetaMask
- **Scoped Permissions**: Agents can only act within granted limits
- **Time-Limited**: Permissions automatically expire
- **Revocable**: Users can revoke permissions anytime
- **Auditable**: All transactions logged and visible
## API Reference
**Base URL:** `https://api.walletpilot.xyz`
| Endpoint | Method | Description |
|----------|--------|-------------|
| `/v1/permissions/request` | POST | Request new permission |
| `/v1/permissions/:id` | GET | Get permission details |
| `/v1/tx/execute` | POST | Execute transaction |
| `/v1/tx/:hash` | GET | Get transaction status |
## Example: DeFi Agent
```typescript
import { WalletPilot, PermissionBuilder } from '@walletpilot/sdk';
async function defiAgent() {
const pilot = new WalletPilot({ apiKey: process.env.WALLETPILOT_KEY });
// Check if we have active permissions
const state = pilot.getState();
if (!state.connected) {
// Request permission
const permission = new PermissionBuilder()
.spend('USDC', '500', 'day')
.chains([1, 42161])
.expiry('7d')
.description('DeFi trading agent')
.build();
const { deepLink } = await pilot.requestPermission(permission);
console.log('Approve in MetaMask:', deepLink);
return;
}
// Execute trades
const swapData = await getSwapQuote('USDC', 'ETH', '100');
await pilot.execute({
to: swapData.to,
data: swapData.data,
chainId: 1,
});
console.log('Swap executed!');
}
```
## Links
- [Documentation](https://docs.walletpilot.xyz)
- [GitHub](https://github.com/andreolf/walletpilot)
- [API Reference](https://api.walletpilot.xyz)Related Skills
WalletPilot
Universal browser wallet automation for AI agents. Supports 10 wallets including MetaMask, Rabby, Phantom, Trust Wallet, OKX, Coinbase, and more. EVM + Solana. Configurable guardrails with spend limits, chain allowlists, and approval thresholds.
---
name: article-factory-wechat
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.
find-skills
Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.
tavily-search
Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.
self-improvement
Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.
botlearn-healthcheck
botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
Google NotebookLM 非官方 Python API 的 OpenClaw Skill。支持内容生成(播客、视频、幻灯片、测验、思维导图等)、文档管理和研究自动化。当用户需要使用 NotebookLM 生成音频概述、视频、学习材料或管理知识库时触发。