Metamask Agent Wallet

Use when the user asks anything about blockchain wallets, transactions, signing, token transfers, supported chains, wallet balances, perpetual futures trading, funding rates, and Hyperliquid vaults, prediction markets, token swaps, cross-chain bridges, market data, token discovery, tokenized real-world assets, RWAs, AI-generated market and asset summaries via pulse, decoding EVM calldata, DeFi earn/yield vaults, installing or removing third-party `mm` CLI plugins, or authentication via the MetaMask Agentic CLI; also when an HTTP request returns 402 Payment Required / x402, when an MCP tool cal

30 stars 15 forksAI, LLMs & Agents

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add MetaMask/agent-skills --skill metamask-agent-wallet
Manual install
git clone --depth 1 https://github.com/MetaMask/agent-skills.git /tmp/agent-skills
mkdir -p ~/.claude/skills
cp -r /tmp/agent-skills/skills/metamask-agent-wallet ~/.claude/skills/metamask-agent-wallet

Personal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.

From the SKILL.md

# MetaMask Agentic CLI Skill

This skill documents the `mm` CLI surface for MetaMask Agent Wallet authentication, wallet lifecycle, balance queries, token transfers, message and typed-data signing, raw transactions, chain discovery, market data, token discovery, tokenized real-world assets, AI market and asset summaries, perpetual futures trading, prediction market trading, prediction trade/redeem history, token swaps, cross-chain bridges, DeFi earn/yield vaults, and EVM calldata decoding.

Use the routing table to select the relevant reference file. CLI behavior lives in `references/`. Repeatable operational patterns live in `workflows/`.

## Command Routing

Match the user's intent to a command and reference file, then read the reference before constructing a command. If intent spans multiple domains, load them sequentially in dependency order.

| User Intent | Command | Reference |
| --- | --- | --- |
| Check authentication status | `mm auth status` | [auth.md](references/auth.md) |
| Login in MetaMask Agentic CLI | `mm login` | [auth.md](references/auth.md) |
| Choose a wallet mode and set up policies | `mm init` | [auth.md](references/auth.md) |
| Show current init settings | `mm init show` | [auth.md](references/auth.md) |
| Sign in via QR code with MetaMask Mobile | `mm login qr` | [auth.md](references/auth.md) |
| Sign in via browser (Google or Email) | `mm login browser` | [auth.md](references/auth.md) |
| Sign out | `mm logout` | [auth.md](references/auth.md) |
Read the full skill on GitHub

Details

Skill name
metamask-agent-wallet
Path
skills/metamask-agent-wallet/SKILL.md
License
MIT
Repo updated
22 October 2026

FAQ

What does the Metamask Agent Wallet skill do?

Use when the user asks anything about blockchain wallets, transactions, signing, token transfers, supported chains, wallet balances, perpetual futures trading, funding rates, and Hyperliquid vaults, prediction markets, token swaps, cross-chain bridges, market data, token discovery, tokenized real-world assets, RWAs, AI-generated market and asset summaries via pulse, decoding EVM calldata, DeFi earn/yield vaults, installing or removing third-party `mm` CLI plugins, or authentication via the MetaMask Agentic CLI; also when an HTTP request returns 402 Payment Required / x402, when an MCP tool cal

How do I install the Metamask Agent Wallet skill?

skills CLI (Claude Code, Cursor, Codex and more): npx skills add MetaMask/agent-skills --skill metamask-agent-wallet. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.

Is Metamask Agent Wallet popular?

It lives in MetaMask/agent-skills, which has 30 GitHub stars and 15 forks, and is included in 1 curated skill list.

Related skills

Xiaohongshu Skill

43

DeliciousBuding/xiaohongshu-skill

小红书 / Xiaohongshu / RedNote AI Agent Skill。用 Python Playwright 搜索和读取内容、管理登录会话、发布图文/视频/长文、评论、点赞和收藏;默认输出 JSON,任何写操作都必须先获得用户确认。用户提到 xiaohongshu、小红书、rednote、小红书搜索、发到小红书、小红书笔记分析、小红书运营或小红书自动化时触发。

AI, LLMs & Agents

Mathmodel Copilot

60

Odyphus/MathModel-Copilot

MathModel Copilot, an evidence-based mathematical-modeling competition workflow built on mathmodel-skill. Use for CUMCM, MCM/ICM, Diangong or custom modeling contests, including requirements, per-question modeling, actual Python runs, independent validation, paper assembly, team handoff and submission audit. Preserves ten stages and Critic/Red Team. Do not trigger for unrelated data analysis or ordinary paper review. Maintenance requests modify the skill rather than start a contest.

AI, LLMs & Agents

AI Kit

58

tigusigalpa/ai-kit

Use when installing, configuring, upgrading, explaining, or maintaining AI-KIT, the portable kit that gives AI coding agents verified project memory, stack rules, guardrails, model routing, and native client configuration.

AI, LLMs & Agents

Agnes AI Skill

47

jomeswang/agnes-ai-skill

Use when the user wants Agnes AI text, image, or video generation and should execute it through the agnes-ai-cli command line instead of hand-writing raw HTTP requests.

AI, LLMs & Agents

Facial Expression Prompting

41

zhouwei713/facial-expression-prompting

Direct believable character performance and generate complete AI video prompts for text-to-video models. Use for facial acting, microexpressions, emotional transitions, dialogue performance, or vague character ideas such as “an ancient beauty breaks down.” When the brief is vague or asks for a video prompt, expand it into a complete prompt with an adult character, scene, dramatic motivation, emotional progression, facial and body performance, camera and lighting, adaptively chosen duration and exact timeline, audio, consistency locks, and negative constraints. When the user explicitly asks onl

AI, LLMs & Agents

Agentx

44

DezXBT/AgentX

Drive X/Twitter from the CLI (read, post, DM, lists, communities, Grok, scheduling, analytics). Use when an agent needs to read or act on X/Twitter. Every command prints one JSON envelope.

AI, LLMs & Agents

Browse the most popular Claude skills, all ai, llms & agents skills, or write your own with the skills generator.