metamask-agent-workflows
Use when the user needs to perform multi-step operations with the MetaMask Agentic CLI such as onboarding, login, swapping tokens, bridging across chains, opening/closing/modifying perpetual positions, prediction market trading, Aave V3 lending and borrowing, or troubleshooting CLI issues.
- Installs
- 260
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/metamask/agent-skills --skill metamask-agent-workflows- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads metamask-agent-workflows automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
MetaMask Agent Workflows
Repeatable multi-step patterns for the mm CLI. Load a workflow file when the user's request is a pattern, not a single command.
Workflow Routing
| Pattern | Workflow |
|---|---|
| First time setup and onboarding | onboarding.md |
| Login flow | login.md |
| Troubleshooting decision tree | troubleshooting.md |
| Swap quote-review-execute flow | swap.md |
| Bridge quote-review-execute flow | bridge.md |
| Open a perpetual position flow | perps-open-position.md |
| Close a perpetual position flow | perps-close-position.md |
| Modify a perpetual position flow | perps-modify-position.md |
| Predict first-time setup and credentials | predict-setup.md |
| Deposit or withdraw pUSD from Predict wallet | predict-funding.md |
| Search and browse prediction markets | predict-markets.md |
| Quote and place a prediction order | predict-place-order.md |
| View or cancel Predict orders and positions | predict-manage-orders.md |
| View Predict portfolio and redeem winnings | predict-portfolio.md |
| Token discovery, prices, and market data | market-data.md |
| Supply assets to Aave V3 | aave-supply.md |
| Withdraw assets from Aave V3 | aave-withdraw.md |
| Borrow from Aave V3 | aave-borrow.md |
| Repay Aave V3 debt | aave-repay.md |
| Toggle Aave V3 collateral | aave-collateral.md |
| Check Aave V3 positions and health factor | aave-positions.md |
| Discover Aave V3 tokens, rates, and liquidity | aave-markets.md |
Always use --toon for command output unless the user explicitly requests a different format.
Preflight
Run these checks before the first CLI operation in a session, in order.
1. Version compatibility
This skill is written for @metamask/agentic-cli v4.0.0 (see cliVersion in the frontmatter). Check the installed version:
mm --version
The installed version is the value after @metamask/agentic-cli/ (e.g. @metamask/agentic-cli/2.0.0 darwin-arm64 node-v22.18.0). Compare its major.minor against the pinned cliVersion. Optionally check the latest published version (best-effort; skip silently on network failure):
npm view @metamask/agentic-cli version
If the installed major.minor differs from the pinned cliVersion, or the installed version is behind the latest release, warn the user once and continue:
Version mismatch: installed CLI
<installed>, this skill is pinned to4.0.0, latest release is<latest>. Command syntax in this skill may be inaccurate until they are aligned. Update the CLI withnpm install -g @metamask/agentic-cli@latest, then re-install the skills withnpx skills add metaMask/agent-skills.
Run this check once per session. Do not block operations on it.
2. Readiness gate (authentication + initialization)
mm doctor is the single readiness check. Run it before the first CLI operation in a session:
mm doctor
It reports an authenticated boolean, an initialized boolean, and a list of hints. Do not run any other command until mm doctor reports both authenticated: true and initialized: true. Authentication and initialization are independent gates: a session can be authenticated while the project has no wallet mode selected, in which case any command that needs a wallet aborts before running with NOT_INITIALIZED — "Project not initialized." (hint: Run mm init to set up wallet and trading modes.).
A project counts as initialized only when a wallet mode is set — and, for server-wallet, a trading mode is set as well (byok needs only the wallet mode). Do not use mm init show as the check: it requires an initialized project and throws NOT_INITIALIZED on an uninitialized one rather than reporting state.
Remediate, then re-run mm doctor and confirm a clean result before doing anything else:
authenticated: false→ followworkflows/login.md(orworkflows/onboarding.mdfor first-time setup) to runmm login.authenticated: trueandinitialized: false→ followworkflows/onboarding.mdto runmm initand select a wallet mode (and a trading mode for server-wallet).
Command Discovery
Before constructing any command, run mm <command> --help to confirm the exact flags, syntax, and defaults. Do not guess flags from memory.
Output Rules
- Route silently. Do not announce which workflow you are loading.
- Surface errors from commands verbatim. Do not mask or reword them.
- If a command fails, check
mm <command> --helpand guide from there.
FAQ
What does the metamask-agent-workflows skill do?
Use when the user needs to perform multi-step operations with the MetaMask Agentic CLI such as onboarding, login, swapping tokens, bridging across chains, opening/closing/modifying perpetual positions, prediction market trading, Aave V3 lending and borrowing, or troubleshooting CLI issues.
How do I install metamask-agent-workflows?
Run npx skills add https://github.com/metamask/agent-skills --skill metamask-agent-workflows in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/metamask-agent-workflows/ (personal) or .claude/skills/metamask-agent-workflows/ (project).
Which AI agents can use metamask-agent-workflows?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is metamask-agent-workflows safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains metamask-agent-workflows?
It is published by metamask in metamask/agent-skills. It has 260 recorded installs.
More from metamask/agent-skills
metamask-agent-wallet
metamask/agent-skills
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 call returns an x402 payment-required result, or the agent needs to pay for a paywalled API, endpoint, file, tool, or resource. Single entry point for all mm CLI operations. Financial operations are protected by server-enforced access controls including MFA approval, configurable wallet policies, and trading-mode guards (guard/beast) that restrict operation scope independently of the agent.
Popular ai & agents skills
google-agents-cli-publish
google/agents-cli
This skill should be used when the user wants to "publish an agent", "publish my ADK agent", "register an agent with Gemini", "publish to Gemini" (formerly Gemini Enterprise), or needs guidance on the agents-cli publish gemini command. Also use when the user wants to "manage agents in Agent Registry", "list/update/delete registered agents", or "register an MCP server". Covers ADK vs A2A registration modes, programmatic and interactive usage, flag reference, auto-detection from deployment metadata, Agent Registry fleet management, and troubleshooting. Part of the agents-cli skills suite. Do NOT use for deployment (use google-agents-cli-deploy).
google-agents-cli-eval
google/agents-cli
This skill should be used when the user wants to "run an evaluation", "evaluate my agent", "evaluate my ADK agent", "write an eval dataset", "analyze eval failures", "compare eval results", "optimize agent", or needs guidance on the Gemini platform eval methodology and the Quality Flywheel. Covers eval metrics, dataset schema, LLM-as-judge scoring, and common failure causes. Applies to any agents-cli project, whatever framework the agent is written in. Do NOT use for agent API code patterns (ADK: use google-agents-cli-adk-code), deployment (use google-agents-cli-deploy), or project scaffolding (use google-agents-cli-scaffold).
skill-creator
anthropics/skills
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
codex-pet
prime-skills/runcomfy-agent-skills
Codex Pet generator on RunComfy. Build a Codex-compatible Codex Pet spritesheet.webp + pet.json from a single reference image, drop it into ${CODEXHOME:-$HOME/.codex}/pets/ / and Codex picks it up as a custom Codex Pet next to the 8 built-ins. This skill produces the exact Codex Pet atlas Codex expects (1536x1872 PNG/WebP, 8 cols x 9 rows, 192x208 cells, 9 animation states — idle, running-right, running-left, waving, jumping, failed, waiting, running, review). Calls OpenAI GPT Image 2 edit ONCE via the local RunComfy CLI as runcomfy run openai/gpt-image-2/edit to produce a canonical Codex Pet pose, then assembles all 9 animation rows programmatically with ImageMagick micro-transforms — no Codex Pro, no $imagegen, no OPENAIAPIKEY required, only RUNCOMFYTOKEN. Triggers on "codex pet", "create codex pet", "make codex pet", "hatch codex pet", "/hatch image", "desktop pet codex", "codex pets", "spritesheet.webp", or any explicit ask to build a custom pet for OpenAI Codex.
full-output-enforcement
leonxlnx/taste-skill
Overrides default LLM truncation behavior. Enforces complete code generation, bans placeholder patterns, and handles token-limit splits cleanly. Apply to any task requiring exhaustive, unabridged output.
executing-plans
obra/superpowers
Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available