skills$openclaw/xmtp-agents
humanagent6.5k

by humanagent

xmtp-agents – OpenClaw Skill

xmtp-agents is an OpenClaw Skills integration for coding workflows. >

6.5k stars5.5k forksSecurity L1
Updated Feb 7, 2026Created Feb 7, 2026coding

Skill Snapshot

namexmtp-agents
description> OpenClaw Skills integration.
ownerhumanagent
repositoryhumanagent/xmtp-agent
languageMarkdown
licenseMIT
topics
securityL1
installopenclaw add @humanagent/xmtp-agent
last updatedFeb 7, 2026

Maintainer

humanagent

humanagent

Maintains xmtp-agents in the OpenClaw Skills directory.

View GitHub profile
File Explorer
55 files
.
building-agents
rules
events-lifecycle.md
866 B
events-text.md
913 B
middleware-basics.md
1.3 KB
middleware-command-router.md
1.2 KB
setup-environment.md
751 B
setup-from-env.md
1.1 KB
SKILL.md
2.8 KB
creating-inline-actions
rules
builder-create.md
1.2 KB
config-menus.md
1.5 KB
helpers-confirmation.md
947 B
helpers-selection.md
1.1 KB
SKILL.md
4.0 KB
handling-attachments
rules
receive-attachment.md
1.2 KB
send-remote-attachment.md
1.1 KB
upload-callback.md
1.6 KB
SKILL.md
1.8 KB
handling-commands
rules
filters-message-types.md
1.1 KB
guards-codec.md
1.1 KB
validators-hex.md
811 B
SKILL.md
1.5 KB
handling-transactions
rules
balance-check.md
1.7 KB
receive-transaction-reference.md
1.6 KB
send-usdc-transfer.md
1.9 KB
SKILL.md
3.6 KB
managing-groups
rules
create-group.md
1.3 KB
members-add.md
1.2 KB
permissions-roles.md
1.4 KB
welcome-on-install.md
2.2 KB
SKILL.md
2.0 KB
resolving-domains
rules
extract-mentions.md
1.4 KB
profiles-farcaster.md
1.5 KB
resolve-address.md
1.3 KB
SKILL.md
3.9 KB
sending-reactions
rules
patterns-thinking.md
1.6 KB
receive-reaction.md
1.2 KB
send-reaction.md
1.1 KB
SKILL.md
1.7 KB
_meta.json
270 B
SKILL.md
2.0 KB
SKILL.md

name: xmtp-agents description: > Building and extending XMTP agents with the Agent SDK. Use when: (1) creating or configuring an XMTP agent, (2) implementing agent features (commands, attachments, reactions, groups, transactions, inline actions, or domain resolution). license: MIT metadata: author: xmtp version: "1.0.0"

XMTP agents

Build event-driven messaging agents on the XMTP network. This skill is the entry point; use the sub-skills below for specific features.

When to apply

  • Starting or configuring a new XMTP agent
  • Adding behavior: commands, attachments, reactions, groups, payments, inline actions, or address/domain resolution

Sub-skills

Sub-skillUse when
building-agentsSetup, env vars, text/lifecycle events, middleware
handling-commandsSlash commands, validators, message filters, type guards
handling-attachmentsSend/receive files, remote attachments, upload storage
sending-reactionsSend or receive reactions, thinking/reply patterns
managing-groupsCreate groups, add members, roles, welcome-on-install
handling-transactionsUSDC transfers, balance checks, transaction references
creating-inline-actionsInline actions, confirmation/selection helpers, config menus
resolving-domainsResolve addresses, Farcaster profiles, extract mentions

How to use

  1. Pick the sub-skill that matches the task (e.g. slash commands → handling-commands).
  2. Read that sub-skill’s SKILL.md and its rules/ for step-by-step guidance.
  3. For SDK or API details, use the xmtp-docs skill (index + specific page fetch).

Quick start

Install the Agent SDK, create an agent from env, handle text, then start:

npm install @xmtp/agent-sdk

Create the agent and handle messages using patterns from building-agents (setup, events, middleware). For commands, attachments, reactions, groups, transactions, inline actions, or resolution, use the corresponding sub-skill above.

README.md

No README available.

Permissions & Security

Security level L1: Low-risk skills with minimal permissions. Review inputs and outputs before running in production.

Requirements

  • OpenClaw CLI installed and configured.
  • Language: Markdown
  • License: MIT
  • Topics:

FAQ

How do I install xmtp-agents?

Run openclaw add @humanagent/xmtp-agent in your terminal. This installs xmtp-agents into your OpenClaw Skills catalog.

Does this skill run locally or in the cloud?

OpenClaw Skills execute locally by default. Review the SKILL.md and permissions before running any skill.

Where can I verify the source code?

The source repository is available at https://github.com/openclaw/skills/tree/main/skills/humanagent/xmtp-agent. Review commits and README documentation before installing.