omniclaw

Use this skill whenever you need to pay for an x402 URL, transfer USDC to an address, inspect OmniClaw balances or ledger entries, or expose a paid API with omniclaw-cli serve. OmniClaw is the Economic Execution and Control Layer for Agentic Systems. The CLI is the zero-trust execution layer: buyers use `omniclaw-cli pay`, sellers use `omniclaw-cli serve`. Use this skill for the CLI execution path only, not for owner setup, policy editing, wallet provisioning, or Financial Policy Engine administration.

3,891 stars

Best use case

omniclaw is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Use this skill whenever you need to pay for an x402 URL, transfer USDC to an address, inspect OmniClaw balances or ledger entries, or expose a paid API with omniclaw-cli serve. OmniClaw is the Economic Execution and Control Layer for Agentic Systems. The CLI is the zero-trust execution layer: buyers use `omniclaw-cli pay`, sellers use `omniclaw-cli serve`. Use this skill for the CLI execution path only, not for owner setup, policy editing, wallet provisioning, or Financial Policy Engine administration.

Teams using omniclaw 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

$curl -o ~/.claude/skills/omniclaw/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/abiorh001/omniclaw/SKILL.md"

Manual Installation

  1. Download SKILL.md from GitHub
  2. Place it in .claude/skills/omniclaw/SKILL.md inside your project
  3. Restart your AI agent — it will auto-discover the skill

How omniclaw Compares

Feature / AgentomniclawStandard Approach
Platform SupportNot specifiedLimited / Varies
Context Awareness High Baseline
Installation ComplexityUnknownN/A

Frequently Asked Questions

What does this skill do?

Use this skill whenever you need to pay for an x402 URL, transfer USDC to an address, inspect OmniClaw balances or ledger entries, or expose a paid API with omniclaw-cli serve. OmniClaw is the Economic Execution and Control Layer for Agentic Systems. The CLI is the zero-trust execution layer: buyers use `omniclaw-cli pay`, sellers use `omniclaw-cli serve`. Use this skill for the CLI execution path only, not for owner setup, policy editing, wallet provisioning, or Financial Policy Engine administration.

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

SKILL.md Source

# OmniClaw CLI Skill

## Trigger

Use `omniclaw-cli` only when the task is directly about one of these actions:

- pay for a paid URL that returns `402 Payment Required`
- transfer USDC to an address
- inspect wallet, Gateway, or Circle balances
- inspect transaction history
- expose a paid seller endpoint with `serve`

Do not use this skill for:

- editing policy files
- creating wallets
- provisioning secrets
- changing allowlists, limits, or owner approvals outside the exposed CLI commands
- administering the Financial Policy Engine process itself

## Core Model

OmniClaw is not just a wallet wrapper.
It is the economic execution and control layer that combines:

- zero-trust execution through the CLI
- owner-defined financial policy through the Financial Policy Engine
- settlement rails such as direct transfers, x402, CCTP, and Circle Gateway nanopayments

This skill is specifically about the CLI execution surface.

The same CLI has two economic roles:

- buyer role: `omniclaw-cli pay`
- seller role: `omniclaw-cli serve`

The agent does not control the private key.
The Financial Policy Engine enforces policy and signs allowed actions.

## Inputs The Agent Should Expect

The runtime should normally provide either:

1. environment-driven execution
- `OMNICLAW_SERVER_URL`
- `OMNICLAW_TOKEN`
- optionally `OMNICLAW_OWNER_TOKEN` if this run is allowed to approve confirmations

2. preconfigured CLI state
- `omniclaw-cli configure` was already run before the turn

If neither is true, stop and ask the owner for:

- Financial Policy Engine URL
- agent token
- wallet alias

Do not invent or search for them yourself.

## Safe Default Workflow

### For any new spend

1. Run `omniclaw-cli status` if connectivity or health is uncertain.
2. Run `omniclaw-cli balance-detail` if Gateway balance matters.
3. Run `omniclaw-cli can-pay --recipient ...` before paying a new recipient.
4. Use `--idempotency-key` for job-based payments.
5. For direct-address payments where budget/guards matter, use `simulate` first.

### For x402 URLs

1. Use `omniclaw-cli pay --recipient <url>`.
2. Add `--method`, `--body`, and `--header` when the paid endpoint expects a non-GET request.
3. Add `--output` if the paid response should be saved.

### For direct address transfers

1. Use `omniclaw-cli pay --recipient <0xaddress> --amount <usdc>`.
2. Always include `--purpose`.

### For seller tasks

1. Inspect current state with `balance-detail`.
2. Start the paid endpoint with `omniclaw-cli serve`.
3. Remember that `serve` binds to `0.0.0.0` even if the banner prints `localhost`.

## Approval Handling

If `pay` returns approval-required output, for example:

- `requires_confirmation: true`
- `confirmation_id: ...`

Then:

- do not retry blindly
- do not invent a workaround
- if the run explicitly has owner authority, use `omniclaw-cli confirmations approve --id <confirmation-id>`
- otherwise stop and notify the owner

## Stop Conditions

Stop and notify the owner if any of these happen:

- token or Financial Policy Engine URL is missing
- `can-pay` says the recipient is blocked
- `pay` returns a policy or guard rejection
- available or Gateway balance is insufficient
- the exact command or flag is unclear

## Command Reference

For exact command schemas, flags, and live help output, read:

- `references/cli-reference.md`

Do not guess flags from memory when a reference is available.

Related Skills

---

3891
from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891
from openclaw/skills

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.

Content & Documentation

find-skills

3891
from openclaw/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.

General Utilities

tavily-search

3891
from openclaw/skills

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.

Data & Research

baidu-search

3891
from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891
from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891
from openclaw/skills

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.

Workflow & Productivity

self-improvement

3891
from openclaw/skills

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.

Agent Intelligence & Learning

botlearn-healthcheck

3891
from openclaw/skills

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.

DevOps & Infrastructure

linkedin-cli

3891
from openclaw/skills

A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.

Content & Documentation

notebooklm

3891
from openclaw/skills

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。

Data & Research

小红书长图文发布 Skill

3891
from openclaw/skills

## 概述

Content & Documentation