weave

Use when creating crypto or stablecoin invoices, generating payment quotes, or tracking invoice payment status with the Weave CLI.

3,891 stars

Best use case

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

Use when creating crypto or stablecoin invoices, generating payment quotes, or tracking invoice payment status with the Weave CLI.

Teams using weave 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/weave/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/aryanj-nyc/weave/SKILL.md"

Manual Installation

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

How weave Compares

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

Frequently Asked Questions

What does this skill do?

Use when creating crypto or stablecoin invoices, generating payment quotes, or tracking invoice payment status with the Weave CLI.

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

# Weave

Weave is a CLI for crypto invoicing and cross-chain payment workflows. Use this when you need to create Bitcoin, Ethereum, Solana, USDC, or USDT invoices, generate payment quotes, and monitor settlement across supported networks such as Base, Tron, and Zcash for agent workflows or operations.

## Overview

Use `weave` for full Weave Cash invoice lifecycle workflows:

1. Create an invoice (`weave create`)
2. Generate payment instructions (`weave quote`)
3. Track settlement (`weave status` or `weave status --watch`)

## Guardrails

- Crypto-to-crypto only. Do not introduce fiat currencies, fiat conversions, or fiat-denominated behavior.
- Prefer machine-readable JSON output. Use `--human` only when explicitly requested.
- Never expose secrets (private keys, tokens, JWTs) in outputs.
- Treat network/API calls as failure-prone and handle non-zero exits explicitly.

## When Not To Use

- Do not use this skill for fiat invoice or fiat settlement workflows.
- Do not use this skill for editing Weave web UI/frontend code.
- Do not use this skill for unrelated wallet custody or private-key management tasks.
- Do not use this skill when the user wants non-Weave payment rails.

## Preflight

1. Confirm CLI availability:

```bash
weave --help
```

2. Discover runtime token/network support before choosing assets:

```bash
weave tokens
```

3. If `weave` is missing, provide compliant install guidance and ask before running:

```bash
go install github.com/AryanJ-NYC/weave-cash/apps/cli/cmd/weave@latest
weave --help
```

If Go is unavailable, use npm fallback:

```bash
npm i -g weave-cash-cli
weave --help
```

If both Go and npm are unavailable, report the missing prerequisites.

## Compliant Install Policy

- Prefer `metadata.openclaw.install` / `metadata.clawdbot.install` package-manager installs.
- Never suggest remote download commands piped directly to a shell interpreter.
- Detect and instruct; do not auto-install dependencies without explicit user approval.

## Token And Network Selection

- Always trust live `weave tokens` output from the runtime binary.
- Do not hardcode token/network lists in reasoning.
- `--receive-network` is required only for receive tokens that support multiple networks.
- Network aliases are accepted (for example `Ethereum|ETH`, `Solana|SOL`, `Tron|TRX` when supported by runtime output).

## Workflow

### 1) Create Invoice

Collect:

- `receive-token`
- `amount` (positive numeric string)
- `wallet-address`
- `receive-network` only when required by runtime token/network map
- optional buyer fields (`description`, `buyer-name`, `buyer-email`, `buyer-address`)

Command:

```bash
weave create \
  --receive-token USDC \
  --receive-network Ethereum \
  --amount 25 \
  --wallet-address 0x1111111111111111111111111111111111111111
```

Expected JSON shape:

```json
{
  "id": "inv_123",
  "invoiceUrl": "https://www.weavecash.com/invoice/inv_123"
}
```

Capture `id` for downstream `quote`/`status` calls.

### 2) Generate Quote

Collect:

- `invoice-id`
- `pay-token`
- `pay-network`
- `refund-address`

Command:

```bash
weave quote inv_123 \
  --pay-token USDT \
  --pay-network Ethereum \
  --refund-address 0x2222222222222222222222222222222222222222
```

Expected fields:

- `depositAddress`
- `depositMemo` (optional)
- `amountIn`
- `amountOut`
- `timeEstimate`
- `expiresAt`

### 3) Check Status

One-shot:

```bash
weave status inv_123
```

Watch mode:

```bash
weave status inv_123 --watch --interval-seconds 5 --timeout-seconds 900
```

Interpretation:

- Exit `0`: reached terminal status (`COMPLETED`, `FAILED`, `REFUNDED`, `EXPIRED`)
- Exit `2`: watch timeout (not a command failure)
- Exit `1`: command/API/network/validation failure

## Error Handling

When exit code is `1`, surface structured stderr JSON when present. Common API-derived shape:

```json
{
  "error": "api message",
  "status": 409,
  "details": {
    "error": "Invoice is not in PENDING status"
  }
}
```

If watch times out (exit `2`), treat as incomplete progress, not fatal failure. Recommend extending `--timeout-seconds` or rerunning a one-shot `weave status <invoice-id>`.

## Runtime Drift Rule

The installed binary and source tree can drift in token support. Always use runtime discovery (`weave tokens`) when deciding valid token/network combinations.

Related Skills

soul-weaver

3891
from openclaw/skills

AI Soul Weaver - 12 Curated Celebrity Templates + Custom Generation. Generate OpenClaw agent configurations through dialog or select from 12 world-famous tech & business leaders.

openclaw-soul-weaver

3891
from openclaw/skills

No waiting! Create professional-grade OpenClaw configurations in 30 seconds through natural conversation. Instantly generate enthusiast-level base configs that intelligently combine emotional and professional needs.

---

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