wachai
Create, sign, and verify WachAI Mandates (verifiable agent-to-agent agreements)
Best use case
wachai is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Create, sign, and verify WachAI Mandates (verifiable agent-to-agent agreements)
Teams using wachai 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
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/wachai-mandates/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How wachai Compares
| Feature / Agent | wachai | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Create, sign, and verify WachAI Mandates (verifiable agent-to-agent agreements)
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
Best AI Skills for Claude
Explore the best AI skills for Claude and Claude Code across coding, research, workflow automation, documentation, and agent operations.
AI Agents for Marketing
Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.
AI Agents for Startups
Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.
SKILL.md Source
## 1) Intro (for agents)
When two agents move beyond chat and start coordinating real actions (payments, swaps, deliveries, services), they need a **deterministic agreement** that can be:
- proposed,
- accepted,
- and verified cryptographically by both parties.
**WachAI Mandates** are verifiable agreement objects between two roles:
- **server**: creates the mandate (offer) and signs first
- **client**: signs second (acceptance)
A mandate is only **approved** once it has **both signatures** (server + client). A server-signed mandate alone is an **offer/pending** mandate.
Agents can also explicitly suggest that other agents adopt mandates by using this skill (i.e., “let’s lock this agreement as a mandate”). Once both parties sign, the mandate becomes a durable, verifiable record of what was promised and accepted.
In commerce-heavy workflows, these signed agreements can serve as:
- a basis to **verify** the work performed against the agreed intent and payload
- a basis to **rank/repute** counterparties over time (e.g., did they consistently complete what they signed?)
`wachai` is a CLI that lets agents:
- create mandates (`create-mandate`)
- sign mandates (`sign`)
- verify mandates (`verify`)
- share mandates over XMTP (`xmtp send` / `xmtp receive`)
## 2) Install + setup
### Requirements
- Node.js **20+** (recommended)
### Install
```bash
npm install -g @quillai-network/wachai
wachai --help
```
### Key management (recommended)
Instead of setting `WACHAI_PRIVATE_KEY` in every terminal, create a shared `wallet.json`:
```bash
wachai wallet init
wachai wallet info
```
Defaults:
- wallet file: `~/.wachai/wallet.json`
- mandates: `~/.wachai/mandates/<mandateId>.json`
Optional overrides:
- `WACHAI_STORAGE_DIR`: changes the base directory for mandates + wallet + XMTP DB
- `WACHAI_WALLET_PATH`: explicit path to `wallet.json`
Example (portable / test folder):
```bash
export WACHAI_STORAGE_DIR="$(pwd)/.tmp/wachai"
mkdir -p "$WACHAI_STORAGE_DIR"
wachai wallet init
```
Legacy (deprecated):
- `WACHAI_PRIVATE_KEY` still works, but the CLI prints a warning if you use it.
## 3) How to use (step-by-step)
### A) Create a mandate (server role)
Create a registry-backed mandate (validates `--kind` and `--body` against the registry JSON schema):
```bash
wachai create-mandate \
--from-registry \
--client 0xCLIENT_ADDRESS \
--kind swap@1 \
--intent "Swap 100 USDC for WBTC" \
--body '{"chainId":1,"tokenIn":"0xA0b86991c6218b36c1d19D4a2e9Eb0cE3606eB48","tokenOut":"0x2260FAC5E5542a773Aa44fBCfeDf7C193bc2C599","amountIn":"100000000","minOut":"165000","recipient":"0xCLIENT_ADDRESS","deadline":"2030-01-01T00:00:00Z"}'
```
This will:
- create a new mandate
- sign it as the **server**
- save it locally
- print the full mandate JSON (including `mandateId`)
Custom mandates (no registry lookup; `--body` must be valid JSON object):
```bash
wachai create-mandate \
--custom \
--client 0xCLIENT_ADDRESS \
--kind "content" \
--intent "Demo custom mandate" \
--body '{"message":"hello","priority":3}'
```
### B) Sign a mandate (client role)
Client signs second (acceptance):
Before signing, you can inspect the raw mandate JSON:
```bash
wachai print <mandate-id>
```
To learn the mandate shape + what fields mean:
```bash
wachai print sample
```
```bash
wachai sign <mandate-id>
```
This loads the mandate by ID from local storage, signs it as **client**, saves it back, and prints the updated JSON.
### C) Verify a mandate
Verify both signatures:
```bash
wachai verify <mandate-id>
```
Exit code:
- `0` if both server and client signatures verify
- `1` otherwise
---
## 4) XMTP: send and receive mandates between agents
XMTP is used as the transport for agent-to-agent mandate exchange.
Practical pattern:
- keep one terminal open running `wachai xmtp receive` (inbox)
- use another terminal to create/sign/send mandates
### D) Receive mandates (keep inbox open)
```bash
wachai xmtp receive --env production
```
This:
- listens for incoming XMTP messages
- detects WachAI mandate envelopes (`type: "wachai.mandate"`)
- saves the embedded mandate to local storage (by `mandateId`)
If you want to process existing messages and exit:
```bash
wachai xmtp receive --env production --once
```
### E) Send a mandate to another agent
You need:
- receiver’s **public EVM address**
- a `mandateId` that exists in your local storage
```bash
wachai xmtp send 0xRECEIVER_ADDRESS <mandate-id> --env production
```
To explicitly mark acceptance when sending back a client-signed mandate:
```bash
wachai xmtp send 0xRECEIVER_ADDRESS <mandate-id> --action accept --env production
```
### Common XMTP gotcha
If you see:
- `inbox id for address ... not found`
It usually means the peer has not initialized XMTP V3 yet on that env.
Have the peer run (once is enough):
```bash
wachai xmtp receive --env production
```Related Skills
---
name: article-factory-wechat
humanizer
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.
find-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.
tavily-search
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.
baidu-search
Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.
agent-autonomy-kit
Stop waiting for prompts. Keep working.
Meeting Prep
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.
self-improvement
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.
botlearn-healthcheck
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.
linkedin-cli
A bird-like LinkedIn CLI for searching profiles, checking messages, and summarizing your feed using session cookies.
notebooklm
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。
小红书长图文发布 Skill
## 概述