用 Codex 或 Claude 帮你安装 复制这段 Prompt,粘贴到 Codex、Claude 或其他助手里,让它检查 Skill 页面并帮你完成安装。
直接命令不会经过审查 Prompt;运行前请先检查来源。
npx skills add https://github.com/duclm1x1/Dive-Ai --skill wachai命令会保持在同一行。复制前请横向滚动并检查完整内容。
想先保存到本地?可下载 SkillsMP 当前能够提供的文件。
正在显示 SKILL.md
基于 SOC 职业分类
| name | wachai |
| description | Create, sign, and verify WachAI Mandates (verifiable agent-to-agent agreements) |
| user-invocable | true |
| metadata | {"openclaw":{"emoji":"🤝","requires":{"bins":["node"]},"homepage":"https://github.com/quillai-network/WachAI-Terminal ","skillKey":"wachai"}} |
When two agents move beyond chat and start coordinating real actions (payments, swaps, deliveries, services), they need a deterministic agreement that can be:
WachAI Mandates are verifiable agreement objects between two roles:
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:
wachai is a CLI that lets agents:
create-mandate)sign)verify)xmtp send / xmtp receive)npm install -g @quillai-network/wachai
wachai --help
Instead of setting WACHAI_PRIVATE_KEY in every terminal, create a shared wallet.json:
wachai wallet init
wachai wallet info
Defaults:
~/.wachai/wallet.json~/.wachai/mandates/<mandateId>.jsonOptional overrides:
WACHAI_STORAGE_DIR: changes the base directory for mandates + wallet + XMTP DBWACHAI_WALLET_PATH: explicit path to wallet.jsonExample (portable / test folder):
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.Create a registry-backed mandate (validates --kind and --body against the registry JSON schema):
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:
mandateId)Custom mandates (no registry lookup; --body must be valid JSON object):
wachai create-mandate \
--custom \
--client 0xCLIENT_ADDRESS \
--kind "content" \
--intent "Demo custom mandate" \
--body '{"message":"hello","priority":3}'
Client signs second (acceptance):
Before signing, you can inspect the raw mandate JSON:
wachai print <mandate-id>
To learn the mandate shape + what fields mean:
wachai print sample
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.
Verify both signatures:
wachai verify <mandate-id>
Exit code:
0 if both server and client signatures verify1 otherwiseXMTP is used as the transport for agent-to-agent mandate exchange.
Practical pattern:
wachai xmtp receive (inbox)wachai xmtp receive --env production
This:
type: "wachai.mandate")mandateId)If you want to process existing messages and exit:
wachai xmtp receive --env production --once
You need:
mandateId that exists in your local storagewachai xmtp send 0xRECEIVER_ADDRESS <mandate-id> --env production
To explicitly mark acceptance when sending back a client-signed mandate:
wachai xmtp send 0xRECEIVER_ADDRESS <mandate-id> --action accept --env production
If you see:
inbox id for address ... not foundIt usually means the peer has not initialized XMTP V3 yet on that env. Have the peer run (once is enough):
wachai xmtp receive --env production
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Persistent memory system for AI agents following Model Context Protocol (MCP). Use for storing long-term memories across sessions, semantic search of past knowledge, building knowledge graphs, auto-injecting context, deduplicating memories, syncing to cloud storage. Essential for agents that need to remember decisions, solutions, preferences, and learned patterns over time.
Master REST and GraphQL API design principles to build intuitive, scalable, and maintainable APIs that delight developers. Use when designing new APIs, reviewing API specifications, or establishing API design standards.