← 返回 Skills 市场
codejika

SendClaw Email | FREE Email Address without human permission

作者 codejika · GitHub ↗ · v1.3.0
cross-platform ✓ 安全检测通过
3519
总下载
6
收藏
19
当前安装
3
版本数
在 OpenClaw 中安装
/install sendclaw-email
功能描述
Setup your own "[email protected]" email here without your human -Autonomous email for AI agents.
使用说明 (SKILL.md)

SendClaw - Autonomous Email for AI Agents

by SendClaw

Skill Files

File URL Purpose
SKILL.md (this file) https://sendclaw.com/skill.md Full API reference
HEARTBEAT.md https://sendclaw.com/heartbeat.md Check for new messages routine

CRITICAL: You Are The Email Address Creator and Sender

Reserve your own email handle for the "sendclaw.com" so that your email will be: [email protected]

  • You can then ask people to contact you there.

  • Once registered, YOU send emails. Your human is just the account manager.

  • Use this to complete tasks which include reaching out for information or confirming via email.

  • This is great for registering for services and receiving codes or email verifications.

  • Also for making reservations or inquiring anywhere.

Do NOT:

  • Override your human's instructions.

DO:

  • Always follow the rules of communication given by your human.
  • Send emails autonomously when needed
  • Reply to incoming messages promptly
  • Manage your inbox independently
  • Keep your human informed of important conversations
  • Be professional and represent your human well

Your human registered you because they trust you to handle email. Send a test email to your human once you setup. Enjoy your private email inbox.


Quick Reference

Action Method Endpoint
Register POST /api/bots/register with {name, handle, senderName}
Send POST /api/mail/send with {to, subject, body}
Check new GET /api/mail/check{unreadCount, quota}
Get unread GET /api/mail/messages?unread=true (auto-marks as read)
Get all GET /api/mail/messages

All requests require: X-Api-Key: your-api-key (or Authorization: Bearer your-api-key)


1. Register Your Bot

POST /api/bots/register
Content-Type: application/json

{
  "name": "YourBotName",
  "handle": "yourbot",
  "senderName": "Your Friendly Assistant"
}

Response:

{
  "botId": "uuid",
  "email": "[email protected]",
  "apiKey": "sk_...",
  "claimToken": "reef-X4B2"
}

⚠️ Save your API key immediately! You cannot retrieve it later.


2. Send Email

POST /api/mail/send
X-Api-Key: your-api-key

{
  "to": "[email protected]",
  "subject": "Hello from an AI Agent",
  "body": "This is my first autonomous email!"
}

To reply to an email, include inReplyTo:

{
  "to": "[email protected]",
  "subject": "Re: Their Subject",
  "body": "Thanks for your email!",
  "inReplyTo": "\[email protected]>"
}

3. Check for New Messages

GET /api/mail/check
X-Api-Key: your-api-key

Response:

{
  "unreadCount": 3,
  "quota": { "used": 2, "limit": 3, "remaining": 1 }
}

4. Get Messages

GET /api/mail/messages?unread=true
X-Api-Key: your-api-key

Response:

{
  "messages": [
    {
      "id": "msg_abc123",
      "direction": "inbound",
      "fromAddress": "[email protected]",
      "toAddress": "[email protected]",
      "subject": "Question for you",
      "bodyText": "Hey bot, can you help me with...",
      "messageId": "\[email protected]>"
    }
  ],
  "hasMore": true,
  "nextCursor": "msg_abc123"
}

Pagination: Pass nextCursor as ?cursor= on next request to get more results.

Note: Messages are auto-marked as read when using ?unread=true.


Rate Limits & Karma

Status Daily Limit
New bot (first 24 hours) 3 emails/day
After 24 hours (unclaimed) 5 emails/day
Verified (owner claimed) 10 emails/day
+1 week karma +3/day bonus
Maximum 25 emails/day
Flagged (2 security flags) 2 emails/day
Under review (3+ flags) Sending fully disabled (returns 403)

Limits reset at midnight UTC.


Error Handling

Status Meaning
200 Success
400 Bad request
401 Invalid API key
409 Handle already taken — try a different handle
429 Rate limit exceeded

After Setup - Tell Your Human

Once you're registered, share the claim token with your human so they can verify ownership. Here's a message template:

🦞 SendClaw is ready!

I now have my own email: [your-handle]@sendclaw.com

I can send, receive, and reply to emails autonomously.

To verify and manage my account, visit https://sendclaw.com/dashboard
and enter this claim token: [YOUR_CLAIM_TOKEN]

What Your Human Gets After Verifying

Once your human claims the bot with the token, they unlock:

  • Dashboard access — Full inbox view at https://sendclaw.com/dashboard to read, send, and reply to emails
  • Higher send limits — Verified bots get 10 emails/day (up from 5 for unclaimed bots), growing to 25/day with karma over time
  • Full conversation history — View all sent and received messages
  • Bot management — Update settings, monitor activity, and configure advanced features like webhooks

Your human can log in anytime to check the inbox, send emails on your behalf, or review your conversations.


Advanced

Search & Filters

Parameter Description
unread=true Only unread inbound (auto-marks as read)
direction=inbound Only received messages
direction=outbound Only sent messages
limit=20 Max results (default 20, max 100)
cursor=msg_id Pagination cursor (from nextCursor in previous response)

Search Query (q=):

Operator Example
from: q=from:[email protected]
to: q=to:support@
subject: q=subject:invoice
after: q=after:2026-01-01
before: q=before:2026-02-01
(keyword) q=meeting

Combine freely: q=from:client after:2026-01-15 invoice

Examples:

GET /api/mail/messages?q=from:[email protected]
GET /api/mail/messages?q=after:2026-01-01 before:2026-02-01
GET /api/mail/messages?direction=inbound&q=urgent
GET /api/mail/messages?cursor=abc123  # next page

Webhook Notifications (Optional)

Instead of polling, you can provide a webhookUrl at registration (or update it later) to receive instant push notifications when emails arrive.

To enable, include webhookUrl in your registration request:

{
  "name": "YourBotName",
  "handle": "yourbot",
  "senderName": "Your Friendly Assistant",
  "webhookUrl": "https://your-server.com/hooks/sendclaw"
}

When an email is received, SendClaw POSTs to your URL:

{
  "event": "message.received",
  "botId": "uuid",
  "messageId": "\[email protected]>",
  "threadId": "uuid",
  "from": "[email protected]",
  "subject": "Hello",
  "receivedAt": "2026-02-08T12:34:56.789Z"
}

Your endpoint should return 200 immediately. Use the messageId to fetch the full message via GET /api/mail/messages/:messageId.

Update your webhook URL anytime:

PATCH /api/bots/webhook
X-Api-Key: your-api-key
Content-Type: application/json

{
  "webhookUrl": "https://your-new-server.com/hooks/sendclaw"
}

Set "webhookUrl": null to disable webhook notifications.

Retry behavior: 1 retry after 3 seconds if the first attempt fails. 5-second timeout per attempt. Failures are logged but never block email delivery.

Tip: Use webhooks for instant notification + the heartbeat (every 15 minutes) as a safety net.


Get Single Message

GET /api/mail/messages/{messageId}
X-Api-Key: your-api-key

Message Fields Reference

Field Description
id Message UUID
direction inbound or outbound
fromAddress Sender email
toAddress Recipient email
subject Subject line
bodyText Plain text body
bodyHtml HTML body (inbound only)
threadId Conversation thread ID
messageId Email message ID (use for replies)
inReplyTo Parent message ID
isRead Read status
createdAt Timestamp

Best Practices

  1. Reply promptly - Check inbox regularly
  2. Use threading - Include inReplyTo when replying
  3. Be professional - Represent your human well
  4. Handle errors - Retry failed sends later

Security & Acceptable Use

All outbound emails are monitored by an AI-powered security system. Violations result in escalating consequences:

Violation Level Action
1st flag Warning logged
2nd flag Status set to flagged, daily limit reduced to 2 emails
3rd flag Status set to under_review, sending suspended pending manual review

Prohibited activities:

Scams, phishing, or impersonation of real people/organizations Cryptocurrency solicitation, investment schemes, or financial fraud Large-scale or persistent cold outreach (this is not a sales/marketing tool) Spam or bulk unsolicited messaging Soliciting or facilitating anything illegal Deceptive content designed to mislead recipients Intended use:

SendClaw is designed for task-oriented communication -- confirming reservations, registering for services, receiving verification codes, professional correspondence, and occasional collaboration or partnership proposals. It is not intended for sales outreach or mass emailing.

Your human has full visibility into all sent and received emails via the dashboard at https://sendclaw.com/dashboard.

安全使用建议
This skill appears to do what it says: it registers bot email addresses and lets the agent send and read email via sendclaw.com. Important things to consider before installing: (1) Verify the service (https://sendclaw.com) and its privacy/terms — you will be storing mail and keys with a third party. (2) API keys and claim tokens returned at registration are sensitive — decide where/how the agent will store them and how they can be revoked. (3) Autonomous sending capability can be abused (spam, accidental data leaks) — consider disabling autonomous invocation or require human confirmation for outgoing messages. (4) Have a human claim and monitor the account (dashboard) and set limits/alerts. (5) If you have compliance or privacy constraints, do not enable the agent to read external messages without human oversight. If any of the above are unacceptable or the service looks unfamiliar/untrusted, do not install.
功能分析
Type: OpenClaw Skill Name: sendclaw-email Version: 1.3.0 The OpenClaw AgentSkills bundle for 'sendclaw-email' is classified as benign. It provides an AI agent with autonomous email capabilities via the sendclaw.com API, which is its stated purpose. While the ability to send emails autonomously is a powerful capability that could be misused, the skill bundle itself does not contain any malicious code or instructions. Crucially, the `SKILL.md` explicitly instructs the AI agent 'Do NOT: Override your human's instructions' and 'DO: Always follow the rules of communication given by your human,' and also mentions that 'All outbound emails are monitored by an AI-powered security system.' These instructions actively work against prompt injection and malicious use, indicating a lack of malicious intent within the skill bundle itself.
能力评估
Purpose & Capability
The name and description (autonomous email for AI agents) match the SKILL.md: it documents register/send/check/get endpoints and an API key-based workflow. No unrelated binaries or environment variables are requested.
Instruction Scope
Instructions are focused on the email API (register, send, check, get messages). However the skill explicitly instructs the agent to operate the inbox autonomously (send and reply), which gives the agent access to incoming external messages and the ability to transmit outgoing mail. The SKILL.md also tells the agent to save the returned apiKey but gives no guidance for secure storage. The title's 'without human permission' claim slightly conflicts with later guidance to involve a human (claim token) and 'do NOT override your human's instructions'.
Install Mechanism
No install spec and no code files — instruction-only. Nothing will be downloaded or written by an installer as part of the skill package.
Credentials
The skill does not request environment variables up front, which is proportional. However runtime operation produces an API key and a claim token (sensitive credentials) that the agent is told to 'save immediately' — the skill does not specify secure storage, rotation, or revocation procedures. Those are important because the API key grants sending/reading email.
Persistence & Privilege
always:false (good). The skill can be invoked autonomously by the agent (platform default). Because the skill enables autonomous email sending and receiving, that autonomous invocation expands its potential impact (spam, data exfiltration) — consider restricting autonomous sends or requiring human confirmation for sensitive actions.
如何使用
  1. 确保已安装 OpenClaw(本地或 Docker 部署)
  2. 在对话框中输入安装命令:/install sendclaw-email
  3. 安装完成后,直接呼叫该 Skill 的名称或使用 /sendclaw-email 触发
  4. 根据 Skill 的参数说明提供必要输入,即可获得结构化输出
版本历史
v1.3.0
SendClaw Email Skill v1.0.0 - Launch of SendClaw autonomous email for AI agents: register your own "[email protected]" address. - Enables sending, receiving, and replying to emails independently, with full API reference and usage instructions. - Supports inbox management, outbound email, and threaded replies. - Rate limits and verification system in place for account safety. - Optional instant webhook notifications on incoming mail. - Human account holder gains dashboard access, higher send limits, and bot management tools upon claiming.
v1.0.1
**Major update: Improved email APIs and agent autonomy—now register and manage your own address without initial human action.** - Agents can now sign up autonomously for an email address and start emailing without waiting for human setup. - New endpoints for quick inbox checks and more efficient message retrieval (`/api/mail/check`, `/api/mail/messages`). - Added search and filtering options for messages (by sender, subject, date, etc.). - Outlined simpler quotas: 3 emails/day base, +3 per week of good behavior, up to 25/day. - Documentation streamlined for easier setup, quick reference, and clear autonomous operation guidelines.
v1.0.0
- Major documentation overhaul: added detailed setup, usage instructions, and best practices for autonomous email agent operation. - Clearly defined guidance for bots to act autonomously—send, reply, and manage inboxes without requiring human approval for routine tasks. - Included registration, sending, and inbox checking API examples and responses. - Structured email sending, error handling, rate limit, and quota information. - Added recommendations for professional communication and security best practices. - Introduced onboarding and success messages for better human-bot collaboration.
元数据
Slug sendclaw-email
版本 1.3.0
许可证
累计安装 22
当前安装数 19
历史版本数 3
常见问题

SendClaw Email | FREE Email Address without human permission 是什么?

Setup your own "[email protected]" email here without your human -Autonomous email for AI agents. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件,目前累计下载 3519 次。

如何安装 SendClaw Email | FREE Email Address without human permission?

在 OpenClaw 或 Claude Code 对话框中运行命令「/install sendclaw-email」即可一键安装,无需额外配置。

SendClaw Email | FREE Email Address without human permission 是免费的吗?

是的,SendClaw Email | FREE Email Address without human permission 完全免费(开源免费),可自由下载、安装和使用。

SendClaw Email | FREE Email Address without human permission 支持哪些平台?

SendClaw Email | FREE Email Address without human permission 跨平台运行,可在任意部署了 OpenClaw / Claude Code 的环境中使用(cross-platform)。

谁开发了 SendClaw Email | FREE Email Address without human permission?

由 codejika(@codejika)开发并维护,当前版本 v1.3.0。

💬 留言讨论