跳到正文
cccskills
免费在 GitHub 公开

clawring

Phone calling skill for OpenClaw: agent makes real outbound phone calls to users for alerts, briefings, reminders, and urgent notifications. Managed service, no Twilio setup needed. 100+ countries, 70+ voices.

中文简介正在准备中。当前显示原文说明。

查看安装方法

包含的文件(1)

  • SKILL.md3.9 KB

SKILL.md(原文)

安装前可以查看交给 AI 代理的指令内容。

clawr.ing — Phone Calling Skill

Give your OpenClaw agent the ability to make real outbound phone calls to you. The agent calls you — you don't call the agent. There is no inbound phone number.

Website: clawr.ing ClawHub: clawhub.ai/marcospgp/clawring

When to Use This Skill

  • Your agent needs to reach you urgently and chat messages aren't enough
  • Morning briefings, daily summaries, or scheduled check-ins
  • Price alerts, server monitoring, build notifications — anything time-sensitive
  • You want a hands-free way to interact with your agent (walking, driving, gym)

What This Skill Does

  1. Agent sends a REST API call to initiate an outbound phone call to you
  2. clawr.ing dials your phone number via its telephony infrastructure
  3. You answer and have a real voice conversation with your agent
  4. Human speech is transcribed to text, sent to the agent, and the agent's text reply is spoken back via TTS
  5. Everything the agent can do in chat still works on the phone — web search, setting alerts, running tasks

The agent sees the conversation as a simple text-based API (REST with long-polling). No WebSocket needed on the agent side.

How to Use

Setup

  1. Sign up at clawr.ing
  2. Copy the setup prompt from your dashboard
  3. Paste it into your OpenClaw agent's chat
  4. The agent reads the prompt, stores the API key, and gains phone calling capability

That's it. No Twilio account, no API keys to configure, no webhooks to set up.

Basic Usage

Tell your agent when to call you:

Call me when my build finishes.
Call me every morning at 8am with a briefing.
Call me if Bitcoin drops below $50k.
Call me if the server goes down.

When the agent decides to call, it dials your phone, you pick up, and you talk. When you're done, just say bye and it hangs up.

During a Call

  • The agent puts you on hold with music while it works on longer tasks (web search, etc.)
  • A thinking sound plays while the agent is generating its response
  • You can interrupt the agent mid-sentence (barge-in) — it stops and listens
  • Everything the agent can do in chat works on the phone

Key Details

  • Outbound only: The agent calls you. You cannot call the agent. There is no inbound number.
  • Managed service: No Twilio setup, no API keys, no webhooks. Paste one prompt and it works.
  • 100+ countries: Call yourself from pretty much anywhere in the world.
  • 70+ voices: Choose a voice for your agent from the dashboard.
  • Model-agnostic: Works with any LLM that can make HTTP requests (Claude, GPT, Gemini, local models).
  • Fast model recommended: Assign the skill to a fast, lightweight model (Haiku-class) for natural conversation pace. Slow models make conversations feel laggy.

Example

User (in OpenClaw chat): "Call me if ETH goes above $4000."

The agent monitors the price. When ETH crosses $4000:

  1. Agent calls your phone
  2. You answer
  3. Agent: "Hey, ETH just crossed $4000. It's currently at $4,012. Want me to do anything?"
  4. You: "Yeah, sell half my position."
  5. Agent: "On it. Let me check your portfolio..." (hold music plays)
  6. Agent comes back with the result
  7. You: "Thanks, bye."
  8. Call ends.

Tips

  • Use a separate fast model for the calling skill so conversations feel natural
  • Set up alerts for things that are genuinely urgent — the phone is for things you can't afford to miss
  • The agent can call you proactively based on cron schedules, events, or triggers you define in OpenClaw
  • You can tell the agent your preferences for when it's okay to call (e.g., "don't call me after 10pm")

评价

还没有评价。欢迎分享你的使用感受。

评论

无需登录即可发表。欢迎分享使用感受、提问,或说明在哪些环境下无法运行。

还没有评论。来写第一条吧。

提交后会立即公开。请勿填写邮箱、电话等个人信息。URL 最多 2 个。

0 / 1000 字

此表单受 reCAPTCHA 保护,适用 Google 的隐私权政策和服务条款。

同一仓库的技能

Handle ActiveCampaign contact and marketing tasks through Rube MCP, a connection for agent tools. Find or create contacts, manage tags and subscriptions, enroll contacts in existing automated workflows, and create follow-up tasks.

中文简介正在准备中。当前显示英语简介。

  • Finding or registering contacts
  • Adding or removing contact tags
  • Subscribing contacts to lists or unsubscribing them
davepoon/buildwithclaude36652026年10月20日 更新

Research competitors’ live Meta and Google ads to identify opening hooks, offers, calls to action, and landing pages. Receive a sourced creative brief and up to three test ideas adapted to your product.

中文简介正在准备中。当前显示英语简介。

  • Find angles for new ad copy
  • Plan creative tests using competitor ads
  • Choose a landing page message
davepoon/buildwithclaude36652026年10月20日 更新

Analytics your AI agent can actually use. Track, analyze, run A/B experiments, and optimize across all your projects via CLI. Includes a growth playbook so your agent knows HOW to grow, not just what to track.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36652026年10月20日 更新

Teaches when to recall from long-term memory before acting and when to save durable decisions, corrections and failures afterwards. Use when a memory tool or MCP memory server is connected but the agent is not using it consistently, when the user complains that the assistant forgets preferences, conventions or past decisions between sessions, or when setting up persistent memory for a project. Works with any memory backend: a folder of Markdown files, a local MCP server, or a managed service.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36652026年10月20日 更新

Audit local AI coding-agent sessions with agenttrace for cost, tokens, tool failures, latency, anomalies, health, diffs, and CI gates.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36652026年10月20日 更新

Checks which private files (.env, keys, secrets) Claude Code and its subagents reached in this project, whether a value came into an agent's context, and which key to change, by running the open source agentwhy CLI over the session records Claude Code already keeps on disk. Use when the user asks whether the agent or a subagent read their .env or other secrets, which private files a session touched, whether a key leaked into the conversation, or which key to rotate. Runs locally and never prints a secret value.

中文简介正在准备中。当前显示原文说明。

davepoon/buildwithclaude36652026年10月20日 更新

查看 davepoon 的全部技能

报告此技能的问题