Token导航 LogoToken导航

Agent Skill · 开发

agentcall(agentcall 开发)

agentcall 用于处理音频、语音、转写和声音素材相关任务,适合在 OpenClaw 中需要整理音频流程、转写内容或生成配音素材时使用。可结合来源仓库、安装命令和原始 README 继续核验具体用法。安装前建议确认权限范围、维护状态,以及是否会触发联网、命令执行或文件读写。

agentcall 是开发类 Agent Skill,可用宿主为 OpenClaw,通过ClawHub获取,权限为接触敏感数据;许可证为 MIT-0,第三方扫描已通过,按安装量在开发类的 21,746 个 Skill 里排第 2,117。

总安装 20,328周安装 847GitHub Stars 公开资料未说明下载 6,776核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
MIT-0
版本
2.1.2

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:agentcall(agentcall 开发)
来源仓库:https://github.com/kintupercy/agentcall
安装命令:
openclaw skills install agentcall
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 OpenClaw 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

ClawHubOpenClaw
openclaw skills install agentcall

这个 Skill 是做什么的

开发类 Skill 面向写代码、改代码和排查问题,一般会读写仓库文件,部分还会执行构建或测试命令。

向您的客服人员提供真实电话号码,以便通过 AgentCall API 进行短信、OTP 验证和语音通话。

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 OpenClaw;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 openclaw skills install agentcall;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要接触敏感数据,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

agentcall 怎么安装?

在终端执行 openclaw skills install agentcall。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

agentcall 支持哪些 AI 工具?

公开资料标注支持 OpenClaw。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

agentcall 需要什么权限?

权限级别是接触敏感数据。该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

agentcall 是免费的吗?

来源标注的许可证是 MIT-0。本站不代收任何费用,也不托管安装包;能否商用、要不要署名,以许可证原文为准。

agentcall 用的人多吗?

公开数据是累计安装 20,328 次,近一周安装 847 次,下载 6,776 次。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

agentcall 安全吗?

第三方扫描结果为通过,但这只覆盖已知的静态检查项,不能替代自己读一遍源码和安装命令。

值得选的地方和要先想清楚的地方

值得选的地方

  • 专注 OpenClaw 一种宿主,触发方式和使用习惯不用来回切换。
  • 许可证明确为 MIT-0,商用和分发边界好判断。
  • 第三方扫描已通过,常见的高风险行为没有命中。

先想清楚的地方

  • 需要接触敏感数据,装到常用环境前要先评估影响面。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 OpenClaw,想直接扩展它能力的人。
  • 需要处理开发类任务、又不想每次都手写提示词的人。
  • 需要许可证清楚、并且有第三方扫描结果的团队项目。

不太适合

  • 环境里有大量密钥、凭证,不方便给第三方 Skill 读取的人。
  • 需要厂商级技术支持和 SLA 的生产系统。

开发类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
skill-vetter

技能审查员 · OpenClaw

8,779,018986操作浏览器MIT-0通过
ontology

本体论 · OpenClaw

6,636,960576只读MIT-0通过
entra-app-registration

内部应用程序注册 · Codex、Claude

6,631,872764接触敏感数据未明确通过
entra-app-registration

内部应用程序注册 · Codex、Claude

3,757,680201接触敏感数据未明确通过
nano-banana-pro

纳米香蕉专业版 · OpenClaw

3,526,898364接触敏感数据MIT-0有提醒
agentcall

agentcall 开发 · 本页

20,328—接触敏感数据MIT-0通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

AgentCall — Phone Numbers for AI Agents

You have access to the AgentCall API for phone numbers, SMS, voice calls, and AI voice calls. Inbound and outbound calls can both be answered or initiated by an OpenAI Realtime voice agent.

Authentication

All authenticated requests require: Authorization: Bearer <AGENTCALL_API_KEY>

The API key is available in the AGENTCALL_API_KEY environment variable.

Base URL

https://api.agentcall.co

For a complete plain-text API reference: GET https://api.agentcall.co/llms.txt (no auth required).

Phone Numbers

Provision a number:

POST /v1/numbers/provision
Body: { "type": "local", "country": "US", "label": "my-agent" }
Types: local ($2/mo), tollfree ($2.50/mo), mobile ($2/mo), sim ($8/mo, Pro only)
Response: { "id": "num_xxx", "number": "+12125551234", "type": "local", ... }

List numbers:

GET /v1/numbers
Query: ?limit=20&country=US&type=local

Get number details:

GET /v1/numbers/:id

Release a number (irreversible):

DELETE /v1/numbers/:id

Inbound AI Voice (Pro plan, $0.40/min, US and Canada numbers only)

Configure a phone number so incoming calls are answered autonomously by an OpenAI Realtime voice agent. The AI follows the system prompt you set.

Configure inbound AI on a number:

POST /v1/numbers/:numberId/inbound-config
Body: {
  "mode": "ai",
  "systemPrompt": "You are the front desk for Acme Plumbing. Greet the caller warmly, take their name and a brief description of the issue, then say someone will call back within 24 hours.",
  "voice": "shimmer",
  "firstMessage": "Hi, thanks for calling Acme Plumbing. How can I help?",
  "maxDurationSecs": 300
}

Get current inbound config:

GET /v1/numbers/:numberId/inbound-config

Disable inbound AI (calls hang up at carrier):

DELETE /v1/numbers/:numberId/inbound-config

Browse Voices and Prompt Templates (no auth)

Both endpoints are public — call them before configuring AI voice to avoid hallucinated business details and to pick a voice that fits the use case.

List the 8 voices with samples:

GET /v1/calls/voices
Returns: { voices: [{ id, name, trait, description, bestFor, sampleUrl }, ...], defaultVoice: "shimmer" }

List ready-made prompt templates:

GET /v1/calls/prompt-templates
Returns 5 templates with [BRACKETED] placeholders to fill in:
- receptionist (Front Desk) — recommends shimmer voice
- lead-qualifier (Sales, BANT-style) — coral
- appointment-booker — sage
- customer-support (FAQ Deflection) — ash
- call-screener (Anti-Spam) — verse
Each entry includes: id, title, description, recommendedVoice, maxDurationSecs, firstMessage, systemPrompt.

For a comprehensive prompt-writing guide: https://agentcall.co/docs/voice-prompts

SMS

Send SMS:

POST /v1/sms/send
Body: { "from": "num_xxx", "to": "+14155551234", "body": "Hello!" }
"from" can be a number ID or E.164 phone string

Get inbox:

GET /v1/sms/inbox/:numberId
Query: ?limit=20&otpOnly=true

Get a specific message:

GET /v1/sms/:messageId

Wait for OTP code (long-polls up to 60 seconds):

GET /v1/sms/otp/:numberId
Query: ?timeout=60000
Response: { "otp": "482913", "message": { ... } }

Outbound Voice Calls

Start a standard outbound call:

POST /v1/calls/initiate
Body: { "from": "num_xxx", "to": "+14155551234", "record": false }

Start an outbound AI voice call (Pro plan, $0.40/min): The AI handles the entire conversation autonomously based on your systemPrompt.

POST /v1/calls/ai
Body: {
  "from": "num_xxx",
  "to": "+14155551234",
  "systemPrompt": "You are calling to schedule a dentist appointment for Tuesday afternoon.",
  "voice": "shimmer",
  "firstMessage": "Hi, I'd like to schedule an appointment please.",
  "maxDurationSecs": 600
}

Voices (default: shimmer; preview each via GET /v1/calls/voices):

  • shimmer: bright, energetic — recommended starting point (default)
  • sage: calm, authoritative, confident — healthcare, finance, advisory
  • ash: warm, conversational — customer service, support lines
  • ballad: expressive, melodic — engaging, narrative conversations
  • coral: clear, professional — B2B calls, sales
  • echo: resonant, deep — formal inquiries, executive comms
  • verse: smooth, articulate — premium/luxury, executive communication
  • alloy: neutral, balanced — generic notifications, IVR-style flows

List call history:

GET /v1/calls
Query: ?limit=20

Get call details:

GET /v1/calls/:callId

Get AI call transcript:

GET /v1/calls/:callId/transcript
Response: { "entries": [{ "role": "ai" | "human", "text": "...", "timestamp": "..." }], "summary": "...", "duration": 111 }

Hang up an active call:

POST /v1/calls/:callId/hangup

Webhooks

Register a webhook:

POST /v1/webhooks
Body: { "url": "https://example.com/hook", "events": ["sms.inbound", "sms.otp", "call.status"] }
Events: sms.inbound, sms.otp, call.inbound, call.ringing, call.status, call.recording, call.transcript, number.released

List webhooks:

GET /v1/webhooks

Rotate webhook secret:

POST /v1/webhooks/:id/rotate

Delete a webhook:

DELETE /v1/webhooks/:id

Usage & Billing

Get usage breakdown:

GET /v1/usage
Query: ?period=2026-04

Pricing (per use, Pro plan):

  • SMS outbound: $0.015/msg
  • SMS inbound: $0.008/msg
  • Voice (standard outbound): $0.035/min
  • Voice (standard inbound): $0.015/min
  • AI voice (outbound): $0.40/min
  • AI voice (inbound): $0.40/min
  • Call recording: $0.01/min

Phone Number Format

All phone numbers must be E.164: +{country code}{number}, e.g. +14155551234

Common Workflows

Set up an AI receptionist on a phone number

  1. POST /v1/numbers/provision with { "type": "local" } — get a number
  2. GET /v1/calls/prompt-templates — pick a template (e.g. "receptionist")
  3. Replace [BRACKETED] placeholders with the customer's real business details
  4. POST /v1/numbers/:numberId/inbound-config with { "mode": "ai", "systemPrompt": "...", "voice": "shimmer", "firstMessage": "..." }
  5. Anyone who calls the number is now answered by the AI agent
  6. GET /v1/calls to see incoming call history; GET /v1/calls/:callId/transcript for transcripts

Test your app's SMS verification (QA)

  1. POST /v1/numbers/provision with { "type": "local" } — get a test number
  2. Enter the number into your staging app's verification form
  3. GET /v1/sms/otp/:numberId?timeout=60000 — wait for the verification code
  4. Assert the code arrives and your app accepts it
  5. DELETE /v1/numbers/:id — release the test number

Make an outbound AI voice call

  1. POST /v1/numbers/provision with { "type": "local" } — get a number (if you don't have one)
  2. POST /v1/calls/ai with { "from": "num_xxx", "to": "+1...", "systemPrompt": "..." } — start the call
  3. Wait for the call to complete
  4. GET /v1/calls/:callId/transcript — get the full conversation transcript

Error Codes

  • 401: Invalid or missing API key
  • 402 payment_method_required: Add a card before configuring billable features (returns setupUrl to Stripe Checkout)
  • 403 plan_limit_voice_ai: Inbound/outbound AI voice requires Pro plan ($19.99/mo)
  • 403 plan_limit_*: Other plan limits — upgrade at agentcall.co/dashboard
  • 400 carrier_not_supported: Inbound AI voice is only supported on US and Canada numbers
  • 404: Resource not found
  • 422: Validation error (check request body)
  • 429: Rate limit exceeded (100 req/min global; per-route limits on expensive endpoints)
  • 503 voice_ai_unavailable: Server-side OpenAI key issue — retry later

平台分布

OpenClaw

70.25%
按下载量换算4,760

安全审计

VirusTotal

通过

ClawScan

通过

Static analysis

通过

权限和风险

接触敏感数据

该 Skill 可能接触密钥、Token、环境变量或敏感配置,应进入高风险复核队列,默认不自动发布。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills