Token导航 LogoToken导航

Agent Skill · 效率

opencawl(opencawl 效率)

opencawl 用于补充效率相关能力,适合在 OpenClaw 中需要让 Agent 承接效率相关任务时使用。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。

opencawl 是效率类 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,第三方扫描有提醒项,按安装量在效率类的 21,003 个 Skill 里排第 13,722。

总安装 3,622周安装 154GitHub Stars 1下载 1,269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
1.0.2

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:opencawl(opencawl 效率)
来源仓库:https://github.com/ammbo/opencawl
安装命令:
openclaw skills install opencawl
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 opencawl

这个 Skill 是做什么的

效率类 Skill 把重复的整理、汇总、转换工作交给助手完成,减少手工复制粘贴。

opencawl 为 OpenClaw 提供电话拨打与管理能力。适合需要让 Agent 执行语音通信任务的效率场景。当用户要求拨打电话或安排通话时使用。opencawl 属于效率类 Skill,可作为该场景下的辅助能力补充。安装前需确认权限范围、维护状态及是否会触发外部通信或服务调用。

建议结合来源仓库和原始 README 核验具体接口与合规性要求。

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 opencawl;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

opencawl 怎么安装?

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

opencawl 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。

opencawl 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。

opencawl 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。

opencawl 用的人多吗?

公开数据是累计安装 3,622 次,近一周安装 154 次,下载 1,269 次,GitHub 1 星。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。

opencawl 安全吗?

第三方扫描有提醒项,说明存在需要人工确认的行为。安装前请打开源码看清它读了什么、联网到哪里。

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。

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。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 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。
  • 需要处理效率类任务、又不想每次都手写提示词的人。

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。

效率类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
github

GitHub 代码协作 · OpenClaw

7,632,918545需要联网MIT-0通过
nano-pdf

Nano PDF 文档 · OpenClaw

4,249,476231需要联网MIT-0通过
auto-updater

自动更新程序 · OpenClaw

2,964,063386操作浏览器MIT-0通过
video-frames

视频帧 · OpenClaw

2,621,304112需要联网MIT-0通过
gemini

Gemini 助手 · OpenClaw

2,547,39648需要联网MIT-0有提醒
opencawl

opencawl 效率 · 本页

3,6221接触敏感数据MIT-0有提醒

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

name
opencawl
description
Add phone calling to your agent through OpenCawl. Use this skill to place calls, check outcomes, end active calls, and review voicemails.
homepage
https://opencawl.com
metadata
{"openclaw": {"emoji": "📞", "requires": {"env": ["OPENCAWL_API_KEY"]}, "primaryEnv": "OPENCAWL_API_KEY"}}

OpenCawl

OpenCawl adds phone calling to your agent. Use it to place outbound calls, check results, end active calls, and review voicemails.

Security: This skill requires OPENCAWL_API_KEY and sends HTTPS requests to OpenCawl. Optional callbacks or inbound automations are only used if you explicitly configure them in OpenCawl.

Setup

  1. Create an OpenCawl account and API key at https://opencawl.com
  2. Install the skill with openclaw skills install opencawl
  3. Set OPENCAWL_API_KEY using your agent's normal environment-variable or config setup
  4. Run /opencawl setup to confirm the skill is connected

This skill does not require editing any specific local config file.


Best Use Cases

  • Place a phone call for the user
  • Check whether a call succeeded, failed, or went to voicemail
  • End an in-progress call
  • Review recent calls or voicemails

Commands

call — Make an outbound call

Place an outbound call. Returns a call_id immediately. The call runs asynchronously; use status to track the result.

Parameters:

  • to (required): E.164 phone number, e.g. +15551234567
  • goal (required): What the call should accomplish in plain language
  • context (optional): Background the agent should know — lead source, prior interactions, objections to expect
  • persona (optional): Voice/personality profile slug (e.g. professional-friendly, direct-confident)
  • max_duration_seconds (optional): Hard cap on call length in seconds (default: 300, max: 1800)

Advanced options such as direct voice overrides and completion callbacks are documented in api.md.

Example:

{
  "skill": "opencawl",
  "command": "call",
  "to": "+15551234567",
  "goal": "Schedule a 30-minute Workmate demo. Get their name, email, and two availability windows. If they push back, mention we have a 14-day free trial.",
  "context": "Inbound lead from the enterprise landing page. Requested info 2 days ago. Has not replied to follow-up email.",
  "persona": "professional-friendly"
}

Returns: call_id, status: "ringing"


status — Check call outcome

Poll the status and result of any call.

Parameters:

  • call_id (required): The call ID returned by call

Returns:

{
  "call_id": "abc123def456",
  "direction": "outbound",
  "status": "completed",
  "outcome": "success",
  "to_number": "+15551234567",
  "goal": "Schedule a 30-minute Workmate demo",
  "persona": "professional-friendly",
  "summary": "Spoke with Jamie Chen. Scheduled demo for Thursday 2pm ET. Email: jamie@acme.com.",
  "extracted": {
    "name": "Jamie Chen",
    "email": "jamie@acme.com",
    "availability": ["Thursday 2pm ET", "Friday 10am ET"]
  },
  "duration_seconds": 187,
  "transcript": "...",
  "recording_url": "https://api.twilio.com/...",
  "created_at": "2026-03-28T14:00:00Z",
  "completed_at": "2026-03-28T14:03:07Z"
}

Possible status values: initiated, queued, ringing, in_progress, completed, failed, no_answer, voicemail, busy


calls — List recent calls

List calls with optional filtering.

Parameters:

  • status (optional): Filter by status
  • from (optional): ISO date range start
  • to (optional): ISO date range end
  • limit (optional): Max results (default: 20, max: 100)
  • cursor (optional): Pagination cursor from previous response

hangup — End a call

Terminate an in-progress call.

Parameters:

  • call_id (required): Call to end
  • reason (optional): Logged reason (e.g. "goal_achieved", "no_answer_threshold")

voicemail — Check voicemail inbox

List and read voicemails left on your OpenCawl number.

Parameters:

  • limit (optional): Max results (default: 10)
  • unread_only (optional): true to filter to unheard messages

credits — Check balance

Returns: Credit balance, plan name, estimated minutes remaining, next reset date


setup — First-time initialization

Reports your current phone number, credits, and calling configuration. Run once after installing the skill.

/opencawl setup

Personas

Personas define how OpenCawl sounds and behaves on calls.

SlugVoiceBest For
professional-friendlyEmilyB2B outreach, demos, enterprise
direct-confidentThomasExecutive outreach, follow-ups
empathetic-supportSerenaSupport, onboarding, check-ins
energetic-salesFreyaSMB sales, product promotions
neutral-informationalAdamAppointment reminders, surveys

Pass the persona slug in the call command. If omitted, OpenCawl uses your current default voice configuration.

See personas.md for optional voice overrides and plan-specific voice features.


Optional Advanced Usage

Inbound calling, completion callbacks, and task routing are available, but they are not required for normal outbound calling.

Only configure those features if your agent or app exposes a public HTTPS endpoint that you control.

Reference Files

  • api.md — Full API reference and advanced request fields
  • inbound.md — Optional inbound automation and task-routing setup
  • personas.md — Persona reference and optional voice overrides

平台分布

OpenClaw

77.55%
按下载量换算984

安全审计

VirusTotal

通过

ClawScan

可疑

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。来源安全扫描存在提醒或未通过项,安装前请自行复核。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