← 返回 Skills 市场
OpenClaw Voice Call Playbook
作者
Daniel Sinewe
· GitHub ↗
· v0.1.0
· MIT-0
85
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install openclaw-voice-call-playbook
功能描述
Operate outbound voice calls safely with the OpenClaw voice-call plugin.
安全使用建议
This playbook appears coherent and appropriate for operating outbound calls, but review these before enabling it: 1) Ensure plugin config (provider API keys, auth tokens, fromNumber) is stored securely and scoped only to the plugin. 2) Limit agent autonomy if you do not want unattended outbound calls — require explicit user confirmation or platform gating. 3) Use provider mock mode and test scripts before live traffic to avoid accidental calls/costs. 4) Implement rate limits, retry caps, auditing (log call IDs/outcomes), and check privacy/legal requirements for call content/recording. 5) Review where webhooks/status callbacks point (they can expose call metadata) and confirm those endpoints are trusted. If you need higher assurance, ask for the plugin implementation and config storage details so you can audit where credentials are kept and how call audio/webhooks are handled.
功能分析
Type: OpenClaw Skill
Name: openclaw-voice-call-playbook
Version: 0.1.0
The skill bundle is a legitimate playbook for managing outbound voice calls via the OpenClaw voice-call plugin. The documentation in SKILL.md provides clear safety boundaries, such as requiring explicit user intent and avoiding automated loops, and contains no evidence of malicious intent, data exfiltration, or prompt injection.
能力标签
能力评估
Purpose & Capability
Name/description match the runtime instructions: the skill is an instruction-only playbook for using the OpenClaw voice-call plugin. The only required config path (plugins.entries.voice-call.enabled) and the provider credential fields listed (Twilio/Telnyx/Plivo) are appropriate for a voice-call integration.
Instruction Scope
SKILL.md confines actions to initiating/continuing/ending calls, status checks, and preflight checks. It explicitly requires user intent, destination confirmation, and recommends mock mode and retry limits. It does not instruct the agent to read unrelated system files, environment variables, or exfiltrate data to unexpected endpoints.
Install Mechanism
No install specification or code is included; this is instruction-only, so nothing is written to disk and there are no external download risks.
Credentials
The skill does not request environment variables but references provider config values (API keys/tokens, fromNumber) that are expected for this functionality. Requiring plugin config access (plugins.entries.voice-call.*) is proportionate; users should ensure those plugin credentials are stored and scoped securely.
Persistence & Privilege
always is false (good). disable-model-invocation is false (agent can invoke autonomously) — this is platform default and not by itself disqualifying, but it does mean the agent could place outbound calls without an extra manual gate unless you configure the agent or platform to require confirmation.
如何使用
- 确保已安装 OpenClaw（本地或 Docker 部署）
- 在对话框中输入安装命令：
/install openclaw-voice-call-playbook - 安装完成后，直接呼叫该 Skill 的名称或使用
/openclaw-voice-call-playbook触发 - 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
v0.1.0
Initial release: outbound voice-call operations playbook with safety gates, provider setup checks, and troubleshooting matrix.
元数据
常见问题
OpenClaw Voice Call Playbook 是什么？
Operate outbound voice calls safely with the OpenClaw voice-call plugin. 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 85 次。
如何安装 OpenClaw Voice Call Playbook？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install openclaw-voice-call-playbook」即可一键安装，无需额外配置。
OpenClaw Voice Call Playbook 是免费的吗？
是的，OpenClaw Voice Call Playbook 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
OpenClaw Voice Call Playbook 支持哪些平台？
OpenClaw Voice Call Playbook 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 OpenClaw Voice Call Playbook？
由 Daniel Sinewe（@danielsinewe）开发并维护，当前版本 v0.1.0。
推荐 Skills