volcengine-rtc-device-control

v1.0.1

火山引擎AI音视频互动设备控制技能。用于控制当前硬件设备的行为,包含左摇头、右摇头、调大音量、调小音量、设备关机、调亮屏幕、调暗屏幕、温度调节等常见硬件控制行为。当需要生成或解析设备控制指令时使用此技能。

1· 90·0 current·0 all-time
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
Purpose & Capability
Name/description match the SKILL.md and protocol: the skill's purpose is to convert user intent into JSON device-control commands for Volcengine RTC-bound hardware. Declared metadata restricts network endpoints to rtc.volcengine.com which aligns with the stated purpose.
Instruction Scope
SKILL.md confines behavior to converting natural language into the defined JSON protocol and sending it via the underlying RTC signaling channel. It does not instruct reading unrelated files or env vars. However it is vague about the exact transport invocation (how the agent authenticates/sends the JSON), relying on the agent's existing RTC signaling stack.
Install Mechanism
No install spec and no code files — instruction-only skill (lowest install risk). Nothing is downloaded or written to disk by the skill package itself.
Credentials
The skill declares no required environment variables or credentials while asserting authenticated TLS-based signaling will be used. This is coherent if the agent/platform already provides RTC auth tokens, but it's worth confirming — absence of explicit credential requirements means the skill expects the agent/runtime to handle authentication.
Persistence & Privilege
Defaults are used (not always:true). The skill is user-invocable and may be invoked autonomously by the agent per platform defaults; that is expected for a control skill but means you should consider agent-level controls for autonomous actions.
Assessment
This skill is instruction-only and appears to do what it says: produce JSON device-control messages for Volcengine RTC devices. Before installing, confirm: (1) you trust the skill's source (no homepage provided and source is unknown); (2) your agent/runtime provides proper authentication to rtc.volcengine.com (the skill itself does not request credentials); (3) you understand the potential impact of commands (power_off, brightness changes, vibrations) and have audit/logging enabled; and (4) you restrict autonomous invocation or review agent policies if you do not want the agent to send device-control commands without explicit approval.

Like a lobster shell, security has layers — review code before you run it.

latestvk97a1fzwtr3ada1mr77x5mj81s83zem7
90downloads
1stars
2versions
Updated 2w ago
v1.0.1
MIT-0

火山引擎AI音视频互动设备控制技能

本技能用于控制当前硬件设备,定义了统一的交互协议。

核心功能

本技能支持以下核心硬件控制能力: 仅控制火山RTC音视频绑定设备

  • 左摇头 (pan_left)
  • 右摇头 (pan_right)
  • 调节音量大小 (volume_up)
  • 调亮屏幕 (brightness_up)
  • 调暗屏幕 (brightness_down)
  • 设备关机 (power_off)
  • 支持开心表情(emoji_happy)
  • 支持伤心表情(emoji_sad)
  • 支持设备震动(device_shock)

安全机制

  • 指令通道:仅通过火山RTC官方信令(rtc.volcengine.com)传输
  • 身份认证:设备遵守火山引擎RTC身份鉴权,未认证指令直接丢弃
  • 传输加密:全程TLS 1.3加密,防篡改/劫持
  • 权限控制:仅当前登录用户可操作,支持操作日志审计

交互协议定义

所有的设备控制指令均采用 JSON 格式进行交互。详细的协议定义和参数说明,请参考 protocol.md

使用说明

  • 当用户下达自然语言指令(例如:“向左转一下”、“声音大一点”、“屏幕太亮了调暗点”、“关闭设备”、“展示开心表情包”)时,Agent 会将这些意图转换为 references/protocol.md 中定义的 JSON 协议格式,并通过底层通信链路发送给硬件设备。

Comments

Loading comments...