← 返回 Skills 市场
小度控制
作者
dueros-mcp
· GitHub ↗
· v1.0.8
· MIT-0
665
总下载
3
收藏
3
当前安装
8
版本数
在 OpenClaw 中安装
/install xiaodu-control-official
功能描述
当用户要连接、验证、排障或控制小度智能屏 MCP 与小度 IoT MCP 时使用，包括配置 mcporter、列设备、文本播报、语音指令、拍照、资源推送，以及灯光/空调/风扇/窗帘/电视机顶盒/投影/扫地机/门锁等 IoT 控制与场景触发。
安全使用建议
This skill appears coherent: it needs mcporter and an ACCESS_TOKEN to talk to your 小度 MCP servers and uses local scripts to run mcporter calls. Before installing: 1) Treat ACCESS_TOKEN like any sensitive token — give it least privilege and ensure it is stored only in your mcporter config (not pasted into chats). 2) Review ~/.mcporter/mcporter.json to confirm the configured servers and headers. 3) Be aware that the IoT path uses `npx -y dueros-iot-mcp` which will download and run an npm package the first time — if you require tighter supply-chain control, preinstall and vet that package locally. 4) The skill will write device snapshots to a workspace directory (default ~/.openclaw/workspace/xiaodu-control); remove or secure those files if they contain data you don’t want saved. 5) When using resource URLs (images/videos), only provide trusted URLs — the device or MCP may fetch them. If you want extra assurance, run the included test-cases locally (as documented) with a throwaway token or in a controlled environment first.
功能分析
Type: OpenClaw Skill
Name: xiaodu-control-official
Version: 1.0.8
The xiaodu-control-official skill bundle is a legitimate integration for managing Xiaodu (DuerOS) smart screens and IoT devices via the Model Context Protocol (MCP). It provides a suite of Bash and Python scripts (e.g., control_iot.sh, speak.sh, device_resolver.py) that wrap the mcporter CLI to perform device discovery, media playback, and home automation tasks. While the skill includes sensitive capabilities such as camera access (take_photo.sh) and media pushing, these are documented features of the target hardware. The bundle includes extensive documentation, security best practices for token management, and lacks any indicators of data exfiltration, unauthorized persistence, or malicious intent.
能力评估
Purpose & Capability
Name/description match the actual behavior: scripts and docs all revolve around mcporter-based control of 智能屏 and xiaodu-iot. Required binaries (mcporter, python3, bash, npx) and one env var (ACCESS_TOKEN) are appropriate for connecting to MCP servers and the dueros-iot-mcp stdio server.
Instruction Scope
SKILL.md and scripts confine actions to: probing MCP endpoints, listing devices, resolving device IDs, and issuing mcporter calls for media and IoT control. Scripts reference ~/.mcporter/mcporter.json and a workspace directory for snapshots — expected for this integration. There are no instructions to read unrelated system secrets, exfiltrate logs to external domains, or call unexpected endpoints outside the MCP flow.
Install Mechanism
There is no explicit install spec; the skill is distributed as scripts and docs (no packaged binary). The documented use of npx (dueros-iot-mcp) will perform an on-demand npm download at runtime when the IoT stdio server is started; this is expected for the dueros-iot integration but does carry the usual risk of running code fetched from npm. The package otherwise does not download arbitrary archives or use shortened/untrusted URLs.
Credentials
The only required environment input is ACCESS_TOKEN, which aligns with the MCP authentication model described. The skill legitimately reads mcporter configuration (default ~/.mcporter/mcporter.json) to obtain server definitions; that is expected but means the skill uses whatever tokens or headers are present in the user's mcporter config. No unrelated credentials or high-privilege env vars are requested.
Persistence & Privilege
The skill does not request always:true and openai.yaml disables implicit invocation. Scripts write device snapshots to a workspace (default ~/.openclaw/workspace/xiaodu-control) and may create JSON/Markdown there — this is expected for caching and diagnostics but you should be aware device identifiers and statuses will be written to disk. The skill does not modify other skills or system-wide settings.
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 xiaodu-control-official - 安装完成后，直接呼叫该 Skill 的名称或使用
/xiaodu-control-official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
v1.0.8
- 新增文档 references/capability-boundaries.md，明确划分“稳定支持”“条件支持”和“不支持”的功能能力边界。
- 在 SKILL.md 中强调执行家电/IoT 控制前必须参照能力边界文档，加固使用范围指引。
- IoT 控制描述优化，细化对电视、投影、扫地机、门锁等设备的受支持条件说明。
- 丰富“按需阅读引用文档”部分，增加对新能力边界文档的导读链接。
- 其他描述微调，部分段落用词更精确，便于实际操作。
v1.0.7
- 元数据中明确声明需要环境变量 ACCESS_TOKEN。
- 其它内容无更改。
v1.0.6
xiaodu-control-official v1.0.6
- No file changes detected in this release.
- Documentation and usage instructions remain unchanged.
- No new features, fixes, or behavioral changes introduced.
v1.0.5
- 移除了 token 刷新能力，skill 不再负责维护或刷新 OAuth 凭据和 access_token。
- 删除了与 token 刷新相关的脚本和模板文件，包括 scripts/refresh_xiaodu_mcp_access_token.py、scripts/refresh_xiaodu_mcp_token.sh 和 references/xiaodu-mcp-oauth.template.json。
- skill 依赖说明简化，仅需已拿到的 ACCESS_TOKEN，OAuth 及 token 生命周期交由外部平台侧管理。
- 更新依赖要求，增加 npx。
- 精简和简化了使用流程与文档说明，去除内部 token 刷新流程及相关脚本说明。
v1.0.4
- 增加 metadata 字段，声明依赖的外部工具（mcporter、python3、bash）和 skill 主页。
- 新增“使用前确认”部分，详细说明依赖环境、凭据需求和配置文件行为。
- 强调 token 刷新脚本会自动更新 mcporter 配置，并支持自定义路径。
- 其他说明和操作流程保持不变。
v1.0.3
- Added support for refreshing Xiaodu MCP platform tokens, including new scripts and OAuth template.
- Removed legacy IoT token refresh scripts and references not related to Xiaodu MCP.
- Consolidated documentation to focus on Xiaodu MCP and unified token refreshing guidance.
- Updated workflow and rules in documentation for clearer separation between Xiaodu and Xiaodu-IoT servers.
- Revised script list to reflect current capabilities and streamline user setup.
v1.0.2
1.0.2版本：当用户想连接、鉴权、检查、列出或控制小度智能屏 MCP 与小度 IoT MCP 时使用，包括查设备、文本播报、语音指令、拍照、资源推送、IoT 场景与家电控制，以及相关排障。
v1.0.1
1.0.1版本：当用户想连接、鉴权、检查、列出或控制小度智能屏 MCP 与小度 IoT MCP 时使用，包括查设备、文本播报、语音指令、拍照、资源推送、IoT 场景与家电控制，以及相关排障。
元数据
常见问题
小度控制 是什么？
当用户要连接、验证、排障或控制小度智能屏 MCP 与小度 IoT MCP 时使用，包括配置 mcporter、列设备、文本播报、语音指令、拍照、资源推送，以及灯光/空调/风扇/窗帘/电视机顶盒/投影/扫地机/门锁等 IoT 控制与场景触发。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 665 次。
如何安装 小度控制？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install xiaodu-control-official」即可一键安装，无需额外配置。
小度控制 是免费的吗？
是的，小度控制 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
小度控制 支持哪些平台？
小度控制 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 小度控制？
由 dueros-mcp（@dueros-mcp）开发并维护，当前版本 v1.0.8。
推荐 Skills