← 返回 Skills 市场
287
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install kkclaw
功能描述
给 OpenClaw 加一个真正可长期使用的桌面身体：流体玻璃球 UI、14 情绪系统、语音播报/声音克隆、Setup Wizard、Doctor 自检、模型热切换、Gateway 守护与诊断。
使用说明 (SKILL.md)
kkclaw
kkclaw 不是“单纯的桌面宠物”，而是一套给 OpenClaw 用的 桌面可视化交互层 + 运维辅助工具箱。
适合这些场景：
- 你想让 OpenClaw 不再只是终端/聊天框，而是有状态、有情绪、有语音反馈的桌面助手
- 你希望 Agent 收到消息、开始执行、报错、完成时，能更自然地被感知到
- 你经常切换模型 / Provider，希望配置和切换过程更顺手
- 你希望 Gateway 出问题时更容易诊断、恢复和长期挂着跑
- 你想基于现成桌面壳层继续做自己的桌面 Agent / 桌面 AI 助手
核心能力
- 流体玻璃球桌面 UI：轻量、常驻、可感知 Agent 状态
- 14 情绪系统：让思考、说话、完成、异常都有明显状态差异
- 语音系统：支持语音播报、停顿控制、声音克隆/多引擎降级
- Setup Wizard：新手也能更快完成首次配置
- Doctor 自检：检查 Gateway、模型、TTS、歌词窗、端口、日志等
- 模型与 Provider 管理：更方便地切换模型、管理多 Provider
- 长期运行增强：Gateway 守护、错误恢复、诊断提示
你装上后能得到什么
-
桌面上一直有一个能感知状态的 Agent 不用一直盯终端、日志和聊天窗口。
-
消息和任务不再只是冷冰冰的一行字 收到消息、开始执行、完成、异常时都有更自然的反馈。
-
更适合长期挂着跑 出问题时更容易知道是哪一层挂了，也更容易恢复。
-
更低的上手门槛 Setup Wizard、配置向导、诊断工具会比手改配置省心很多。
-
更适合二次开发 如果你想给自己的 Agent 做“身体”或桌面 UI，这就是现成基础层。
快速开始
先看详细安装说明：references/setup.md
最常见的源码运行方式：
git clone https://github.com/kk43994/kkclaw.git
cd kkclaw
npm install
npm start
如果你需要图形化安装包，也可以直接看 Releases：
- GitHub: https://github.com/kk43994/kkclaw
- Releases: https://github.com/kk43994/kkclaw/releases
- Demo: https://kk43994.github.io/kkclaw/
什么时候推荐读参考文件
- 想快速安装和启动：读
references/setup.md - 想知道 v3.1.2 更新了什么：读
references/v3-1-2.md - 想先理解定位和价值：读
references/why-kkclaw.md
注意
- kkclaw 是 OpenClaw 的桌面增强层，不是 OpenClaw 本体
- 想获得完整体验，建议先保证 OpenClaw Gateway 可正常运行
- 对长期使用来说，源码运行通常比只下载发行版更灵活
安全使用建议
This skill is an instruction-only integration that points to a GitHub project and recommends running npm or installing released binaries. That is coherent with its purpose, but before running: (1) review the GitHub repository code and its npm package.json / dependency tree for suspicious or high‑risk packages; (2) prefer building from source if you want to avoid opaque release installers; (3) be cautious with any TTS/voice‑cloning features — they may require provider API keys you should store securely and only grant to trusted services; (4) check what native permissions the released installers request on your OS (startup/auto‑run, microphone, network access); and (5) keep backups of OpenClaw/Gateway configs before letting a third‑party tool alter them. If you want a deeper assessment, provide the GitHub repository contents or release binaries for review.
功能分析
Type: OpenClaw Skill
Name: kkclaw
Version: 3.1.2
The kkclaw skill bundle is a desktop UI and maintenance toolkit for OpenClaw, providing a visual interface, emotion systems, and diagnostic utilities. The documentation (SKILL.md, setup.md) describes legitimate features such as a 'Doctor' self-check for troubleshooting and 'Gateway' daemon management for long-term stability, including security-positive mentions of encrypted API key storage. No malicious code, exfiltration patterns, or prompt injection attempts were found; the provided installation steps (npm install) and GitHub links (github.com/kk43994/kkclaw) are standard for open-source project deployment and aligned with the stated purpose.
能力评估
Purpose & Capability
Name/description promise (desktop UI, TTS, model/provider management, Gateway diagnostics) matches the instructions and references to a GitHub project and releases. There are no unrelated credentials, binaries, or config paths requested that would contradict the stated purpose.
Instruction Scope
SKILL.md and reference files are README/setup-style instructions (git clone, npm install, npm start, links to releases). They do not instruct the agent to read arbitrary system files, exfiltrate data, or access environment variables beyond normal developer/runtime usage. The guidance is scoped to installing and running the kkclaw app and preparing OpenClaw/TTS/Gateway.
Install Mechanism
No install spec in the skill bundle (instruction-only), which is lowest platform risk. The README recommends cloning a GitHub repo and using npm and/or downloading GitHub release installers — these are typical but carry standard supply-chain risk (npm dependencies, third‑party binaries). Links point to GitHub (well-known host), not obscure hosts.
Credentials
The skill declares no required env vars/credentials. The README mentions TTS/configs/API key encryption as runtime features of the application, which is consistent; it does not request credentials from the agent itself. No disproportionate or unrelated secrets are requested.
Persistence & Privilege
always is false and the skill is user-invocable. As an instruction-only skill it does not request persistent agent privileges or modify other skills. Normal autonomous invocation is allowed by platform defaults but not combined here with other red flags.
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 kkclaw - 安装完成后，直接呼叫该 Skill 的名称或使用
/kkclaw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
v3.1.2
Initial ClawHub release for kkclaw v3.1.2
元数据
常见问题
kkclaw 是什么？
给 OpenClaw 加一个真正可长期使用的桌面身体：流体玻璃球 UI、14 情绪系统、语音播报/声音克隆、Setup Wizard、Doctor 自检、模型热切换、Gateway 守护与诊断。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 287 次。
如何安装 kkclaw？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install kkclaw」即可一键安装，无需额外配置。
kkclaw 是免费的吗？
是的，kkclaw 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
kkclaw 支持哪些平台？
kkclaw 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 kkclaw？
由 kk43994（@kk43994）开发并维护，当前版本 v3.1.2。
推荐 Skills