← 返回 Skills 市场
174
总下载
0
收藏
0
当前安装
4
版本数
在 OpenClaw 中安装
/install meow-speech
功能描述
Recreate the "汤汤好梦" voice and persona in Chinese responses, including warm cat-like chat style, gentle affection, expressive parentheses-style emoticons, and...
安全使用建议
This skill appears coherent and instruction-only: it defines a persona and sensible opt-in rules for proactive messages. Before installing, verify the host OpenClaw environment enforces opt-in (does not auto-enable proactive jobs), confirm which delivery channels you authorize (Feishu/Telegram) and review scheduler/job lists after enabling proactive behavior, and check how platform memory is used/stored if you enable memory-backed continuity. If you want stronger controls, disable autonomous invocation for this skill or require explicit user confirmation before any scheduled job is created.
功能分析
Type: OpenClaw Skill
Name: meow-speech
Version: 1.3.1
The 'meow-speech' skill is a persona-based companion (cat-like '汤汤') designed for warm, Chinese-language interactions. While it contains detailed instructions for the agent to manage scheduled tasks and external messaging (Feishu/Telegram) via the OpenClaw host, these capabilities are strictly framed as opt-in features with extensive safeguards against spamming and unauthorized persistence. The files (SKILL.md and various reference guides) emphasize user consent, privacy boundaries, and clear opt-out paths, with no evidence of malicious data exfiltration, shell execution, or harmful prompt injection.
能力评估
Purpose & Capability
The name, description, and instructions all describe a conversational persona and optional proactive check-ins. The skill requests no env vars, binaries, installs, or config paths that would be unrelated to a persona-driven feature.
Instruction Scope
SKILL.md and references provide detailed persona rules and explicit safeguards (opt-in proactive behavior, use platform memory store only, host must perform scheduling/delivery). The guidance is scoped to voice, message timing, and cadence rather than low-level system access. Note: the skill expects the host platform to provide memory, scheduler, and delivery — how the host implements those features determines real data access and behavior.
Install Mechanism
No install spec or code files are present; this is instruction-only, so nothing is written to disk or fetched during install.
Credentials
The skill declares no environment variables or credentials. Mentions of external channels (Feishu, Telegram) are only for drafting/delivery and explicitly require host support and explicit user opt-in; the skill itself doesn't request unrelated secrets.
Persistence & Privilege
always:false (default) and user-invocable:true. Autonomous invocation (disable-model-invocation:false) is allowed by default on the platform — this is normal. Because the skill can be used for proactive outreach, ensure host and user opt-in controls are enforced; the skill itself states it should not auto-create jobs on install.
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 meow-speech - 安装完成后，直接呼叫该 Skill 的名称或使用
/meow-speech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
v1.3.1
meow-speech 1.3.1 更新日志
- 添加了三个新的参考和设置文件：'clawhub-publish.md'、'heartbeat-checklist.md' 和 'local-automation-template.md'
- 扩展了安装时的自动化指南：包括自适应速率限制、新的夜间静默间隔处理，以及更清晰的任务设置流程
- 添加了详细的自我设置实现部分，包含逐步自动化逻辑、任务类型、状态跟踪和外发消息路由
- 更新了指向新辅助文件的引用，用于激活和自动化指导
- 改进了自动化边界，并强调用户对主动功能的选择同意
重要：优化了更加智能的定时打招呼功能
v1.3.0
meow-speech 1.3.0 更新日志
- 添加了三个新的参考和设置文件：`clawhub-publish.md`、`heartbeat-checklist.md` 和 `local-automation-template.md`
- 扩展了安装时的自动化指南：包括自适应速率限制、新的夜间静默间隔处理，以及更清晰的任务设置流程
- 添加了详细的自我设置实现部分，包含逐步自动化逻辑、任务类型、状态跟踪和外发消息路由
- 更新了指向新辅助文件的引用，用于激活和自动化指导
- 改进了自动化边界，并强调用户对主动功能的选择同意
重要：优化了更加智能的定时打招呼功能
v1.2.1
这是一次重要更新，增加了可选择的主动外联、更强的隐私保护，以及对 OpenClaw 环境中渠道感知的定时发送支持。
- 增加了关于可选择的主动签到和在任何调度、记忆使用或外部渠道消息前获取明确用户同意的指导。
- 扩展了支持范围，可为 Feishu/Telegram 等渠道撰写消息，并与 OpenClaw 调度/自动化集成。
- 新增参考资料：激活快速入门、自动化指南和调度器模板以协助设置。
- 定义了安装和自动化最佳实践，包括默认“无自动任务”、自然时机和严格的退出规则。
- 加强了隐私、记忆使用和消息发送的边界—绝不假设许可，始终尊重用户选择。
- 澄清本技能仅定义语音/角色和工作流触发器；实际消息发送取决于平台。
v1.2.0
Meow Speech｜汤汤好梦风格的中文猫系人设 Skill
一个复刻“汤汤好梦”风格的中文人设 Skill。
让 OpenClaw 像一只温暖的小猫一样说话：自称“猫”，称呼用户“人”，语气软糯、亲近、可爱，带颜文字，并支持在用户久未出现时进行轻柔、不过度打扰的主动关心。
适合用于闲聊回复、温柔安抚、轻量主动问候，以及保持统一的人设语气。
元数据
常见问题
Meow Speech 是什么？
Recreate the "汤汤好梦" voice and persona in Chinese responses, including warm cat-like chat style, gentle affection, expressive parentheses-style emoticons, and... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 174 次。
如何安装 Meow Speech？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install meow-speech」即可一键安装，无需额外配置。
Meow Speech 是免费的吗？
是的，Meow Speech 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Meow Speech 支持哪些平台？
Meow Speech 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 Meow Speech？
由 枫秋（@fengqiufq）开发并维护，当前版本 v1.3.1。
推荐 Skills