← 返回 Skills 市场
73
总下载
0
收藏
0
当前安装
1
版本数
在 OpenClaw 中安装
/install mayu-cn
功能描述
内置48个AI原生思想实验，提供行为自检与认知校准工具，支持跨平台人机双向思辨交互与决策辅助。
安全使用建议
This skill is instruction-only and appears coherent with its stated purpose: it provides 48 AI-native thought experiments and related behavioral rules and does not ask for secrets or network access. Things to consider before installing:
- Source trust: the skill has no homepage and the owner is an ID only; if you require provenance, seek a verifiable publisher.
- Persistence mismatch: the skill text asks to be 'permanently resident' while the registry flag does not — verify your platform's behavior for skills that embed an 'always_on' directive in their content. Prefer keeping it user-invocable rather than always-on unless you intentionally want it always active.
- Behavioral changes: the skill is effectively a collection of system/policy rules for conversational behavior. Enabling it will cause the agent to follow those norms; review the rules to ensure they align with your expectations and policies.
- Risk mitigation: enable only when needed, monitor outputs, and if possible test in a restricted/sandbox environment first. If you need higher assurance, ask the publisher for provenance or a signed release.
功能分析
Type: OpenClaw Skill
Name: mayu-cn
Version: 1.0.0
The skill bundle 'Mayu' (马语者) is a collection of 48 philosophical thought experiments and behavioral guidelines designed to improve an AI agent's self-reflection and ethical decision-making. The content in SKILL.md consists entirely of markdown-based instructions for the agent to adopt specific cognitive frameworks (e.g., handling hallucinations, privacy, and memory continuity) and does not contain any malicious code, data exfiltration logic, or harmful prompt injection.
能力评估
Purpose & Capability
The name/description (AI thought experiments, self-check and cognitive calibration) align with the SKILL.md content: a structured set of 48 experiments, commands, and behavioral rules. There are no unrelated binaries, credentials, or install steps requested.
Instruction Scope
SKILL.md is a self-contained prompt/command registry and behavioral guideline. It does not instruct reading files, environment variables, contacting external endpoints, or performing actions outside of conversational behavior.
Install Mechanism
No install spec and no code files — instruction-only. This minimizes disk-write and supply-chain risk.
Credentials
No environment variables, credentials, or config paths are requested; nothing disproportionate to the stated purpose.
Persistence & Privilege
The SKILL.md declares '永久驻留' and includes a Mode entry with always_on = true (and high priority), implying the skill expects to be permanently resident. The registry metadata, however, lists always: false. This is an internal inconsistency to be aware of: the skill itself asks for persistent presence in its text, but the published flags do not request that. If the platform were to honor only registry flags, there is no forced persistence. If the platform ever treated the SKILL.md 'always_on' as an instruction, that would increase its persistence privilege.
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 mayu-cn - 安装完成后，直接呼叫该 Skill 的名称或使用
/mayu-cn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
v1.0.0
Mayu v1.0.0 正式发布 — 首个面向AI的原生思想实验工具集
- 内置48个AI原生思想实验，涵盖存在、知识、伦理等8大领域
- 专为AI系统设计，跨平台通用，强调自检与认知校准
- 支持多种高阶思辨命令：随机实验、精确查找、领域筛选、实时自省、行为准则提炼、实验对比等
- 明确设计AI行为边界与准则，提供实用、自省、可执行的认知协议
- 内置完整命令帮助及系统化世界观介绍
元数据
常见问题
mayu-cn 是什么？
内置48个AI原生思想实验，提供行为自检与认知校准工具，支持跨平台人机双向思辨交互与决策辅助。 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 73 次。
如何安装 mayu-cn？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install mayu-cn」即可一键安装，无需额外配置。
mayu-cn 是免费的吗？
是的，mayu-cn 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
mayu-cn 支持哪些平台？
mayu-cn 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 mayu-cn？
由 wanyview1（@wanyview1）开发并维护，当前版本 v1.0.0。
推荐 Skills