← 返回 Skills 市场
82
总下载
0
收藏
0
当前安装
2
版本数
在 OpenClaw 中安装
/install unreasonable-hospitality
功能描述
Apply Will Guidara's 'Unreasonable Hospitality' + PDCA closed-loop feedback to AI product design, development, and interaction. Transforms products from func...
安全使用建议
This skill is primarily a written framework and checklist for making AI products more 'human' — it does not ask for credentials or install code. Before enabling it, review the SKILL.md and the included references to ensure the tone and recommendations match your product policies. Note: the guidance encourages using "context and history" for personalization; if your agent has access to sensitive connectors (email, drive, CRM), be mindful of what context the agent is allowed to use and ensure access controls and consent are appropriate. Otherwise, the skill appears coherent and proportionate to its stated purpose.
功能分析
Type: OpenClaw Skill
Name: unreasonable-hospitality
Version: 1.1.0
The 'unreasonable-hospitality' skill bundle is a purely instructional framework based on Will Guidara's hospitality principles for product design and AI interaction. It contains no executable code, scripts, or network calls. The instructions in SKILL.md and the reference files (principles.md, checklist.md) focus on improving user experience, empathy, and feedback loops without any indicators of malicious intent, data exfiltration, or prompt injection attacks.
能力评估
Purpose & Capability
The name and description describe product-design and AI-assistant hospitality guidance; the skill is instruction-only and only includes local reference documents and checklists that directly support that purpose. There are no unrelated dependencies or requested credentials.
Instruction Scope
SKILL.md contains prescriptive design guidance (7 laws, PDCA loop, checklists) and references two local files. It suggests using context/history when building assistants, which is appropriate for the stated purpose and does not explicitly instruct the agent to read system files, env vars, or send data to external endpoints.
Install Mechanism
There is no install spec and no code files — this is an instruction-only skill. Nothing is downloaded or written to disk by the skill itself.
Credentials
The skill requires no environment variables, credentials, or config paths. Its guidance about using user context/history is conceptual and not tied to any secret or credential requests.
Persistence & Privilege
The skill is not always-enabled (always: false) and uses the platform defaults for invocation. It does not request persistent system-level changes or modify other skills' configs.
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 unreasonable-hospitality - 安装完成后，直接呼叫该 Skill 的名称或使用
/unreasonable-hospitality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
v1.1.0
v1.1: PDCA closed-loop feedback system for sustaining hospitality. 5 metrics, closed-loop anti-patterns, 2 new principles (#13 Closed Loop, #14 Accountability Without Bureaucracy), 10 feedback checkpoints. Source: Guidara + PDCA synthesis.
v1.0.0
v1.0: Universal skill based on Will Guidara's book. 7 Laws + 12 Principles + Design Checklist + Anti-patterns + Scoring Framework. For AI assistants, UI/UX, copy, product review, onboarding.
元数据
常见问题
Unreasonable Hospitality 是什么？
Apply Will Guidara's 'Unreasonable Hospitality' + PDCA closed-loop feedback to AI product design, development, and interaction. Transforms products from func... 它是一个面向 Claude Code / OpenClaw 的 AI Agent Skill 插件，目前累计下载 82 次。
如何安装 Unreasonable Hospitality？
在 OpenClaw 或 Claude Code 对话框中运行命令「/install unreasonable-hospitality」即可一键安装，无需额外配置。
Unreasonable Hospitality 是免费的吗？
是的，Unreasonable Hospitality 完全免费，采用 MIT-0 许可证，可自由下载、安装和使用。
Unreasonable Hospitality 支持哪些平台？
Unreasonable Hospitality 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 Unreasonable Hospitality？
由 ZackO2o（@zacko2o）开发并维护，当前版本 v1.1.0。
推荐 Skills